In this guided coding session we will be using a small dataset to illustrate how to identify latent communities in networks. The dataset corresponds to the Twitter ego network of RECSM_UPF – each node is another Twitter account that this Twitter account follows, and the edges indicate whether each of those accounts in turn follow each other. (See at the end of this script for the code on how I put together this network.) Edges are thus directed.
The first step is to read the list of edges and nodes in this network:
edges <- read.csv("../data/recsm-edges.csv", stringsAsFactors=FALSE)
head(edges)## Source Target
## 1 100065631 101710163
## 2 100065631 1025315378
## 3 100065631 107148161
## 4 100065631 1184096065
## 5 100065631 1196671592
## 6 100065631 1212365359nodes <- read.csv("../data/recsm-nodes.csv", stringsAsFactors=FALSE)
head(nodes)## Id Label name
## 1 100065631 MikeKawula Mike Kawula \U0001f334\U0001f428\U0001f334
## 2 1001390960 ResearchGermany Research in Germany
## 3 1008658832 Datafloq Datafloq
## 4 1009369783 SowiLady Angelika Scheuer
## 5 1014378523 TysonGingery Tyson Gingery
## 6 101710163 el_gordo_ Carlos Rachedi
## description
## 1 Entrepreneur, Author, Inc 500\U0001f64f CEO \U0001f60e Top 100 Marketing Influencer \U0001f449 Co-Host of Entrepreneurs GSD Podcast https://t.co/XHeBPFPCnu Co-Founder @DinnerTableMBA
## 2 Information about research and funding opportunities, open PhD and research positions, news and upcoming events in Germany. Imprint: https://t.co/Uyy8Jxv4c5
## 3 Datafloq is the one-stop source for #BigData, #blockchain & #AI. We offer information, insights & opportunities to drive innovation with emerging technologies.
## 4 Social scientist & survey researcher at @gesis_org - Deputy Director Scientific at European Social Survey (ESS ERIC)
## 5 Survey Research. Polls. Sports. Food. Data. Media. Funnies. Saffy the Dog.
## 6 #ecommerce, digital, online marketing, mobile, social. https://t.co/abDeYwwRcN e-commerce, SEO. Online #leadmanagement #socialselling #Inbound Stmicroelectronic
## followers_count statuses_count friends_count
## 1 113700 125362 70651
## 2 46745 28245 370
## 3 34529 63959 3946
## 4 104 64 106
## 5 105 966 725
## 6 8395 51083 8965
## created_at location
## 1 Mon Dec 28 22:36:58 +0000 2009 Tampa, FL
## 2 Mon Dec 10 10:31:43 +0000 2012 Germany
## 3 Thu Dec 13 12:03:23 +0000 2012 Global
## 4 Thu Dec 13 17:52:09 +0000 2012 Mannheim, Germany
## 5 Sun Dec 16 03:02:12 +0000 2012 San Diego, CA
## 6 Mon Jan 04 09:17:41 +0000 2010 Aix-en-Provence, FranceWe will now convert these two datasets into a network object in R using igraph.
library(igraph)
g <- graph_from_data_frame(d=edges, vertices=nodes, directed=TRUE)
g## IGRAPH 143e2e6 DN-- 828 18406 --
## + attr: name (v/c), Label (v/c), description (v/c),
## | followers_count (v/n), statuses_count (v/n), friends_count
## | (v/n), created_at (v/c), location (v/c)
## + edges from 143e2e6 (vertex names):
## [1] Mike Kawula \U0001f334\U0001f428\U0001f334->Carlos Rachedi
## [2] Mike Kawula \U0001f334\U0001f428\U0001f334->Questions Consulting
## [3] Mike Kawula \U0001f334\U0001f428\U0001f334->NASSER ALOJAIBY
## [4] Mike Kawula \U0001f334\U0001f428\U0001f334->MaryLù Cinquerrui
## [5] Mike Kawula \U0001f334\U0001f428\U0001f334->Tim Hughes
## [6] Mike Kawula \U0001f334\U0001f428\U0001f334->equastat.com
## + ... omitted several edgesWhat does it mean? - U means undirected
- N means named graph
- 902 is the number of nodes
- 13606 is the number of edges
- name (v/c) means name is a node attribute and it’s a character
Networks often have different clusters or communities of nodes that are more densely connected to each other than to the rest of the network. Let’s cover some of the different existing methods to identify these communities.
The most straightforward way to partition a network is into connected components. Each component is a group of nodes that are connected to each other, but not to the rest of the nodes. For example, this network has only one component (every node is at least connected to one other node in the network).
components(g)## $membership
## Mike Kawula \U0001f334\U0001f428\U0001f334
## 1
## Research in Germany
## 1
## Datafloq
## 1
## Angelika Scheuer
## 1
## Tyson Gingery
## 1
## Carlos Rachedi
## 1
## Questions Consulting
## 1
## Pep Lobera
## 1
## Kiko Llaneras
## 1
## AnticsUPF
## 1
## Nick Emmel
## 1
## Doc Washburn
## 1
## Sociología Práctica
## 1
## Universia España
## 1
## Claire Durand
## 1
## Dr. Kapil Bansal
## 1
## CSES
## 1
## Liang Wang
## 1
## Mike McCulloch
## 1
## Uri Simonsohn
## 1
## Luis Cornago
## 1
## Ineke Stoop
## 1
## UCL Institute of Education
## 1
## NASSER ALOJAIBY
## 1
## Business Strategy
## 1
## Prerit Saxena
## 1
## Fondazione Brodolini
## 1
## Alexander P. Gage
## 1
## United Way of LebCo
## 1
## Universidad Córdoba
## 1
## Universitat València
## 1
## Stata
## 1
## Antonio Arciniega
## 1
## J Box-Steffensmeier
## 1
## Mike Beder
## 1
## Factam IS
## 1
## Christian Kirschniak
## 1
## David Rothschild
## 1
## Raül Tormos
## 1
## Supriyo B Chatterjee
## 1
## Social Research Hub
## 1
## Marco Brambilla
## 1
## EAE Business School
## 1
## FES Sociología
## 1
## CESOP
## 1
## octa\U0001f49aio
## 1
## Pew Research Journalism
## 1
## Ioannis Andreadis
## 1
## Eric Harrison
## 1
## Lina González
## 1
## Kenneth Benoit
## 1
## Mike Hine
## 1
## Alexandru Cernat
## 1
## Michael Dimock
## 1
## Idoia Portilla
## 1
## RayPoynter
## 1
## Parametría
## 1
## Rodolfo Rivera
## 1
## APSA & ICA Political Communication Divisions
## 1
## WAPOR
## 1
## Pau Marí-Klose
## 1
## Robert Pinter
## 1
## OpenPop.org
## 1
## Gabriel Castagnino
## 1
## Aneta Piekut
## 1
## MaryLù Cinquerrui
## 1
## Mark Amos
## 1
## Wouter Zwysen
## 1
## andrea fumarola
## 1
## Tim Hughes
## 1
## Statistics Ireland
## 1
## Carla Gentry
## 1
## IECA
## 1
## Roger Senserrich
## 1
## leon morton
## 1
## Gudbjorg Andrea Jons
## 1
## equastat.com
## 1
## Ahilan MK
## 1
## Mick Wagner
## 1
## Dr Joanne Greenhalgh
## 1
## Incorrigible FCA
## 1
## Johan Braeken
## 1
## Brent Thompson
## 1
## NATSEM
## 1
## UCLM
## 1
## Ciências Sociais
## 1
## Ignacio Jurado
## 1
## Biomedicina BCN
## 1
## MissSmarty:Plants
## 1
## Randy Bartlett
## 1
## CLIK
## 1
## Simon Munzert
## 1
## Ciències Polítiques i Sociologia
## 1
## IBES
## 1
## Social Sci @WesternU
## 1
## Mark Eaves
## 1
## ISI
## 1
## Mario Callegaro
## 1
## Humanitats UPF
## 1
## eKonomicus
## 1
## Dr. Sunshine Menezes
## 1
## Brice Escarguel
## 1
## politiquesupf
## 1
## ieextremadura
## 1
## Josh De La Rosa
## 1
## Peter Lugtig
## 1
## Mark Tabladillo
## 1
## Remco Ploeg
## 1
## rich murnane
## 1
## Daniel Liria Campón ۞♀
## 1
## Маx
## 1
## inside-R Community
## 1
## Loeffler Antiques
## 1
## Paul Thoresen
## 1
## Colegio de Sociología y Politología de Navarra
## 1
## Dan Hedlin
## 1
## Dr. Vanessa Higgins
## 1
## Lorena Recabarren
## 1
## ECPR
## 1
## Becarios 'la Caixa'
## 1
## Bob Lee \U0001f30a\U0001f30a\U0001f30a
## 1
## Patrick Dunleavy
## 1
## World Values Survey
## 1
## Toni Gril
## 1
## CityLIS
## 1
## Universidad Zaragoza
## 1
## ESRA
## 1
## DIW Berlin
## 1
## EPSA
## 1
## Niels \U0001f4c8
## 1
## Julio Burdman
## 1
## SusanMarieMartin PhD
## 1
## Nicolás Tereschuk \U0001f1e6\U0001f1f7
## 1
## Betty Adamou
## 1
## Pranay Roy ☃️
## 1
## PSSRU at Kent
## 1
## Pneuron Corporation
## 1
## Andrew Mercer
## 1
## Adam M. Lippert
## 1
## Epoché
## 1
## datakey
## 1
## Albert Julià Cano
## 1
## Andy Kirk
## 1
## Horizon 2020\U0001f1ea\U0001f1fa
## 1
## Basilio M. P.
## 1
## Cathleen M. Stuetzer
## 1
## Lluís Orriols
## 1
## Universidad de León
## 1
## Harvard Sociology
## 1
## Chris Morley, PhD
## 1
## Herodato
## 1
## Ben Carlos Thypin
## 1
## Stas Kolenikov
## 1
## Amanda Lenhart
## 1
## jasonrhody
## 1
## Rich Clark
## 1
## Maria Laura Tagina
## 1
## M. José
## 1
## Michael Link
## 1
## Richard Iannone
## 1
## Recerca
## 1
## Juan Font Alonso
## 1
## Jane McCarthy \U0001f340
## 1
## Universitat Jaume I
## 1
## R-bloggers
## 1
## charliemansell
## 1
## Universidad Granada
## 1
## Brendan Halpin
## 1
## GESIS
## 1
## Joanna Bryson 2
## 1
## Pradyot Rai
## 1
## Social Trends Inst.
## 1
## Talan ★ Innovation
## 1
## Palmer Gibbs
## 1
## Andy Hall
## 1
## Olivier MZD\U0001f310
## 1
## Eva Zeglovits
## 1
## Roeland Beerten
## 1
## Tim Gollins
## 1
## Craig Mullins
## 1
## Strikedeck
## 1
## Jorge Galindo
## 1
## Wittgenstein Centre
## 1
## Ctr for Political St
## 1
## Encuestas MURAL
## 1
## ORCID Organization
## 1
## BambergSocialScience
## 1
## Manikant Rajput *
## 1
## UNStats
## 1
## Jessica Broome
## 1
## UOC
## 1
## ESADE
## 1
## annie feighery
## 1
## Jill Sheppard
## 1
## Elena Costas Pérez
## 1
## David McCulloch
## 1
## Coosje L.S. Veldkamp
## 1
## SpaethCommunications
## 1
## Alexandre Lopez
## 1
## Evan Powell
## 1
## NIDI
## 1
## Gauri Salokhe
## 1
## Estadistica
## 1
## Hiver
## 1
## Score and Change
## 1
## C.J. Anderson
## 1
## Sergi Sergiev
## 1
## Jeffrey Henning
## 1
## Obra Social la Caixa
## 1
## Leslie Chan
## 1
## Research & Twitts
## 1
## Aaron Bergstrom
## 1
## Francesco C Billari \U0001f1ea\U0001f1fa\U0001f1ee\U0001f1f9
## 1
## Univ. de Huelva UHU
## 1
## Anna Manning
## 1
## Kurt Muehmel
## 1
## Estadística La Rioja
## 1
## DataCamp
## 1
## Jean Pak
## 1
## Steven R Clark
## 1
## Jorge San Miguel Lobeto
## 1
## Molly Roberts
## 1
## Bill Nigh
## 1
## InvestigaOnline.com (R.Gil)
## 1
## YouThisMe
## 1
## Heini Väisänen
## 1
## Social Research Assn
## 1
## kevinfarley
## 1
## AXA Research Fund
## 1
## Natalia da Silva
## 1
## Gonzalo Rivero
## 1
## Wojciech Jablonski
## 1
## Nielsen
## 1
## Nate Silver
## 1
## Thomas J. Leeper
## 1
## Jesse Holcomb
## 1
## insight-intelligence
## 1
## UOC universidad
## 1
## UOC university
## 1
## Carolina Plescia
## 1
## NSD
## 1
## PSSRU at Manchester
## 1
## Big Data & Society
## 1
## Netquest
## 1
## Steve Kerr
## 1
## Patricia Behisa ★
## 1
## björn buß
## 1
## Complex Systems Lab
## 1
## Fernanda K O Palermo
## 1
## Ernesto Treviño Ronz
## 1
## Our Fare Is Fair™
## 1
## LERU
## 1
## Pedro Magalhães
## 1
## Digital Marketing
## 1
## Natalie Bennett
## 1
## Chitra Chaudhuri
## 1
## Worka Holic
## 1
## Carreres Professionals UPF
## 1
## Alexander Wenz
## 1
## mysurveylab
## 1
## mobiusmedia
## 1
## Stefanie Hoherz \U0001f1ea\U0001f1fa
## 1
## Nick Allum
## 1
## BleuPage Pro
## 1
## Francesc García
## 1
## Pew Research Internet
## 1
## IPUMS International
## 1
## Modesto Escobar
## 1
## Universidad UDIMA
## 1
## Universidad Murcia
## 1
## Opinno
## 1
## Universidad de Navarra
## 1
## Pedro Muñoz del Río
## 1
## Pablo Simón
## 1
## Angelo N Ferrara DC
## 1
## Philip S. Brenner
## 1
## Emilio Ferrara
## 1
## Georgiann Baldino
## 1
## Daniël Lakens
## 1
## Iara VPS
## 1
## SmartData Collective
## 1
## elizabethpark
## 1
## Teresa Colquitt
## 1
## John D. Cook
## 1
## Management Class
## 1
## John Palmer
## 1
## Jeff Leek
## 1
## Ramkumar
## 1
## Malcolm Isaacs
## 1
## unican.es
## 1
## NTU Politics and IR
## 1
## Marieke Haan
## 1
## Wilde Agency
## 1
## Ignacio Ramirez
## 1
## keithbolam
## 1
## Michael Bosnjak
## 1
## CrossValidated
## 1
## Ulrich Krieger
## 1
## Ricardo Montes B
## 1
## ASA Sociology
## 1
## AAPOR
## 1
## ESRC International Centre for Lifecourse Studies
## 1
## jose ramon albert
## 1
## Cristóbal Martínez
## 1
## Carles Dijous (AAlb)
## 1
## Colpolsoc-Andalucía
## 1
## Elegant Science
## 1
## Langer Research
## 1
## Tavlesh
## 1
## Political Analysis
## 1
## Interactive Data Lab
## 1
## Empirica
## 1
## Adam Swift
## 1
## Annika Coughlin
## 1
## Andres Lazaro Lopez
## 1
## Universitat de Barcelona
## 1
## Eloy Pascal
## 1
## Lorena González
## 1
## Vrije Universiteit Amsterdam
## 1
## Policy Studies Inst
## 1
## Michael Meotti
## 1
## CSIC
## 1
## Dale Barr
## 1
## Sílvia Claveria
## 1
## Martijn Schoonvelde
## 1
## Alexey Mitkin
## 1
## Alessandra Decataldo
## 1
## Jon Burton
## 1
## AgE de Investigacion
## 1
## CJ Bowen
## 1
## Sociology@Oxford
## 1
## ESRC
## 1
## Ruben van Gaalen
## 1
## Via Evaluation
## 1
## Ross Morley
## 1
## AleCarioli
## 1
## Empiria
## 1
## Amelia McNamara
## 1
## Lisa Rutherford
## 1
## Ana Slavec\U0001f426
## 1
## Francesco Bartolucci
## 1
## ECSR Sociology
## 1
## Lewis
## 1
## Bernd Weiss
## 1
## Tim Huijts
## 1
## Dr. Annie Rights Research
## 1
## Yanna Stefanu
## 1
## Abel Coronado
## 1
## Sociology Theory
## 1
## Significance
## 1
## Casper Albers
## 1
## Result Logix
## 1
## Revista Mètode
## 1
## Lluís Coromina Soler
## 1
## CIPPEC
## 1
## Antsy Ant Web Design
## 1
## Gale Pryor
## 1
## AASCU Policy
## 1
## Sebastián Lavezzolo
## 1
## Universitat Andorra
## 1
## Levente Littvay
## 1
## MDMroczkowski
## 1
## Baird Group
## 1
## Oludele Olabisi
## 1
## Jana Javornik
## 1
## Cathy Harrison
## 1
## Paul Long
## 1
## Andrew Gelman
## 1
## chi2innovations
## 1
## #hellomynameis Rus Clark\u2695
## 1
## Lillian D'Costa
## 1
## Liliana Arroyo
## 1
## Gerardo Maldonado
## 1
## U-M ISR
## 1
## Georgiana Bostean
## 1
## Julie Brown
## 1
## Ronald Musizvingoza
## 1
## Opvizor
## 1
## LeeMMBJack McCarty
## 1
## Gerry Nicolaas
## 1
## #SherDilKejriwal
## 1
## carsten frömel
## 1
## Holger Mueller
## 1
## New Slave
## 1
## Ugofilippo Basellini
## 1
## SurveyCTO
## 1
## AngeliqueV
## 1
## Dr Lea Shanley
## 1
## Simon Porter
## 1
## The DR K-12 Network
## 1
## Idea8ion
## 1
## Ariadna Fernández
## 1
## Ravi
## 1
## Aleksander Beryozkin
## 1
## 4273π
## 1
## Paul Naish
## 1
## economiquesupf
## 1
## Damiano Uccheddu
## 1
## Susanna Gerritse
## 1
## Cardiff Q-Step
## 1
## Population Europe
## 1
## RStudio
## 1
## Sameera Jade Daniels
## 1
## FB Network
## 1
## Better Surveys
## 1
## CRC Digital
## 1
## Caucus of Working Ed
## 1
## Arnold Haine
## 1
## Eiji Matsuda
## 1
## Beth Tracy
## 1
## Yfke \U0001f609ngena
## 1
## UCF Tech Transfer
## 1
## IGPA
## 1
## Matthew Lamons
## 1
## UPF Barcelona
## 1
## P.A.BLO.UCM
## 1
## Laura Ronkainen
## 1
## Chris Casale
## 1
## NCRM
## 1
## Andreas Lenz
## 1
## MedPro Group
## 1
## UM SurveyMethodology
## 1
## Anna de Castellarnau
## 1
## Pablo Fdez-Vazquez
## 1
## trafficono.me
## 1
## Florian Keusch
## 1
## TSE15 Conference
## 1
## CompleteMktg
## 1
## Thijs Jansen
## 1
## Cameron Thies
## 1
## Delta Sales
## 1
## bruno arpino
## 1
## Vox Media México
## 1
## Guillermo Cordero
## 1
## Jessi Bishop-Royse
## 1
## MMU Q-Step
## 1
## Annika Sehl
## 1
## Jorge Cimentada
## 1
## Albert Putnam
## 1
## Sergi Vidal
## 1
## Insights Association
## 1
## Free Speech For All
## 1
## bookmarkxpress
## 1
## Social Problems
## 1
## Enda Ridge
## 1
## Jorge Luis
## 1
## Adam Bulley
## 1
## IHAWKES
## 1
## RONAK SHAH
## 1
## Oriol Llauradó
## 1
## QMSS at Columbia
## 1
## JIPS PCT
## 1
## ACER
## 1
## Matthias Nolte
## 1
## UCL Q-Step Centre
## 1
## Hajo Boomgaarden
## 1
## Dave
## 1
## John Tomlinson
## 1
## Danilo Serani
## 1
## The IBM MSP Team
## 1
## Stata UK
## 1
## Josep Niubò
## 1
## Rafa Grande
## 1
## Working Washington
## 1
## PASCAL Observatory
## 1
## Zoltan Fazekas
## 1
## Real KM Magazine
## 1
## B2B Listings
## 1
## Robert Napoli
## 1
## ESCI-UPF
## 1
## JohnWaldronMIW
## 1
## Lucas Gortazar
## 1
## Frederic Guerrero-Solé
## 1
## Biblioteca CRAI UPF
## 1
## CUQM
## 1
## Mathias Golombek
## 1
## WheelHealthcare ☤
## 1
## SAS Can Academic
## 1
## chris goswami
## 1
## Emilio Zagheni
## 1
## CoEBigData
## 1
## Tim Hughes 提姆·休斯
## 1
## Jason Ryckman
## 1
## Community Scene
## 1
## ChallengeData
## 1
## Scott Clifford
## 1
## Demografía (CSIC)
## 1
## GYFAL
## 1
## UConn SurveyResearch
## 1
## Jari Lyytimäki
## 1
## TxGenJobs
## 1
## The_Quipper
## 1
## UCL Big Data
## 1
## Kyley McGeeney
## 1
## Alina Vranceanu
## 1
## Marcel Wigert
## 1
## Dr Fabian Cannizzo
## 1
## Natalia Capel
## 1
## Kyle Chapman
## 1
## Josip Bronzaruka
## 1
## Hugo Alatrista Salas
## 1
## VETs Rising
## 1
## Benoît Ruiz
## 1
## Blue Lizard Media
## 1
## OSKA research
## 1
## Dominic McSherry
## 1
## RUDAHANGARWA Ignace
## 1
## André Pirralha
## 1
## Social Research @ANU
## 1
## Bart Meuleman
## 1
## Delphos Nudge Unit
## 1
## Craig McAngus
## 1
## MarketSight, LLC
## 1
## Yazmin Vallejo
## 1
## Malcolm Fairbrother
## 1
## CSIC C. Valenciana
## 1
## ThinkR
## 1
## LOrtiz
## 1
## Vicenç Navarro
## 1
## Family Polarization
## 1
## Jared F Edgerton
## 1
## Francesco Rampazzo
## 1
## Tech Junkie
## 1
## Alberto Bayardo
## 1
## MA_Sociodemo_UPF
## 1
## Renata Franc
## 1
## Laboratorio Escapes
## 1
## Frauke Kreuter
## 1
## U. Ramon Llull (URL)
## 1
## Imanis Data
## 1
## Àngels Pont
## 1
## Daniel E Moreno
## 1
## colpolsocaragon
## 1
## Antti Kouvo
## 1
## Drone Creativo
## 1
## Cuebiq
## 1
## Mellow Yellow
## 1
## Verena Halbherr
## 1
## Silicon Beach Talent
## 1
## Tom Guterbock
## 1
## Dr. Emma Tumilty
## 1
## CSS at Columbia
## 1
## Now U Know Training
## 1
## Oxford Politics and IR
## 1
## Ansgar Hudde
## 1
## Vincent Brissot
## 1
## ScotCen
## 1
## Aclima, Inc.
## 1
## Bo
## 1
## Typ A Marketing
## 1
## Advance Services Inc
## 2
## CESSDA ERIC
## 1
## Edyta Kowal
## 1
## USGS R Community
## 1
## MATLAB Helper ®
## 1
## SIPA SusDev
## 1
## Kerry Barrett
## 1
## Sarah E. Patterson
## 1
## LAPOP
## 1
## Daniel Blanche
## 1
## HelpTheCrowd
## 1
## Elisenda Rentería
## 1
## ScotlandDST
## 1
## Folio
## 1
## Emily Gilbert
## 1
## EuropeanValuesStudy
## 1
## Devadas
## 1
## Akhil Sharma
## 1
## WHERE R THE KIDS
## 1
## Alex Lane
## 1
## Aaron Wazlavek
## 1
## Cornell SRI
## 1
## Max Brackett
## 1
## Narciso Michavila
## 1
## El Pati Descobert
## 1
## Consell d'Estudiants
## 1
## Invoice by Alto
## 1
## Alexandra Kupera
## 1
## UK Data Archive
## 1
## RJ Hayden \U0001f1ee\U0001f1ea \U0001f1e6\U0001f1fa \U0001f1fa\U0001f1f8
## 1
## Haidji
## 1
## Tony Vidler
## 1
## Leopoldo Cabrera
## 1
## Pau Vall i Prat\U0001f397
## 1
## SERISS EU
## 1
## Población CSIC
## 1
## 1st In SEO
## 1
## Drs. Albert Spijkers
## 1
## Yamil Nares
## 1
## Nexus Informática
## 1
## Istvan Hajnal
## 1
## Beatriz V.Garzón
## 1
## Ｔｏｎｙ Ｓｍｉｔｈ ＡＣＩＨ #SocialHousing
## 1
## monika jimenez
## 1
## UCC+i UV
## 1
## SurveyResearchCenter
## 1
## Imma T
## 1
## ASInc Central NE
## 2
## ATHLOS Project
## 1
## Lars Lauber
## 1
## Donald Reith
## 1
## Rodrigo
## 1
## Roger Barres
## 1
## María Sabatier
## 1
## Centres CERCA
## 1
## Jiten
## 1
## Sandra Nieto
## 1
## Community Commons
## 1
## Dr. Sofie Marien
## 1
## Molly Goodman \U0001f4ab
## 1
## raphaël couderc
## 1
## David Nelson
## 1
## Ed Eldridge
## 1
## Mirela Causevic
## 1
## CorrelViz
## 1
## Kyle Wackrow
## 1
## C-Metriks
## 1
## Sara Marsillas
## 1
## Dr Emmanuel Caillaud
## 1
## European University
## 1
## LSE Statistics
## 1
## Media4Math
## 1
## LISResearchAu
## 1
## Paul Hitlin
## 1
## Pippa Norris
## 1
## HR Tech Online
## 1
## Swapnil Popat
## 1
## UNACNCRB
## 1
## Maaz Gardezi
## 1
## ESS_Deutschland
## 1
## Comité MMSS - FES
## 1
## Pablo Barberá
## 1
## Agnese Vitali
## 1
## Alessandra Petrucci
## 1
## paolo parra saiani
## 1
## Thought Layer
## 1
## Elena Ambrosetti
## 1
## Mariano Torcal
## 1
## PitchBook Data
## 1
## cswsolutions
## 1
## Mercè Roca
## 1
## Michael Povel
## 1
## NexGen Research
## 1
## CSIC Catalunya
## 1
## World Programming
## 1
## Methodology Center
## 1
## AppliedDemogToolbox
## 1
## Timberlake
## 1
## IC Kollectif
## 1
## HPCNY
## 1
## Junyan Zhu
## 1
## Muthumeena
## 1
## BigData
## 1
## EP
## 1
## Ined
## 1
## Isaac Ddumba
## 1
## ISER
## 1
## ObservatorioDeRedes
## 1
## Webdatanet COST
## 1
## Media Psychology
## 1
## DATAx
## 1
## Big Data Week
## 1
## Valeria Bordone
## 1
## Public Policy Center
## 1
## Posgrado CSIC
## 1
## Alessandro Di Nallo
## 1
## Roy Jackaman
## 1
## Ministerio Economía
## 1
## Peymaneh Shafi
## 1
## Dr Mike Sutton
## 1
## Carlos E. Lagorio
## 1
## Anna Brown
## 1
## Beatriz Serrano
## 1
## Dominic Nyhuis
## 1
## Kenneth Fernandez
## 1
## SOURCE
## 1
## Elite Research
## 1
## Ray Walshe
## 1
## NUCATS Institute
## 1
## XAVIER SIRÉS
## 1
## Kirk Borne
## 1
## Gianluca Cafagna
## 1
## Lisa Horwich
## 1
## Carlos J. Gil
## 1
## Blanca López Zamora
## 1
## Alice Goisis
## 1
## Liz Hamel
## 1
## Ronald van Loon
## 1
## NCCR LIVES
## 1
## Eralba Cela
## 1
## Manuel Betancurt
## 1
## Henrik Dobewall
## 1
## Txell Argelagués
## 1
## AI Newsletter
## 1
## BASTION Digital
## 1
## Willem van de Ven
## 1
## Bate Brand
## 1
## Sanja Rahim
## 1
## Soledad Caballero
## 1
## JFkw
## 1
## Daniel Oberski
## 1
## PhD Forum
## 1
## Chiara Pensato
## 1
## Col·legi de Politòlegs i Sociòlegs de Catalunya
## 1
## Mathew Blanchfield
## 1
## PamelaJF
## 1
## ICPS
## 1
## Voice of Researchers
## 1
## Survey Magazine
## 1
## Muntasir Masum
## 1
## H. Karamanoukian MD
## 1
## Markus Quandt
## 1
## Ilary Bottini
## 1
## PNGumich
## 1
## BuzzCloud
## 1
## Gretchen Donehower
## 1
## ADD Markable
## 1
## ipfconline
## 1
## Jamie Ferrill
## 1
## Anittah/Digital
## 1
## Nazario Biala
## 1
## Mario Cortina Borja
## 1
## UCT IP Unit
## 1
## Julio Rezende, PhD
## 1
## ComPolCat
## 1
## ESS ERIC
## 1
## Forwards
## 1
## aklanta kalita
## 1
## DemoLab_UEvora
## 1
## UM SRC
## 1
## Biomass Research
## 1
## SocArXiv
## 1
## Ajay Grover
## 1
## Barry Schouten
## 1
## Eileen Omosa
## 1
## Gail Farrelly
## 1
## Robk News
## 1
## Woking Stronger IN
## 1
## CourseHour
## 1
## Spiritual Landscapes
## 1
## Sheila Cherry
## 1
## Theoni Stathopoulou
## 1
## EESresearch
## 1
## Ilya Kashnitsky
## 1
## In Summa Innovation
## 1
## CED Barcelona
## 1
## CXO Events
## 1
## PyData
## 1
## D.J. Flynn
## 1
## Meetup R Nantes
## 1
## Marko Bernasconi
## 1
## Big Data News
## 1
## Chuck Schoeneberger
## 1
## Mark Bryan
## 1
## Allen Y. Tien MD MHS
## 1
## Francisco I Pedraza
## 1
## Dr Anja Neundorf
## 1
## Frank La Vigne
## 1
## The R Foundation
## 1
## Lala H. Muradova
## 1
## Danielle Uskovic
## 1
## POLEXP
## 1
## SRMS of ASA
## 1
## DemoSoc UPF
## 1
## BIGSSS Bremen
## 1
## PISA_Facts
## 1
## Rene Bautista
## 1
## UNC European Studies
## 1
## AERA MMR SIG
## 1
## WVS Spain
## 1
## Observatori Recerca
## 1
## Sílvia Majó Vázquez
## 1
## María Ramos
## 1
## Roberta Rù
## 1
## mel bartley
## 1
## Onsoft (Pty) Ltd
## 1
## CSIS
## 1
## Abt Data Science, Surveys & Enabling Technologies
## 1
## CREW
## 1
## Kasule Alex
## 1
## BusinessIntelligence
## 1
## BigSurv18
## 1
## Nathanael Gratias
## 1
## +Politología
## 1
## CPC
## 1
## Pompeu
## 1
## Martin Ravallion
## 1
## SUDA
## 1
## Stuart Gray #FBPE
## 1
## Arndt Leininger
## 1
## Aïda Solé Auró
## 1
## Dave Saunders
## 1
## Jessica Holzberg \U0001f937\U0001f3fc♀️
## 1
## Universitat Politècnica de València
## 1
## Alison Park
## 1
## PureTech Talent
## 1
## Survey Practice
## 1
## IPZ
## 1
## PolNet 2018
## 1
## AAPOR's Got Talent
## 1
## Diederik Boertien
## 1
## Felix Haass
## 1
## Enric Cid
## 1
## Maria Sironi
## 1
## Bad Survey Question
## 1
## Peter Whiteford
## 1
## Eka Software
## 1
## ISU
## 1
## Survey Methods
## 1
## European Social Survey
## 1
## ColpisGenere
## 1
## RES
## 1
## GTI UPF - Interactive Technologies Group
## 1
## Javier Carbonell
## 1
## Ken Bodnar
## 1
## Gratuitous Phil
## 1
## Raphael Nishimura
## 1
## Léa Pessin
## 1
## Alejandro Moreno
## 1
## Rstats
## 1
## Vidal Romero
## 1
## aedemo
## 1
## Gary Pollock
## 1
## Big Data Conference
## 1
## virginia
## 1
## Prof Peter Lynn
## 1
## Writing For Research
## 1
## Rory Fitzgerald
## 1
##
## $csize
## [1] 826 2
##
## $no
## [1] 2Most networks have a single giant connected component that includes most nodes. Most studies of networks actually focus on the giant component (e.g. the shortest path between nodes in a network with two or more component is Inf!).
g <- decompose(g)[[1]]Even within a giant component, there can be different subsets of the network that are more connected to each other than to the rest of the network. The goal of community detection algorithms is to identify these subsets.
There are a few different algorithms, each following a different logic.
The walktrap algorithm finds communities through a series of short random walks. The idea is that these random walks tend to stay within the same community. The length of these random walks is 4 edges by default, but you may want to experiment with different values (longer random walks will lead to fewer communities). The goal of this algorithm is to identify the partition that maximizes a modularity score.
cluster_walktrap(g)## IGRAPH clustering walktrap, groups: 50, mod: 0.46
## + groups:
## $`1`
## [1] "Pep Lobera"
## [2] "Kiko Llaneras"
## [3] "Sociología Práctica"
## [4] "Luis Cornago"
## [5] "Pau Marí-Klose"
## [6] "Roger Senserrich"
## [7] "Ciências Sociais"
## [8] "Ignacio Jurado"
## [9] "Ciències Polítiques i Sociologia"
## + ... omitted several groups/verticescluster_walktrap(g, steps=10)## IGRAPH clustering walktrap, groups: 11, mod: 0.42
## + groups:
## $`1`
## [1] "Olivier MZD\U0001f310"
## [2] "Tavlesh"
## [3] "LeeMMBJack McCarty"
## [4] "Dave"
## [5] "Working Washington"
## [6] "WHERE R THE KIDS"
## [7] "Aaron Wazlavek"
## [8] "RJ Hayden \U0001f1ee\U0001f1ea \U0001f1e6\U0001f1fa \U0001f1fa\U0001f1f8"
##
## + ... omitted several groups/verticescluster_walktrap(g, steps=20)## IGRAPH clustering walktrap, groups: 8, mod: 0.38
## + groups:
## $`1`
## [1] "Mike Kawula \U0001f334\U0001f428\U0001f334"
## [2] "Carlos Rachedi"
## [3] "Questions Consulting"
## [4] "Doc Washburn"
## [5] "Dr. Kapil Bansal"
## [6] "NASSER ALOJAIBY"
## [7] "Business Strategy"
## [8] "Prerit Saxena"
## [9] "Christian Kirschniak"
## + ... omitted several groups/verticescluster_walktrap(g, steps=30)## IGRAPH clustering walktrap, groups: 8, mod: 0.35
## + groups:
## $`1`
## [1] "Mike McCulloch" "Uri Simonsohn"
## [3] "Alexander P. Gage" "United Way of LebCo"
## [5] "Mike Beder" "Pew Research Journalism"
## [7] "RayPoynter" "Johan Braeken"
## [9] "NATSEM" "Randy Bartlett"
## [11] "inside-R Community" "Toni Gril"
## [13] "CityLIS" "Niels \U0001f4c8"
## [15] "Betty Adamou" "Pranay Roy ☃️"
## [17] "datakey" "Andy Kirk"
## + ... omitted several groups/verticesOther methods are:
cluster_infomap(g)## IGRAPH clustering infomap, groups: 28, mod: 0.48
## + groups:
## $`1`
## [1] "Angelika Scheuer"
## [2] "Tyson Gingery"
## [3] "Claire Durand"
## [4] "Ineke Stoop"
## [5] "UCL Institute of Education"
## [6] "Alexander P. Gage"
## [7] "Stata"
## [8] "Mike Beder"
## [9] "Eric Harrison"
## + ... omitted several groups/vertices#cluster_edge_betweenness(g)
cluster_label_prop(g)## IGRAPH clustering label propagation, groups: 35, mod: 0.41
## + groups:
## $`1`
## [1] "Mike Kawula \U0001f334\U0001f428\U0001f334"
## [2] "Datafloq"
## [3] "Carlos Rachedi"
## [4] "Questions Consulting"
## [5] "Doc Washburn"
## [6] "Dr. Kapil Bansal"
## [7] "Liang Wang"
## [8] "Mike McCulloch"
## [9] "NASSER ALOJAIBY"
## + ... omitted several groups/verticescluster_louvain(as.undirected(g))## IGRAPH clustering multi level, groups: 6, mod: 0.48
## + groups:
## $`1`
## [1] "Pep Lobera"
## [2] "Kiko Llaneras"
## [3] "CSES"
## [4] "Luis Cornago"
## [5] "Antonio Arciniega"
## [6] "J Box-Steffensmeier"
## [7] "Raül Tormos"
## [8] "CESOP"
## [9] "Ioannis Andreadis"
## + ... omitted several groups/verticesThe choice of one or other algorithm may depend on substantive or practical reasons, as always. For now, let’s pick the Louvain algorithm.
comm <- cluster_louvain(as.undirected(g))V(g)$name[membership(comm)==1]## [1] "Pep Lobera"
## [2] "Kiko Llaneras"
## [3] "CSES"
## [4] "Luis Cornago"
## [5] "Antonio Arciniega"
## [6] "J Box-Steffensmeier"
## [7] "Raül Tormos"
## [8] "CESOP"
## [9] "Ioannis Andreadis"
## [10] "Kenneth Benoit"
## [11] "Parametría"
## [12] "Rodolfo Rivera"
## [13] "APSA & ICA Political Communication Divisions"
## [14] "Pau Marí-Klose"
## [15] "andrea fumarola"
## [16] "Roger Senserrich"
## [17] "NATSEM"
## [18] "Ignacio Jurado"
## [19] "Simon Munzert"
## [20] "Ciències Polítiques i Sociologia"
## [21] "IBES"
## [22] "eKonomicus"
## [23] "Daniel Liria Campón ۞♀"
## [24] "Маx"
## [25] "Lorena Recabarren"
## [26] "ECPR"
## [27] "Patrick Dunleavy"
## [28] "EPSA"
## [29] "Julio Burdman"
## [30] "Nicolás Tereschuk \U0001f1e6\U0001f1f7"
## [31] "Basilio M. P."
## [32] "Lluís Orriols"
## [33] "Maria Laura Tagina"
## [34] "Juan Font Alonso"
## [35] "Andy Hall"
## [36] "Eva Zeglovits"
## [37] "Jorge Galindo"
## [38] "Ctr for Political St"
## [39] "Encuestas MURAL"
## [40] "BambergSocialScience"
## [41] "Jill Sheppard"
## [42] "Elena Costas Pérez"
## [43] "Jorge San Miguel Lobeto"
## [44] "Molly Roberts"
## [45] "Gonzalo Rivero"
## [46] "Thomas J. Leeper"
## [47] "Carolina Plescia"
## [48] "björn buß"
## [49] "Ernesto Treviño Ronz"
## [50] "Pedro Magalhães"
## [51] "Modesto Escobar"
## [52] "Pablo Simón"
## [53] "NTU Politics and IR"
## [54] "Ignacio Ramirez"
## [55] "Political Analysis"
## [56] "Sílvia Claveria"
## [57] "Martijn Schoonvelde"
## [58] "Empiria"
## [59] "CIPPEC"
## [60] "Sebastián Lavezzolo"
## [61] "Levente Littvay"
## [62] "Andrew Gelman"
## [63] "Gerardo Maldonado"
## [64] "IGPA"
## [65] "Pablo Fdez-Vazquez"
## [66] "Thijs Jansen"
## [67] "Cameron Thies"
## [68] "Guillermo Cordero"
## [69] "Hajo Boomgaarden"
## [70] "Danilo Serani"
## [71] "Zoltan Fazekas"
## [72] "Lucas Gortazar"
## [73] "Scott Clifford"
## [74] "Alina Vranceanu"
## [75] "André Pirralha"
## [76] "Social Research @ANU"
## [77] "Craig McAngus"
## [78] "Vicenç Navarro"
## [79] "Jared F Edgerton"
## [80] "Alberto Bayardo"
## [81] "Àngels Pont"
## [82] "colpolsocaragon"
## [83] "Oxford Politics and IR"
## [84] "LAPOP"
## [85] "Narciso Michavila"
## [86] "El Pati Descobert"
## [87] "Pau Vall i Prat\U0001f397"
## [88] "Roger Barres"
## [89] "María Sabatier"
## [90] "Dr. Sofie Marien"
## [91] "European University"
## [92] "Pippa Norris"
## [93] "Pablo Barberá"
## [94] "Mariano Torcal"
## [95] "Junyan Zhu"
## [96] "EP"
## [97] "ObservatorioDeRedes"
## [98] "Dominic Nyhuis"
## [99] "SOURCE"
## [100] "Txell Argelagués"
## [101] "BASTION Digital"
## [102] "Sanja Rahim"
## [103] "Col·legi de Politòlegs i Sociòlegs de Catalunya"
## [104] "ICPS"
## [105] "ComPolCat"
## [106] "EESresearch"
## [107] "D.J. Flynn"
## [108] "Francisco I Pedraza"
## [109] "Dr Anja Neundorf"
## [110] "Lala H. Muradova"
## [111] "POLEXP"
## [112] "UNC European Studies"
## [113] "WVS Spain"
## [114] "Sílvia Majó Vázquez"
## [115] "María Ramos"
## [116] "Nathanael Gratias"
## [117] "+Politología"
## [118] "Arndt Leininger"
## [119] "IPZ"
## [120] "PolNet 2018"
## [121] "Felix Haass"
## [122] "ColpisGenere"
## [123] "RES"
## [124] "Javier Carbonell"
## [125] "Alejandro Moreno"
## [126] "Vidal Romero"
## [127] "virginia"V(g)$name[membership(comm)==2]## [1] "AnticsUPF"
## [2] "Sociología Práctica"
## [3] "Universia España"
## [4] "Universidad Córdoba"
## [5] "Universitat València"
## [6] "Factam IS"
## [7] "FES Sociología"
## [8] "Lina González"
## [9] "UCLM"
## [10] "Biomedicina BCN"
## [11] "CLIK"
## [12] "Humanitats UPF"
## [13] "politiquesupf"
## [14] "Colegio de Sociología y Politología de Navarra"
## [15] "Becarios 'la Caixa'"
## [16] "Universidad Zaragoza"
## [17] "Horizon 2020\U0001f1ea\U0001f1fa"
## [18] "Universidad de León"
## [19] "Recerca"
## [20] "Universitat Jaume I"
## [21] "Universidad Granada"
## [22] "ORCID Organization"
## [23] "UOC"
## [24] "ESADE"
## [25] "Alexandre Lopez"
## [26] "Obra Social la Caixa"
## [27] "Univ. de Huelva UHU"
## [28] "AXA Research Fund"
## [29] "UOC universidad"
## [30] "UOC university"
## [31] "Complex Systems Lab"
## [32] "LERU"
## [33] "Carreres Professionals UPF"
## [34] "Francesc García"
## [35] "Universidad UDIMA"
## [36] "Universidad Murcia"
## [37] "Universidad de Navarra"
## [38] "unican.es"
## [39] "Colpolsoc-Andalucía"
## [40] "Universitat de Barcelona"
## [41] "Lorena González"
## [42] "CSIC"
## [43] "AgE de Investigacion"
## [44] "Revista Mètode"
## [45] "Universitat Andorra"
## [46] "Liliana Arroyo"
## [47] "Ariadna Fernández"
## [48] "economiquesupf"
## [49] "UPF Barcelona"
## [50] "P.A.BLO.UCM"
## [51] "ACER"
## [52] "Josep Niubò"
## [53] "ESCI-UPF"
## [54] "Frederic Guerrero-Solé"
## [55] "Biblioteca CRAI UPF"
## [56] "CoEBigData"
## [57] "CSIC C. Valenciana"
## [58] "U. Ramon Llull (URL)"
## [59] "Drone Creativo"
## [60] "Consell d'Estudiants"
## [61] "monika jimenez"
## [62] "UCC+i UV"
## [63] "Imma T"
## [64] "Centres CERCA"
## [65] "Sandra Nieto"
## [66] "Comité MMSS - FES"
## [67] "Mercè Roca"
## [68] "CSIC Catalunya"
## [69] "Public Policy Center"
## [70] "Posgrado CSIC"
## [71] "Ministerio Economía"
## [72] "XAVIER SIRÉS"
## [73] "Blanca López Zamora"
## [74] "Biomass Research"
## [75] "Spiritual Landscapes"
## [76] "Observatori Recerca"
## [77] "Pompeu"
## [78] "Universitat Politècnica de València"
## [79] "ISU"
## [80] "GTI UPF - Interactive Technologies Group"V(g)$name[membership(comm)==3]## [1] "Research in Germany"
## [2] "Nick Emmel"
## [3] "Fondazione Brodolini"
## [4] "Stata"
## [5] "octa\U0001f49aio"
## [6] "OpenPop.org"
## [7] "Mark Amos"
## [8] "Statistics Ireland"
## [9] "IECA"
## [10] "Social Sci @WesternU"
## [11] "ieextremadura"
## [12] "Adam M. Lippert"
## [13] "Albert Julià Cano"
## [14] "Harvard Sociology"
## [15] "M. José"
## [16] "Brendan Halpin"
## [17] "Social Trends Inst."
## [18] "Wittgenstein Centre"
## [19] "UNStats"
## [20] "NIDI"
## [21] "Estadistica"
## [22] "Francesco C Billari \U0001f1ea\U0001f1fa\U0001f1ee\U0001f1f9"
## [23] "Estadística La Rioja"
## [24] "Heini Väisänen"
## [25] "Stefanie Hoherz \U0001f1ea\U0001f1fa"
## [26] "IPUMS International"
## [27] "John Palmer"
## [28] "ASA Sociology"
## [29] "Andres Lazaro Lopez"
## [30] "Vrije Universiteit Amsterdam"
## [31] "Sociology@Oxford"
## [32] "Ruben van Gaalen"
## [33] "AleCarioli"
## [34] "ECSR Sociology"
## [35] "Tim Huijts"
## [36] "Sociology Theory"
## [37] "Jana Javornik"
## [38] "Georgiana Bostean"
## [39] "Ronald Musizvingoza"
## [40] "Ugofilippo Basellini"
## [41] "Aleksander Beryozkin"
## [42] "Damiano Uccheddu"
## [43] "Population Europe"
## [44] "Laura Ronkainen"
## [45] "bruno arpino"
## [46] "Jessi Bishop-Royse"
## [47] "Jorge Cimentada"
## [48] "Sergi Vidal"
## [49] "Social Problems"
## [50] "JIPS PCT"
## [51] "Rafa Grande"
## [52] "Emilio Zagheni"
## [53] "Demografía (CSIC)"
## [54] "Dr Fabian Cannizzo"
## [55] "Kyle Chapman"
## [56] "LOrtiz"
## [57] "Family Polarization"
## [58] "Francesco Rampazzo"
## [59] "MA_Sociodemo_UPF"
## [60] "Laboratorio Escapes"
## [61] "Antti Kouvo"
## [62] "Ansgar Hudde"
## [63] "Sarah E. Patterson"
## [64] "Daniel Blanche"
## [65] "Elisenda Rentería"
## [66] "Alexandra Kupera"
## [67] "Leopoldo Cabrera"
## [68] "Población CSIC"
## [69] "ATHLOS Project"
## [70] "Sara Marsillas"
## [71] "Agnese Vitali"
## [72] "Alessandra Petrucci"
## [73] "Elena Ambrosetti"
## [74] "AppliedDemogToolbox"
## [75] "Ined"
## [76] "Isaac Ddumba"
## [77] "Valeria Bordone"
## [78] "Alessandro Di Nallo"
## [79] "Gianluca Cafagna"
## [80] "Carlos J. Gil"
## [81] "Alice Goisis"
## [82] "NCCR LIVES"
## [83] "Eralba Cela"
## [84] "Soledad Caballero"
## [85] "PamelaJF"
## [86] "Muntasir Masum"
## [87] "Gretchen Donehower"
## [88] "ESS ERIC"
## [89] "DemoLab_UEvora"
## [90] "SocArXiv"
## [91] "Ilya Kashnitsky"
## [92] "CED Barcelona"
## [93] "DemoSoc UPF"
## [94] "BIGSSS Bremen"
## [95] "PISA_Facts"
## [96] "AERA MMR SIG"
## [97] "Roberta Rù"
## [98] "mel bartley"
## [99] "CSIS"
## [100] "CREW"
## [101] "CPC"
## [102] "Martin Ravallion"
## [103] "SUDA"
## [104] "Aïda Solé Auró"
## [105] "Diederik Boertien"
## [106] "Maria Sironi"
## [107] "Peter Whiteford"
## [108] "Léa Pessin"
## [109] "Rstats"V(g)$name[membership(comm)==4]## [1] "Uri Simonsohn" "Johan Braeken" "inside-R Community"
## [4] "Niels \U0001f4c8" "Pranay Roy ☃️" "jasonrhody"
## [7] "R-bloggers" "Coosje L.S. Veldkamp" "DataCamp"
## [10] "Natalia da Silva" "Daniël Lakens" "John D. Cook"
## [13] "Jeff Leek" "Dale Barr" "Amelia McNamara"
## [16] "Francesco Bartolucci" "Casper Albers" "RStudio"
## [19] "Adam Bulley" "RONAK SHAH" "ThinkR"
## [22] "USGS R Community" "Rodrigo" "Mirela Causevic"
## [25] "Maaz Gardezi" "Mario Cortina Borja" "Forwards"
## [28] "CourseHour" "Sheila Cherry" "PyData"
## [31] "Meetup R Nantes" "The R Foundation" "Stuart Gray #FBPE"V(g)$name[membership(comm)==5]## [1] "Mike Kawula \U0001f334\U0001f428\U0001f334"
## [2] "Datafloq"
## [3] "Carlos Rachedi"
## [4] "Questions Consulting"
## [5] "Doc Washburn"
## [6] "Dr. Kapil Bansal"
## [7] "Liang Wang"
## [8] "Mike McCulloch"
## [9] "NASSER ALOJAIBY"
## [10] "Business Strategy"
## [11] "Prerit Saxena"
## [12] "United Way of LebCo"
## [13] "Christian Kirschniak"
## [14] "Supriyo B Chatterjee"
## [15] "Marco Brambilla"
## [16] "EAE Business School"
## [17] "Mike Hine"
## [18] "Gabriel Castagnino"
## [19] "MaryLù Cinquerrui"
## [20] "Tim Hughes"
## [21] "Carla Gentry"
## [22] "leon morton"
## [23] "equastat.com"
## [24] "Ahilan MK"
## [25] "Mick Wagner"
## [26] "Brent Thompson"
## [27] "MissSmarty:Plants"
## [28] "Randy Bartlett"
## [29] "Mark Eaves"
## [30] "Dr. Sunshine Menezes"
## [31] "Brice Escarguel"
## [32] "Mark Tabladillo"
## [33] "Remco Ploeg"
## [34] "rich murnane"
## [35] "Loeffler Antiques"
## [36] "Paul Thoresen"
## [37] "Pneuron Corporation"
## [38] "Epoché"
## [39] "Andy Kirk"
## [40] "Richard Iannone"
## [41] "Jane McCarthy \U0001f340"
## [42] "Joanna Bryson 2"
## [43] "Pradyot Rai"
## [44] "Talan ★ Innovation"
## [45] "Olivier MZD\U0001f310"
## [46] "Craig Mullins"
## [47] "Strikedeck"
## [48] "Manikant Rajput *"
## [49] "annie feighery"
## [50] "David McCulloch"
## [51] "Evan Powell"
## [52] "Hiver"
## [53] "Score and Change"
## [54] "C.J. Anderson"
## [55] "Sergi Sergiev"
## [56] "Aaron Bergstrom"
## [57] "Anna Manning"
## [58] "Kurt Muehmel"
## [59] "Jean Pak"
## [60] "Bill Nigh"
## [61] "kevinfarley"
## [62] "insight-intelligence"
## [63] "Steve Kerr"
## [64] "Patricia Behisa ★"
## [65] "Fernanda K O Palermo"
## [66] "Our Fare Is Fair™"
## [67] "Digital Marketing"
## [68] "Natalie Bennett"
## [69] "Chitra Chaudhuri"
## [70] "mobiusmedia"
## [71] "BleuPage Pro"
## [72] "Pedro Muñoz del Río"
## [73] "Angelo N Ferrara DC"
## [74] "Emilio Ferrara"
## [75] "Georgiann Baldino"
## [76] "SmartData Collective"
## [77] "Teresa Colquitt"
## [78] "Management Class"
## [79] "Ramkumar"
## [80] "Malcolm Isaacs"
## [81] "Wilde Agency"
## [82] "keithbolam"
## [83] "CrossValidated"
## [84] "Ricardo Montes B"
## [85] "Cristóbal Martínez"
## [86] "Carles Dijous (AAlb)"
## [87] "Elegant Science"
## [88] "Tavlesh"
## [89] "Interactive Data Lab"
## [90] "Eloy Pascal"
## [91] "Michael Meotti"
## [92] "Alexey Mitkin"
## [93] "CJ Bowen"
## [94] "Via Evaluation"
## [95] "Ross Morley"
## [96] "Lewis"
## [97] "Abel Coronado"
## [98] "Result Logix"
## [99] "Antsy Ant Web Design"
## [100] "Baird Group"
## [101] "Oludele Olabisi"
## [102] "chi2innovations"
## [103] "#hellomynameis Rus Clark\u2695"
## [104] "Lillian D'Costa"
## [105] "Opvizor"
## [106] "LeeMMBJack McCarty"
## [107] "carsten frömel"
## [108] "Holger Mueller"
## [109] "New Slave"
## [110] "Dr Lea Shanley"
## [111] "Simon Porter"
## [112] "Idea8ion"
## [113] "4273π"
## [114] "Paul Naish"
## [115] "Sameera Jade Daniels"
## [116] "FB Network"
## [117] "CRC Digital"
## [118] "Caucus of Working Ed"
## [119] "Arnold Haine"
## [120] "Beth Tracy"
## [121] "UCF Tech Transfer"
## [122] "Matthew Lamons"
## [123] "Chris Casale"
## [124] "Andreas Lenz"
## [125] "trafficono.me"
## [126] "CompleteMktg"
## [127] "Delta Sales"
## [128] "Vox Media México"
## [129] "Albert Putnam"
## [130] "Free Speech For All"
## [131] "bookmarkxpress"
## [132] "Enda Ridge"
## [133] "Jorge Luis"
## [134] "Matthias Nolte"
## [135] "Dave"
## [136] "John Tomlinson"
## [137] "The IBM MSP Team"
## [138] "Stata UK"
## [139] "Working Washington"
## [140] "Real KM Magazine"
## [141] "B2B Listings"
## [142] "Robert Napoli"
## [143] "JohnWaldronMIW"
## [144] "Mathias Golombek"
## [145] "WheelHealthcare ☤"
## [146] "SAS Can Academic"
## [147] "chris goswami"
## [148] "Tim Hughes 提姆·休斯"
## [149] "Jason Ryckman"
## [150] "Community Scene"
## [151] "ChallengeData"
## [152] "The_Quipper"
## [153] "Marcel Wigert"
## [154] "Natalia Capel"
## [155] "Josip Bronzaruka"
## [156] "Hugo Alatrista Salas"
## [157] "VETs Rising"
## [158] "Benoît Ruiz"
## [159] "Blue Lizard Media"
## [160] "OSKA research"
## [161] "Yazmin Vallejo"
## [162] "Tech Junkie"
## [163] "Imanis Data"
## [164] "Cuebiq"
## [165] "Mellow Yellow"
## [166] "Silicon Beach Talent"
## [167] "Now U Know Training"
## [168] "Vincent Brissot"
## [169] "Bo"
## [170] "Edyta Kowal"
## [171] "MATLAB Helper ®"
## [172] "Kerry Barrett"
## [173] "HelpTheCrowd"
## [174] "ScotlandDST"
## [175] "Folio"
## [176] "Devadas"
## [177] "Akhil Sharma"
## [178] "WHERE R THE KIDS"
## [179] "Alex Lane"
## [180] "Aaron Wazlavek"
## [181] "Max Brackett"
## [182] "Invoice by Alto"
## [183] "RJ Hayden \U0001f1ee\U0001f1ea \U0001f1e6\U0001f1fa \U0001f1fa\U0001f1f8"
## [184] "Haidji"
## [185] "Tony Vidler"
## [186] "1st In SEO"
## [187] "Drs. Albert Spijkers"
## [188] "Nexus Informática"
## [189] "Beatriz V.Garzón"
## [190] "Ｔｏｎｙ Ｓｍｉｔｈ ＡＣＩＨ #SocialHousing"
## [191] "Lars Lauber"
## [192] "Donald Reith"
## [193] "Jiten"
## [194] "Community Commons"
## [195] "Molly Goodman \U0001f4ab"
## [196] "Ed Eldridge"
## [197] "CorrelViz"
## [198] "Media4Math"
## [199] "HR Tech Online"
## [200] "Swapnil Popat"
## [201] "UNACNCRB"
## [202] "Thought Layer"
## [203] "PitchBook Data"
## [204] "cswsolutions"
## [205] "Michael Povel"
## [206] "World Programming"
## [207] "IC Kollectif"
## [208] "HPCNY"
## [209] "Muthumeena"
## [210] "BigData"
## [211] "DATAx"
## [212] "Big Data Week"
## [213] "Roy Jackaman"
## [214] "Peymaneh Shafi"
## [215] "Dr Mike Sutton"
## [216] "Beatriz Serrano"
## [217] "Elite Research"
## [218] "Ray Walshe"
## [219] "NUCATS Institute"
## [220] "Kirk Borne"
## [221] "Ronald van Loon"
## [222] "Manuel Betancurt"
## [223] "AI Newsletter"
## [224] "Willem van de Ven"
## [225] "Bate Brand"
## [226] "Chiara Pensato"
## [227] "Mathew Blanchfield"
## [228] "H. Karamanoukian MD"
## [229] "Ilary Bottini"
## [230] "BuzzCloud"
## [231] "ADD Markable"
## [232] "ipfconline"
## [233] "Jamie Ferrill"
## [234] "Anittah/Digital"
## [235] "Nazario Biala"
## [236] "Julio Rezende, PhD"
## [237] "aklanta kalita"
## [238] "Ajay Grover"
## [239] "Gail Farrelly"
## [240] "Robk News"
## [241] "Woking Stronger IN"
## [242] "In Summa Innovation"
## [243] "CXO Events"
## [244] "Marko Bernasconi"
## [245] "Big Data News"
## [246] "Chuck Schoeneberger"
## [247] "Allen Y. Tien MD MHS"
## [248] "Frank La Vigne"
## [249] "Danielle Uskovic"
## [250] "Onsoft (Pty) Ltd"
## [251] "BusinessIntelligence"
## [252] "Dave Saunders"
## [253] "PureTech Talent"
## [254] "Eka Software"
## [255] "Ken Bodnar"
## [256] "Gratuitous Phil"
## [257] "Big Data Conference"V(g)$name[membership(comm)==6]## [1] "Angelika Scheuer"
## [2] "Tyson Gingery"
## [3] "Claire Durand"
## [4] "Ineke Stoop"
## [5] "UCL Institute of Education"
## [6] "Alexander P. Gage"
## [7] "Mike Beder"
## [8] "David Rothschild"
## [9] "Social Research Hub"
## [10] "Pew Research Journalism"
## [11] "Eric Harrison"
## [12] "Alexandru Cernat"
## [13] "Michael Dimock"
## [14] "Idoia Portilla"
## [15] "RayPoynter"
## [16] "WAPOR"
## [17] "Robert Pinter"
## [18] "Aneta Piekut"
## [19] "Wouter Zwysen"
## [20] "Gudbjorg Andrea Jons"
## [21] "Dr Joanne Greenhalgh"
## [22] "Incorrigible FCA"
## [23] "Ciências Sociais"
## [24] "ISI"
## [25] "Mario Callegaro"
## [26] "Josh De La Rosa"
## [27] "Peter Lugtig"
## [28] "Dan Hedlin"
## [29] "Dr. Vanessa Higgins"
## [30] "Bob Lee \U0001f30a\U0001f30a\U0001f30a"
## [31] "World Values Survey"
## [32] "Toni Gril"
## [33] "CityLIS"
## [34] "ESRA"
## [35] "DIW Berlin"
## [36] "SusanMarieMartin PhD"
## [37] "Betty Adamou"
## [38] "PSSRU at Kent"
## [39] "Andrew Mercer"
## [40] "datakey"
## [41] "Cathleen M. Stuetzer"
## [42] "Chris Morley, PhD"
## [43] "Herodato"
## [44] "Ben Carlos Thypin"
## [45] "Stas Kolenikov"
## [46] "Amanda Lenhart"
## [47] "Rich Clark"
## [48] "Michael Link"
## [49] "charliemansell"
## [50] "GESIS"
## [51] "Palmer Gibbs"
## [52] "Roeland Beerten"
## [53] "Tim Gollins"
## [54] "Jessica Broome"
## [55] "SpaethCommunications"
## [56] "Gauri Salokhe"
## [57] "Jeffrey Henning"
## [58] "Leslie Chan"
## [59] "Research & Twitts"
## [60] "Steven R Clark"
## [61] "InvestigaOnline.com (R.Gil)"
## [62] "YouThisMe"
## [63] "Social Research Assn"
## [64] "Wojciech Jablonski"
## [65] "Nielsen"
## [66] "Nate Silver"
## [67] "Jesse Holcomb"
## [68] "NSD"
## [69] "PSSRU at Manchester"
## [70] "Big Data & Society"
## [71] "Netquest"
## [72] "Worka Holic"
## [73] "Alexander Wenz"
## [74] "mysurveylab"
## [75] "Nick Allum"
## [76] "Pew Research Internet"
## [77] "Opinno"
## [78] "Philip S. Brenner"
## [79] "Iara VPS"
## [80] "elizabethpark"
## [81] "Marieke Haan"
## [82] "Michael Bosnjak"
## [83] "Ulrich Krieger"
## [84] "AAPOR"
## [85] "ESRC International Centre for Lifecourse Studies"
## [86] "jose ramon albert"
## [87] "Langer Research"
## [88] "Empirica"
## [89] "Adam Swift"
## [90] "Annika Coughlin"
## [91] "Policy Studies Inst"
## [92] "Alessandra Decataldo"
## [93] "Jon Burton"
## [94] "ESRC"
## [95] "Lisa Rutherford"
## [96] "Ana Slavec\U0001f426"
## [97] "Bernd Weiss"
## [98] "Dr. Annie Rights Research"
## [99] "Yanna Stefanu"
## [100] "Significance"
## [101] "Lluís Coromina Soler"
## [102] "Gale Pryor"
## [103] "AASCU Policy"
## [104] "MDMroczkowski"
## [105] "Cathy Harrison"
## [106] "Paul Long"
## [107] "U-M ISR"
## [108] "Julie Brown"
## [109] "Gerry Nicolaas"
## [110] "#SherDilKejriwal"
## [111] "SurveyCTO"
## [112] "AngeliqueV"
## [113] "The DR K-12 Network"
## [114] "Ravi"
## [115] "Susanna Gerritse"
## [116] "Cardiff Q-Step"
## [117] "Better Surveys"
## [118] "Eiji Matsuda"
## [119] "Yfke \U0001f609ngena"
## [120] "NCRM"
## [121] "MedPro Group"
## [122] "UM SurveyMethodology"
## [123] "Anna de Castellarnau"
## [124] "Florian Keusch"
## [125] "TSE15 Conference"
## [126] "MMU Q-Step"
## [127] "Annika Sehl"
## [128] "Insights Association"
## [129] "IHAWKES"
## [130] "Oriol Llauradó"
## [131] "QMSS at Columbia"
## [132] "UCL Q-Step Centre"
## [133] "PASCAL Observatory"
## [134] "CUQM"
## [135] "GYFAL"
## [136] "UConn SurveyResearch"
## [137] "Jari Lyytimäki"
## [138] "TxGenJobs"
## [139] "UCL Big Data"
## [140] "Kyley McGeeney"
## [141] "Dominic McSherry"
## [142] "RUDAHANGARWA Ignace"
## [143] "Bart Meuleman"
## [144] "Delphos Nudge Unit"
## [145] "MarketSight, LLC"
## [146] "Malcolm Fairbrother"
## [147] "Renata Franc"
## [148] "Frauke Kreuter"
## [149] "Daniel E Moreno"
## [150] "Verena Halbherr"
## [151] "Tom Guterbock"
## [152] "Dr. Emma Tumilty"
## [153] "CSS at Columbia"
## [154] "ScotCen"
## [155] "Aclima, Inc."
## [156] "Typ A Marketing"
## [157] "CESSDA ERIC"
## [158] "SIPA SusDev"
## [159] "Emily Gilbert"
## [160] "EuropeanValuesStudy"
## [161] "Cornell SRI"
## [162] "UK Data Archive"
## [163] "SERISS EU"
## [164] "Yamil Nares"
## [165] "Istvan Hajnal"
## [166] "SurveyResearchCenter"
## [167] "raphaël couderc"
## [168] "David Nelson"
## [169] "Kyle Wackrow"
## [170] "C-Metriks"
## [171] "Dr Emmanuel Caillaud"
## [172] "LSE Statistics"
## [173] "LISResearchAu"
## [174] "Paul Hitlin"
## [175] "ESS_Deutschland"
## [176] "paolo parra saiani"
## [177] "NexGen Research"
## [178] "Methodology Center"
## [179] "Timberlake"
## [180] "ISER"
## [181] "Webdatanet COST"
## [182] "Media Psychology"
## [183] "Carlos E. Lagorio"
## [184] "Anna Brown"
## [185] "Kenneth Fernandez"
## [186] "Lisa Horwich"
## [187] "Liz Hamel"
## [188] "Henrik Dobewall"
## [189] "JFkw"
## [190] "Daniel Oberski"
## [191] "PhD Forum"
## [192] "Voice of Researchers"
## [193] "Survey Magazine"
## [194] "Markus Quandt"
## [195] "PNGumich"
## [196] "UCT IP Unit"
## [197] "UM SRC"
## [198] "Barry Schouten"
## [199] "Eileen Omosa"
## [200] "Theoni Stathopoulou"
## [201] "Mark Bryan"
## [202] "SRMS of ASA"
## [203] "Rene Bautista"
## [204] "Abt Data Science, Surveys & Enabling Technologies"
## [205] "Kasule Alex"
## [206] "BigSurv18"
## [207] "Jessica Holzberg \U0001f937\U0001f3fc♀️"
## [208] "Alison Park"
## [209] "Survey Practice"
## [210] "AAPOR's Got Talent"
## [211] "Enric Cid"
## [212] "Bad Survey Question"
## [213] "Survey Methods"
## [214] "European Social Survey"
## [215] "Raphael Nishimura"
## [216] "aedemo"
## [217] "Gary Pollock"
## [218] "Prof Peter Lynn"
## [219] "Writing For Research"
## [220] "Rory Fitzgerald"library(quanteda)## Warning: package 'quanteda' was built under R version 3.4.4## Package version: 1.3.0## Parallel computing: 2 of 4 threads used.## See https://quanteda.io for tutorials and examples.##
## Attaching package: 'quanteda'## The following object is masked from 'package:utils':
##
## Viewfor (i in 1:6){
message("Cluster ", i)
dfm <- dfm(V(g)$description[membership(comm)==i],
remove_punct=TRUE, remove=c(stopwords("english"), stopwords("spanish")))
print(topfeatures(dfm, n=25))
}## Cluster 1## political science social politics scientist
## 39 20 18 17 13
## research phd https t.co data
## 12 11 11 11 10
## methods política survey professor public
## 10 10 9 9 9
## profesor policy opinión pública university
## 8 8 7 7 7
## elections politólogo opinion investigación director
## 7 7 6 6 6## Cluster 2## universitat twitter oficial pompeu fabra
## 21 14 14 12 11
## upf universidad research per t.co
## 10 10 8 8 8
## recerca catalunya social https barcelona
## 7 7 6 6 5
## investigación pública official és sociología
## 5 5 5 5 4
## university csic asociación association mayor
## 4 4 3 3 3## Cluster 3## research social demography sociology phd university
## 28 25 22 16 13 13
## statistics population professor demographer interested data
## 12 12 10 9 9 7
## health sociologist family associate t.co views
## 7 7 7 7 6 6
## demographic european researcher student https policy
## 6 6 6 6 5 5
## tweets
## 5## Cluster 4## data r t.co science https statistics
## 13 12 9 9 7 6
## open #rstats community professor blog source
## 5 5 4 4 3 3
## social digital views analysis university tweets
## 3 3 3 3 3 3
## http analytics phd #analytics media opinions
## 2 2 2 2 2 2
## python
## 2## Cluster 5## data t.co https marketing business
## 53 39 34 29 26
## digital #bigdata science social analytics
## 22 19 18 17 17
## help views media #datascience #iot
## 17 14 14 12 12
## author #ai software research learning
## 11 11 10 10 10
## tech opinions management global ceo
## 10 10 10 10 9## Cluster 6## research survey social data t.co
## 90 78 53 50 26
## methods science researcher university institute
## 24 24 21 18 18
## director methodology views https methodologist
## 17 16 15 15 13
## statistics surveys centre market public
## 12 11 11 11 11
## http quantitative professor development analysis
## 11 10 10 10 10# description
df <- data.frame(
description = V(g)$description,
location = V(g)$location,
cluster = as.numeric(membership(comm)),
stringsAsFactors=F
)
recsm <- dfm(corpus(df, text_field="description"),
remove=c(stopwords("english"), stopwords("spanish")))
for (i in 1:4){
print(
head(textstat_keyness(recsm, target=docvars(recsm)$cluster==i,
measure="lr"), n=20)
)
}## feature G2 p n_target n_reference
## 1 political 107.440942 0.000000e+00 39 10
## 2 politics 30.541027 3.268801e-08 17 11
## 3 política 29.092759 6.899437e-08 10 1
## 4 elections 22.132320 2.544889e-06 7 0
## 5 politólogo 22.132320 2.544889e-06 7 0
## 6 ● 22.132320 2.544889e-06 7 0
## 7 profesor 19.028282 1.287953e-05 8 2
## 8 @politikon_es 18.354321 1.834025e-05 6 0
## 9 opinión 18.314118 1.873139e-05 7 1
## 10 scientist 15.387931 8.754568e-05 13 15
## 11 análisis 14.607979 1.323530e-04 5 0
## 12 electoral 14.607979 1.323530e-04 5 0
## 13 ciencia 11.411652 7.298492e-04 5 1
## 14 madrid 10.907986 9.575059e-04 4 0
## 15 pública 10.685801 1.079610e-03 7 5
## 16 science 8.973450 2.739308e-03 20 53
## 17 experimental 8.114512 4.391230e-03 4 1
## 18 . 7.607870 5.811410e-03 190 942
## 19 quantio 7.283000 6.961019e-03 3 0
## 20 comportamiento 7.283000 6.961019e-03 3 0
## feature G2 p n_target n_reference
## 1 universitat 77.46610 0.000000e+00 21 4
## 2 pompeu 40.48253 1.983819e-10 12 3
## 3 oficial 39.91533 2.652137e-10 14 7
## 4 fabra 36.14568 1.831037e-09 11 3
## 5 upf 34.53949 4.176914e-09 10 2
## 6 twitter 32.18993 1.398132e-08 14 12
## 7 recerca 28.19880 1.094723e-07 7 0
## 8 per 19.88224 8.236185e-06 8 5
## 9 universidad 19.53545 9.875001e-06 10 11
## 10 catalunya 17.64611 2.660591e-05 7 4
## 11 és 13.27784 2.685623e-04 5 2
## 12 csic 11.23200 8.039889e-04 4 1
## 13 asociación 9.57672 1.970601e-03 3 0
## 14 mayor 9.57672 1.970601e-03 3 0
## 15 educación 9.57672 1.970601e-03 3 0
## 16 superior 9.57672 1.970601e-03 3 0
## 17 fundada 9.57672 1.970601e-03 3 0
## 18 estudiantes 9.57672 1.970601e-03 3 0
## 19 servei 9.57672 1.970601e-03 3 0
## 20 cerca 9.57672 1.970601e-03 3 0
## feature G2 p n_target n_reference
## 1 demography 87.908491 0.000000e+00 22 0
## 2 population 40.517435 1.948693e-10 12 1
## 3 sociology 34.189065 5.000918e-09 16 10
## 4 demographer 32.794312 1.024442e-08 9 0
## 5 demographic 20.311719 6.579635e-06 6 0
## 6 statistics 13.376847 2.547496e-04 12 19
## 7 phd 12.473747 4.127114e-04 13 24
## 8 sociologist 11.517943 6.892763e-04 7 6
## 9 family 11.517943 6.892763e-04 7 6
## 10 ; 10.336259 1.304421e-03 15 39
## 11 associate 9.508378 2.045359e-03 7 8
## 12 estadística 9.296878 2.295447e-03 4 1
## 13 funded 9.296878 2.295447e-03 4 1
## 14 ageing 9.296878 2.295447e-03 4 1
## 15 sociological 9.296878 2.295447e-03 4 1
## 16 inequality 9.233912 2.375735e-03 5 3
## 17 instituto 8.157535 4.288262e-03 3 0
## 18 dynamics 8.157535 4.288262e-03 3 0
## 19 #ageing 8.157535 4.288262e-03 3 0
## 20 aging 8.157535 4.288262e-03 3 0
## feature G2 p n_target n_reference
## 1 r 46.247112 1.042400e-11 12 8
## 2 #rstats 14.112230 1.722204e-04 5 6
## 3 / 14.055796 1.774660e-04 34 369
## 4 open 11.015861 9.033556e-04 5 10
## 5 statistics 7.981633 4.725431e-03 6 25
## 6 data 7.328770 6.785946e-03 13 121
## 7 community 7.273640 6.997386e-03 4 10
## 8 co-editor 7.264778 7.031997e-03 2 0
## 9 biostatistics 7.264778 7.031997e-03 2 0
## 10 happens 7.264778 7.031997e-03 2 0
## 11 ~ 7.264778 7.031997e-03 2 0
## 12 #statistics 7.264778 7.031997e-03 2 0
## 13 usgs 7.264778 7.031997e-03 2 0
## 14 science 6.788971 9.172274e-03 9 64
## 15 source 6.328210 1.188322e-02 3 5
## 16 : 6.013310 1.419837e-02 16 179
## 17 @ 5.717200 1.679950e-02 3 6
## 18 interaction 5.442115 1.965686e-02 2 1
## 19 blog 5.192432 2.268546e-02 3 7
## 20 scientific 4.395378 3.603648e-02 2 2recsm <- dfm(corpus(df, text_field="location"),
remove=c(stopwords("english"), stopwords("spanish")))
# location
for (i in 1:4){
print(
head(textstat_keyness(recsm, target=docvars(recsm)$cluster==i,
measure="lr"), n=20)
)
}## feature G2 p n_target n_reference
## 1 buenos 14.315048 0.0001546239 5 0
## 2 argentina 10.672102 0.0010876347 4 0
## 3 aires 10.672102 0.0010876347 4 0
## 4 méxico 7.888585 0.0049747775 4 1
## 5 barcelona 4.946547 0.0261428391 15 44
## 6 catalunya 4.915635 0.0266146809 4 3
## 7 | 4.915635 0.0266146809 4 3
## 8 canberra 4.832501 0.0279280931 3 1
## 9 madrid 4.359395 0.0368053764 8 16
## 10 columbus 3.696654 0.0545217034 2 0
## 11 lisbon 3.696654 0.0545217034 2 0
## 12 ciudad 3.696654 0.0545217034 2 0
## 13 spain 3.665473 0.0555508674 11 32
## 14 nottingham 2.599285 0.1069119074 3 3
## 15 oh 2.100204 0.1472794421 2 1
## 16 world 2.100204 0.1472794421 2 1
## 17 portugal 2.100204 0.1472794421 2 1
## 18 leuven 2.100204 0.1472794421 2 1
## 19 oxford 1.437541 0.2305376105 3 5
## 20 norway 1.279855 0.2579259876 2 2
## feature G2 p n_target n_reference
## 1 barcelona 69.755368 1.110223e-16 29 30
## 2 spain 34.903570 3.464450e-09 18 25
## 3 madrid 22.267716 2.371605e-06 11 13
## 4 españa 14.984469 1.083997e-04 8 10
## 5 valència 7.453847 6.330102e-03 3 1
## 6 valencia 5.321929 2.105868e-02 2 0
## 7 granada 5.321929 2.105868e-02 2 0
## 8 catalonia 5.321929 2.105868e-02 2 0
## 9 comunidad 5.321929 2.105868e-02 2 0
## 10 catalunya 4.133525 4.204170e-02 3 4
## 11 - 1.555863 2.122720e-01 3 10
## 12 ( 1.509669 2.191896e-01 2 4
## 13 ) 1.509669 2.191896e-01 2 4
## 14 córdoba 1.192173 2.748916e-01 1 0
## 15 jaén 1.192173 2.748916e-01 1 0
## 16 castilla-la 1.192173 2.748916e-01 1 0
## 17 mancha 1.192173 2.748916e-01 1 0
## 18 navarra 1.192173 2.748916e-01 1 0
## 19 zaragoza 1.192173 2.748916e-01 1 0
## 20 león 1.192173 2.748916e-01 1 0
## feature G2 p n_target n_reference
## 1 southampton 8.0264588 0.004609888 3 0
## 2 geneva 8.0264588 0.004609888 3 0
## 3 lausanne 4.2340987 0.039619655 2 0
## 4 professor 2.5800296 0.108219641 2 1
## 5 oxford 2.0659377 0.150622251 3 5
## 6 ireland 1.7020251 0.192023349 2 2
## 7 hague 1.7020251 0.192023349 2 2
## 8 switzerland 1.7020251 0.192023349 2 2
## 9 spain 1.5660573 0.210780508 8 35
## 10 ontario 1.1416515 0.285303619 2 3
## 11 california 1.1416515 0.285303619 2 3
## 12 views 0.8585641 0.354140841 1 0
## 13 seville 0.8585641 0.354140841 1 0
## 14 mérida 0.8585641 0.354140841 1 0
## 15 badajoz 0.8585641 0.354140841 1 0
## 16 limerick 0.8585641 0.354140841 1 0
## 17 laxenburg 0.8585641 0.354140841 1 0
## 18 den 0.8585641 0.354140841 1 0
## 19 haag 0.8585641 0.354140841 1 0
## 20 bocconi 0.8585641 0.354140841 1 0
## feature G2 p n_target n_reference
## 1 india 2.051693 0.1520370 2 8
## 2 central 1.933222 0.1644063 1 0
## 3 region 1.933222 0.1644063 1 0
## 4 nj-ish 1.933222 0.1644063 1 0
## 5 vu 1.933222 0.1644063 1 0
## 6 medical 1.933222 0.1644063 1 0
## 7 center 1.933222 0.1644063 1 0
## 8 vumc 1.933222 0.1644063 1 0
## 9 uruguay 1.933222 0.1644063 1 0
## 10 mn 1.933222 0.1644063 1 0
## 11 statistics 1.933222 0.1644063 1 0
## 12 groningen 1.933222 0.1644063 1 0
## 13 pune 1.933222 0.1644063 1 0
## 14 ohio 1.933222 0.1644063 1 0
## 15 nantes 1.933222 0.1644063 1 0
## 16 portsmouth 1.933222 0.1644063 1 0
## 17 netherlands 1.274708 0.2588853 2 12
## 18 queensland 1.146556 0.2842712 1 1
## 19 bremen 1.146556 0.2842712 1 1
## 20 singapore 1.146556 0.2842712 1 1The final way in which we can think about network communities is in terms of hierarchy or structure. We’ll discuss one of these methods.
K-core decomposition allows us to identify the core and the periphery of the network. A k-core is a maximal subnet of a network such that all nodes have at least degree K.
coreness(g)## Mike Kawula \U0001f334\U0001f428\U0001f334
## 30
## Research in Germany
## 13
## Datafloq
## 30
## Angelika Scheuer
## 50
## Tyson Gingery
## 32
## Carlos Rachedi
## 28
## Questions Consulting
## 27
## Pep Lobera
## 43
## Kiko Llaneras
## 43
## AnticsUPF
## 20
## Nick Emmel
## 9
## Doc Washburn
## 5
## Sociología Práctica
## 18
## Universia España
## 25
## Claire Durand
## 34
## Dr. Kapil Bansal
## 3
## CSES
## 46
## Liang Wang
## 30
## Mike McCulloch
## 1
## Uri Simonsohn
## 18
## Luis Cornago
## 36
## Ineke Stoop
## 50
## UCL Institute of Education
## 28
## NASSER ALOJAIBY
## 8
## Business Strategy
## 1
## Prerit Saxena
## 1
## Fondazione Brodolini
## 2
## Alexander P. Gage
## 9
## United Way of LebCo
## 1
## Universidad Córdoba
## 25
## Universitat València
## 25
## Stata
## 47
## Antonio Arciniega
## 44
## J Box-Steffensmeier
## 28
## Mike Beder
## 32
## Factam IS
## 28
## Christian Kirschniak
## 4
## David Rothschild
## 20
## Raül Tormos
## 50
## Supriyo B Chatterjee
## 26
## Social Research Hub
## 40
## Marco Brambilla
## 12
## EAE Business School
## 16
## FES Sociología
## 28
## CESOP
## 10
## octa\U0001f49aio
## 9
## Pew Research Journalism
## 30
## Ioannis Andreadis
## 44
## Eric Harrison
## 50
## Lina González
## 4
## Kenneth Benoit
## 40
## Mike Hine
## 1
## Alexandru Cernat
## 50
## Michael Dimock
## 29
## Idoia Portilla
## 23
## RayPoynter
## 41
## Parametría
## 16
## Rodolfo Rivera
## 7
## APSA & ICA Political Communication Divisions
## 37
## WAPOR
## 50
## Pau Marí-Klose
## 43
## Robert Pinter
## 21
## OpenPop.org
## 50
## Gabriel Castagnino
## 27
## Aneta Piekut
## 43
## MaryLù Cinquerrui
## 18
## Mark Amos
## 50
## Wouter Zwysen
## 42
## andrea fumarola
## 35
## Tim Hughes
## 30
## Statistics Ireland
## 10
## Carla Gentry
## 31
## IECA
## 25
## Roger Senserrich
## 35
## leon morton
## 2
## Gudbjorg Andrea Jons
## 28
## equastat.com
## 16
## Ahilan MK
## 12
## Mick Wagner
## 2
## Dr Joanne Greenhalgh
## 9
## Incorrigible FCA
## 9
## Johan Braeken
## 5
## Brent Thompson
## 9
## NATSEM
## 16
## UCLM
## 25
## Ciências Sociais
## 2
## Ignacio Jurado
## 43
## Biomedicina BCN
## 24
## MissSmarty:Plants
## 18
## Randy Bartlett
## 14
## CLIK
## 26
## Simon Munzert
## 41
## Ciències Polítiques i Sociologia
## 31
## IBES
## 19
## Social Sci @WesternU
## 3
## Mark Eaves
## 23
## ISI
## 24
## Mario Callegaro
## 50
## Humanitats UPF
## 22
## eKonomicus
## 24
## Dr. Sunshine Menezes
## 2
## Brice Escarguel
## 30
## politiquesupf
## 31
## ieextremadura
## 12
## Josh De La Rosa
## 50
## Peter Lugtig
## 50
## Mark Tabladillo
## 29
## Remco Ploeg
## 1
## rich murnane
## 28
## Daniel Liria Campón ۞♀
## 1
## Маx
## 13
## inside-R Community
## 26
## Loeffler Antiques
## 14
## Paul Thoresen
## 30
## Colegio de Sociología y Politología de Navarra
## 16
## Dan Hedlin
## 35
## Dr. Vanessa Higgins
## 36
## Lorena Recabarren
## 11
## ECPR
## 45
## Becarios 'la Caixa'
## 12
## Bob Lee \U0001f30a\U0001f30a\U0001f30a
## 11
## Patrick Dunleavy
## 48
## World Values Survey
## 50
## Toni Gril
## 27
## CityLIS
## 15
## Universidad Zaragoza
## 25
## ESRA
## 50
## DIW Berlin
## 23
## EPSA
## 40
## Niels \U0001f4c8
## 18
## Julio Burdman
## 12
## SusanMarieMartin PhD
## 13
## Nicolás Tereschuk \U0001f1e6\U0001f1f7
## 12
## Betty Adamou
## 35
## Pranay Roy ☃️
## 5
## PSSRU at Kent
## 13
## Pneuron Corporation
## 30
## Andrew Mercer
## 50
## Adam M. Lippert
## 44
## Epoché
## 18
## datakey
## 10
## Albert Julià Cano
## 40
## Andy Kirk
## 26
## Horizon 2020\U0001f1ea\U0001f1fa
## 36
## Basilio M. P.
## 43
## Cathleen M. Stuetzer
## 13
## Lluís Orriols
## 43
## Universidad de León
## 20
## Harvard Sociology
## 20
## Chris Morley, PhD
## 9
## Herodato
## 50
## Ben Carlos Thypin
## 1
## Stas Kolenikov
## 50
## Amanda Lenhart
## 22
## jasonrhody
## 6
## Rich Clark
## 46
## Maria Laura Tagina
## 26
## M. José
## 36
## Michael Link
## 50
## Richard Iannone
## 28
## Recerca
## 26
## Juan Font Alonso
## 35
## Jane McCarthy \U0001f340
## 15
## Universitat Jaume I
## 25
## R-bloggers
## 37
## charliemansell
## 6
## Universidad Granada
## 26
## Brendan Halpin
## 42
## GESIS
## 50
## Joanna Bryson 2
## 5
## Pradyot Rai
## 6
## Social Trends Inst.
## 14
## Talan ★ Innovation
## 13
## Palmer Gibbs
## 1
## Andy Hall
## 37
## Olivier MZD\U0001f310
## 2
## Eva Zeglovits
## 29
## Roeland Beerten
## 48
## Tim Gollins
## 15
## Craig Mullins
## 26
## Strikedeck
## 27
## Jorge Galindo
## 43
## Wittgenstein Centre
## 50
## Ctr for Political St
## 50
## Encuestas MURAL
## 1
## ORCID Organization
## 21
## BambergSocialScience
## 46
## Manikant Rajput *
## 5
## UNStats
## 23
## Jessica Broome
## 32
## UOC
## 26
## ESADE
## 23
## annie feighery
## 6
## Jill Sheppard
## 48
## Elena Costas Pérez
## 37
## David McCulloch
## 2
## Coosje L.S. Veldkamp
## 6
## SpaethCommunications
## 1
## Alexandre Lopez
## 20
## Evan Powell
## 22
## NIDI
## 50
## Gauri Salokhe
## 6
## Estadistica
## 13
## Hiver
## 19
## Score and Change
## 1
## C.J. Anderson
## 21
## Sergi Sergiev
## 26
## Jeffrey Henning
## 44
## Obra Social la Caixa
## 26
## Leslie Chan
## 7
## Research & Twitts
## 18
## Aaron Bergstrom
## 2
## Francesco C Billari \U0001f1ea\U0001f1fa\U0001f1ee\U0001f1f9
## 50
## Univ. de Huelva UHU
## 25
## Anna Manning
## 25
## Kurt Muehmel
## 7
## Estadística La Rioja
## 8
## DataCamp
## 26
## Jean Pak
## 8
## Steven R Clark
## 22
## Jorge San Miguel Lobeto
## 35
## Molly Roberts
## 37
## Bill Nigh
## 30
## InvestigaOnline.com (R.Gil)
## 18
## YouThisMe
## 1
## Heini Väisänen
## 41
## Social Research Assn
## 50
## kevinfarley
## 9
## AXA Research Fund
## 14
## Natalia da Silva
## 15
## Gonzalo Rivero
## 43
## Wojciech Jablonski
## 50
## Nielsen
## 32
## Nate Silver
## 45
## Thomas J. Leeper
## 43
## Jesse Holcomb
## 22
## insight-intelligence
## 30
## UOC universidad
## 25
## UOC university
## 13
## Carolina Plescia
## 37
## NSD
## 45
## PSSRU at Manchester
## 13
## Big Data & Society
## 43
## Netquest
## 35
## Steve Kerr
## 22
## Patricia Behisa ★
## 16
## björn buß
## 38
## Complex Systems Lab
## 16
## Fernanda K O Palermo
## 25
## Ernesto Treviño Ronz
## 1
## Our Fare Is Fair™
## 8
## LERU
## 24
## Pedro Magalhães
## 44
## Digital Marketing
## 23
## Natalie Bennett
## 22
## Chitra Chaudhuri
## 15
## Worka Holic
## 50
## Carreres Professionals UPF
## 20
## Alexander Wenz
## 50
## mysurveylab
## 22
## mobiusmedia
## 30
## Stefanie Hoherz \U0001f1ea\U0001f1fa
## 50
## Nick Allum
## 14
## BleuPage Pro
## 26
## Francesc García
## 22
## Pew Research Internet
## 45
## IPUMS International
## 50
## Modesto Escobar
## 29
## Universidad UDIMA
## 20
## Universidad Murcia
## 25
## Opinno
## 1
## Universidad de Navarra
## 25
## Pedro Muñoz del Río
## 5
## Pablo Simón
## 43
## Angelo N Ferrara DC
## 6
## Philip S. Brenner
## 49
## Emilio Ferrara
## 24
## Georgiann Baldino
## 8
## Daniël Lakens
## 26
## Iara VPS
## 12
## SmartData Collective
## 26
## elizabethpark
## 8
## Teresa Colquitt
## 5
## John D. Cook
## 24
## Management Class
## 16
## John Palmer
## 36
## Jeff Leek
## 25
## Ramkumar
## 5
## Malcolm Isaacs
## 17
## unican.es
## 25
## NTU Politics and IR
## 14
## Marieke Haan
## 50
## Wilde Agency
## 10
## Ignacio Ramirez
## 19
## keithbolam
## 20
## Michael Bosnjak
## 50
## CrossValidated
## 18
## Ulrich Krieger
## 50
## Ricardo Montes B
## 10
## ASA Sociology
## 50
## AAPOR
## 50
## ESRC International Centre for Lifecourse Studies
## 43
## jose ramon albert
## 2
## Cristóbal Martínez
## 5
## Carles Dijous (AAlb)
## 26
## Colpolsoc-Andalucía
## 16
## Elegant Science
## 7
## Langer Research
## 30
## Tavlesh
## 8
## Political Analysis
## 45
## Interactive Data Lab
## 7
## Empirica
## 17
## Adam Swift
## 17
## Annika Coughlin
## 35
## Andres Lazaro Lopez
## 16
## Universitat de Barcelona
## 26
## Eloy Pascal
## 2
## Lorena González
## 3
## Vrije Universiteit Amsterdam
## 7
## Policy Studies Inst
## 17
## Michael Meotti
## 15
## CSIC
## 26
## Dale Barr
## 18
## Sílvia Claveria
## 43
## Martijn Schoonvelde
## 37
## Alexey Mitkin
## 21
## Alessandra Decataldo
## 6
## Jon Burton
## 50
## AgE de Investigacion
## 26
## CJ Bowen
## 23
## Sociology@Oxford
## 50
## ESRC
## 50
## Ruben van Gaalen
## 50
## Via Evaluation
## 13
## Ross Morley
## 22
## AleCarioli
## 48
## Empiria
## 29
## Amelia McNamara
## 26
## Lisa Rutherford
## 40
## Ana Slavec\U0001f426
## 50
## Francesco Bartolucci
## 9
## ECSR Sociology
## 50
## Lewis
## 28
## Bernd Weiss
## 50
## Tim Huijts
## 26
## Dr. Annie Rights Research
## 50
## Yanna Stefanu
## 14
## Abel Coronado
## 20
## Sociology Theory
## 45
## Significance
## 49
## Casper Albers
## 18
## Result Logix
## 21
## Revista Mètode
## 25
## Lluís Coromina Soler
## 22
## CIPPEC
## 10
## Antsy Ant Web Design
## 10
## Gale Pryor
## 3
## AASCU Policy
## 8
## Sebastián Lavezzolo
## 43
## Universitat Andorra
## 20
## Levente Littvay
## 35
## MDMroczkowski
## 1
## Baird Group
## 19
## Oludele Olabisi
## 4
## Jana Javornik
## 50
## Cathy Harrison
## 32
## Paul Long
## 32
## Andrew Gelman
## 42
## chi2innovations
## 27
## #hellomynameis Rus Clark\u2695
## 2
## Lillian D'Costa
## 9
## Liliana Arroyo
## 26
## Gerardo Maldonado
## 44
## U-M ISR
## 50
## Georgiana Bostean
## 38
## Julie Brown
## 6
## Ronald Musizvingoza
## 15
## Opvizor
## 12
## LeeMMBJack McCarty
## 12
## Gerry Nicolaas
## 50
## #SherDilKejriwal
## 1
## carsten frömel
## 2
## Holger Mueller
## 30
## New Slave
## 2
## Ugofilippo Basellini
## 49
## SurveyCTO
## 7
## AngeliqueV
## 9
## Dr Lea Shanley
## 24
## Simon Porter
## 30
## The DR K-12 Network
## 7
## Idea8ion
## 10
## Ariadna Fernández
## 15
## Ravi
## 5
## Aleksander Beryozkin
## 1
## 4273π
## 8
## Paul Naish
## 37
## economiquesupf
## 18
## Damiano Uccheddu
## 50
## Susanna Gerritse
## 30
## Cardiff Q-Step
## 35
## Population Europe
## 50
## RStudio
## 37
## Sameera Jade Daniels
## 30
## FB Network
## 1
## Better Surveys
## 41
## CRC Digital
## 9
## Caucus of Working Ed
## 1
## Arnold Haine
## 30
## Eiji Matsuda
## 50
## Beth Tracy
## 2
## Yfke \U0001f609ngena
## 50
## UCF Tech Transfer
## 5
## IGPA
## 25
## Matthew Lamons
## 30
## UPF Barcelona
## 36
## P.A.BLO.UCM
## 9
## Laura Ronkainen
## 2
## Chris Casale
## 28
## NCRM
## 50
## Andreas Lenz
## 12
## MedPro Group
## 4
## UM SurveyMethodology
## 50
## Anna de Castellarnau
## 13
## Pablo Fdez-Vazquez
## 43
## trafficono.me
## 5
## Florian Keusch
## 50
## TSE15 Conference
## 50
## CompleteMktg
## 16
## Thijs Jansen
## 5
## Cameron Thies
## 29
## Delta Sales
## 5
## bruno arpino
## 50
## Vox Media México
## 10
## Guillermo Cordero
## 43
## Jessi Bishop-Royse
## 20
## MMU Q-Step
## 41
## Annika Sehl
## 6
## Jorge Cimentada
## 25
## Albert Putnam
## 23
## Sergi Vidal
## 50
## Insights Association
## 50
## Free Speech For All
## 5
## bookmarkxpress
## 28
## Social Problems
## 45
## Enda Ridge
## 18
## Jorge Luis
## 2
## Adam Bulley
## 1
## IHAWKES
## 10
## RONAK SHAH
## 4
## Oriol Llauradó
## 22
## QMSS at Columbia
## 4
## JIPS PCT
## 2
## ACER
## 18
## Matthias Nolte
## 22
## UCL Q-Step Centre
## 43
## Hajo Boomgaarden
## 18
## Dave
## 8
## John Tomlinson
## 23
## Danilo Serani
## 40
## The IBM MSP Team
## 28
## Stata UK
## 9
## Josep Niubò
## 26
## Rafa Grande
## 35
## Working Washington
## 1
## PASCAL Observatory
## 24
## Zoltan Fazekas
## 37
## Real KM Magazine
## 19
## B2B Listings
## 27
## Robert Napoli
## 28
## ESCI-UPF
## 20
## JohnWaldronMIW
## 14
## Lucas Gortazar
## 35
## Frederic Guerrero-Solé
## 25
## Biblioteca CRAI UPF
## 21
## CUQM
## 15
## Mathias Golombek
## 30
## WheelHealthcare ☤
## 2
## SAS Can Academic
## 25
## chris goswami
## 19
## Emilio Zagheni
## 50
## CoEBigData
## 19
## Tim Hughes 提姆·休斯
## 30
## Jason Ryckman
## 22
## Community Scene
## 8
## ChallengeData
## 22
## Scott Clifford
## 37
## Demografía (CSIC)
## 50
## GYFAL
## 3
## UConn SurveyResearch
## 44
## Jari Lyytimäki
## 4
## TxGenJobs
## 1
## The_Quipper
## 1
## UCL Big Data
## 12
## Kyley McGeeney
## 50
## Alina Vranceanu
## 40
## Marcel Wigert
## 18
## Dr Fabian Cannizzo
## 12
## Natalia Capel
## 28
## Kyle Chapman
## 17
## Josip Bronzaruka
## 5
## Hugo Alatrista Salas
## 12
## VETs Rising
## 2
## Benoît Ruiz
## 4
## Blue Lizard Media
## 2
## OSKA research
## 15
## Dominic McSherry
## 14
## RUDAHANGARWA Ignace
## 2
## André Pirralha
## 22
## Social Research @ANU
## 14
## Bart Meuleman
## 50
## Delphos Nudge Unit
## 12
## Craig McAngus
## 21
## MarketSight, LLC
## 32
## Yazmin Vallejo
## 8
## Malcolm Fairbrother
## 14
## CSIC C. Valenciana
## 25
## ThinkR
## 26
## LOrtiz
## 48
## Vicenç Navarro
## 21
## Family Polarization
## 42
## Jared F Edgerton
## 12
## Francesco Rampazzo
## 50
## Tech Junkie
## 30
## Alberto Bayardo
## 2
## MA_Sociodemo_UPF
## 50
## Renata Franc
## 50
## Laboratorio Escapes
## 16
## Frauke Kreuter
## 50
## U. Ramon Llull (URL)
## 26
## Imanis Data
## 13
## Àngels Pont
## 36
## Daniel E Moreno
## 17
## colpolsocaragon
## 21
## Antti Kouvo
## 10
## Drone Creativo
## 5
## Cuebiq
## 5
## Mellow Yellow
## 7
## Verena Halbherr
## 50
## Silicon Beach Talent
## 12
## Tom Guterbock
## 43
## Dr. Emma Tumilty
## 14
## CSS at Columbia
## 1
## Now U Know Training
## 1
## Oxford Politics and IR
## 27
## Ansgar Hudde
## 50
## Vincent Brissot
## 28
## ScotCen
## 48
## Aclima, Inc.
## 3
## Bo
## 5
## Typ A Marketing
## 1
## CESSDA ERIC
## 50
## Edyta Kowal
## 9
## USGS R Community
## 5
## MATLAB Helper ®
## 16
## SIPA SusDev
## 2
## Kerry Barrett
## 2
## Sarah E. Patterson
## 50
## LAPOP
## 38
## Daniel Blanche
## 48
## HelpTheCrowd
## 3
## Elisenda Rentería
## 48
## ScotlandDST
## 26
## Folio
## 21
## Emily Gilbert
## 50
## EuropeanValuesStudy
## 50
## Devadas
## 7
## Akhil Sharma
## 17
## WHERE R THE KIDS
## 8
## Alex Lane
## 17
## Aaron Wazlavek
## 7
## Cornell SRI
## 35
## Max Brackett
## 2
## Narciso Michavila
## 43
## El Pati Descobert
## 43
## Consell d'Estudiants
## 17
## Invoice by Alto
## 14
## Alexandra Kupera
## 28
## UK Data Archive
## 50
## RJ Hayden \U0001f1ee\U0001f1ea \U0001f1e6\U0001f1fa \U0001f1fa\U0001f1f8
## 10
## Haidji
## 10
## Tony Vidler
## 23
## Leopoldo Cabrera
## 43
## Pau Vall i Prat\U0001f397
## 36
## SERISS EU
## 50
## Población CSIC
## 50
## 1st In SEO
## 30
## Drs. Albert Spijkers
## 26
## Yamil Nares
## 50
## Nexus Informática
## 27
## Istvan Hajnal
## 26
## Beatriz V.Garzón
## 12
## Ｔｏｎｙ Ｓｍｉｔｈ ＡＣＩＨ #SocialHousing
## 20
## monika jimenez
## 19
## UCC+i UV
## 26
## SurveyResearchCenter
## 27
## Imma T
## 11
## ATHLOS Project
## 15
## Lars Lauber
## 10
## Donald Reith
## 5
## Rodrigo
## 26
## Roger Barres
## 31
## María Sabatier
## 8
## Centres CERCA
## 22
## Jiten
## 22
## Sandra Nieto
## 23
## Community Commons
## 4
## Dr. Sofie Marien
## 36
## Molly Goodman \U0001f4ab
## 9
## raphaël couderc
## 6
## David Nelson
## 9
## Ed Eldridge
## 6
## Mirela Causevic
## 28
## CorrelViz
## 20
## Kyle Wackrow
## 1
## C-Metriks
## 8
## Sara Marsillas
## 8
## Dr Emmanuel Caillaud
## 7
## European University
## 36
## LSE Statistics
## 23
## Media4Math
## 8
## LISResearchAu
## 12
## Paul Hitlin
## 24
## Pippa Norris
## 44
## HR Tech Online
## 29
## Swapnil Popat
## 21
## UNACNCRB
## 4
## Maaz Gardezi
## 2
## ESS_Deutschland
## 50
## Comité MMSS - FES
## 14
## Pablo Barberá
## 43
## Agnese Vitali
## 50
## Alessandra Petrucci
## 24
## paolo parra saiani
## 40
## Thought Layer
## 14
## Elena Ambrosetti
## 50
## Mariano Torcal
## 44
## PitchBook Data
## 8
## cswsolutions
## 14
## Mercè Roca
## 8
## Michael Povel
## 17
## NexGen Research
## 21
## CSIC Catalunya
## 26
## World Programming
## 18
## Methodology Center
## 17
## AppliedDemogToolbox
## 38
## Timberlake
## 27
## IC Kollectif
## 23
## HPCNY
## 7
## Junyan Zhu
## 16
## Muthumeena
## 2
## BigData
## 22
## EP
## 45
## Ined
## 50
## Isaac Ddumba
## 11
## ISER
## 50
## ObservatorioDeRedes
## 19
## Webdatanet COST
## 50
## Media Psychology
## 15
## DATAx
## 26
## Big Data Week
## 26
## Valeria Bordone
## 50
## Public Policy Center
## 11
## Posgrado CSIC
## 26
## Alessandro Di Nallo
## 50
## Roy Jackaman
## 3
## Ministerio Economía
## 10
## Peymaneh Shafi
## 2
## Dr Mike Sutton
## 12
## Carlos E. Lagorio
## 50
## Anna Brown
## 50
## Beatriz Serrano
## 13
## Dominic Nyhuis
## 38
## Kenneth Fernandez
## 48
## SOURCE
## 8
## Elite Research
## 26
## Ray Walshe
## 11
## NUCATS Institute
## 6
## XAVIER SIRÉS
## 4
## Kirk Borne
## 37
## Gianluca Cafagna
## 6
## Lisa Horwich
## 12
## Carlos J. Gil
## 42
## Blanca López Zamora
## 4
## Alice Goisis
## 50
## Liz Hamel
## 27
## Ronald van Loon
## 30
## NCCR LIVES
## 50
## Eralba Cela
## 26
## Manuel Betancurt
## 22
## Henrik Dobewall
## 21
## Txell Argelagués
## 21
## AI Newsletter
## 9
## BASTION Digital
## 19
## Willem van de Ven
## 4
## Bate Brand
## 2
## Sanja Rahim
## 16
## Soledad Caballero
## 15
## JFkw
## 5
## Daniel Oberski
## 50
## PhD Forum
## 35
## Chiara Pensato
## 1
## Col·legi de Politòlegs i Sociòlegs de Catalunya
## 36
## Mathew Blanchfield
## 30
## PamelaJF
## 15
## ICPS
## 33
## Voice of Researchers
## 45
## Survey Magazine
## 35
## Muntasir Masum
## 32
## H. Karamanoukian MD
## 11
## Markus Quandt
## 46
## Ilary Bottini
## 2
## PNGumich
## 13
## BuzzCloud
## 2
## Gretchen Donehower
## 15
## ADD Markable
## 4
## ipfconline
## 30
## Jamie Ferrill
## 8
## Anittah/Digital
## 19
## Nazario Biala
## 15
## Mario Cortina Borja
## 20
## UCT IP Unit
## 1
## Julio Rezende, PhD
## 14
## ComPolCat
## 18
## ESS ERIC
## 50
## Forwards
## 16
## aklanta kalita
## 6
## DemoLab_UEvora
## 50
## UM SRC
## 50
## Biomass Research
## 3
## SocArXiv
## 45
## Ajay Grover
## 19
## Barry Schouten
## 50
## Eileen Omosa
## 11
## Gail Farrelly
## 17
## Robk News
## 28
## Woking Stronger IN
## 4
## CourseHour
## 28
## Spiritual Landscapes
## 2
## Sheila Cherry
## 1
## Theoni Stathopoulou
## 26
## EESresearch
## 36
## Ilya Kashnitsky
## 50
## In Summa Innovation
## 26
## CED Barcelona
## 50
## CXO Events
## 24
## PyData
## 16
## D.J. Flynn
## 22
## Meetup R Nantes
## 14
## Marko Bernasconi
## 18
## Big Data News
## 19
## Chuck Schoeneberger
## 6
## Mark Bryan
## 22
## Allen Y. Tien MD MHS
## 30
## Francisco I Pedraza
## 8
## Dr Anja Neundorf
## 38
## Frank La Vigne
## 28
## The R Foundation
## 20
## Lala H. Muradova
## 25
## Danielle Uskovic
## 9
## POLEXP
## 29
## SRMS of ASA
## 50
## DemoSoc UPF
## 50
## BIGSSS Bremen
## 36
## PISA_Facts
## 2
## Rene Bautista
## 50
## UNC European Studies
## 1
## AERA MMR SIG
## 1
## WVS Spain
## 6
## Observatori Recerca
## 26
## Sílvia Majó Vázquez
## 37
## María Ramos
## 43
## Roberta Rù
## 50
## mel bartley
## 50
## Onsoft (Pty) Ltd
## 12
## CSIS
## 44
## Abt Data Science, Surveys & Enabling Technologies
## 48
## CREW
## 50
## Kasule Alex
## 2
## BusinessIntelligence
## 28
## BigSurv18
## 50
## Nathanael Gratias
## 8
## +Politología
## 36
## CPC
## 50
## Pompeu
## 20
## Martin Ravallion
## 7
## SUDA
## 50
## Stuart Gray #FBPE
## 2
## Arndt Leininger
## 39
## Aïda Solé Auró
## 50
## Dave Saunders
## 1
## Jessica Holzberg \U0001f937\U0001f3fc♀️
## 50
## Universitat Politècnica de València
## 26
## Alison Park
## 50
## PureTech Talent
## 4
## Survey Practice
## 50
## IPZ
## 37
## PolNet 2018
## 30
## AAPOR's Got Talent
## 29
## Diederik Boertien
## 50
## Felix Haass
## 38
## Enric Cid
## 32
## Maria Sironi
## 50
## Bad Survey Question
## 50
## Peter Whiteford
## 45
## Eka Software
## 16
## ISU
## 18
## Survey Methods
## 46
## European Social Survey
## 38
## ColpisGenere
## 11
## RES
## 34
## GTI UPF - Interactive Technologies Group
## 10
## Javier Carbonell
## 35
## Ken Bodnar
## 30
## Gratuitous Phil
## 12
## Raphael Nishimura
## 49
## Léa Pessin
## 50
## Alejandro Moreno
## 44
## Rstats
## 18
## Vidal Romero
## 20
## aedemo
## 27
## Gary Pollock
## 33
## Big Data Conference
## 24
## virginia
## 45
## Prof Peter Lynn
## 50
## Writing For Research
## 48
## Rory Fitzgerald
## 50which(coreness(g)==50) # what is the core of the network?## Angelika Scheuer
## 4
## Ineke Stoop
## 22
## Raül Tormos
## 39
## Eric Harrison
## 49
## Alexandru Cernat
## 53
## WAPOR
## 60
## OpenPop.org
## 63
## Mark Amos
## 67
## Mario Callegaro
## 98
## Josh De La Rosa
## 105
## Peter Lugtig
## 106
## World Values Survey
## 123
## ESRA
## 127
## Andrew Mercer
## 138
## Herodato
## 151
## Stas Kolenikov
## 153
## Michael Link
## 159
## GESIS
## 169
## Wittgenstein Centre
## 183
## Ctr for Political St
## 184
## NIDI
## 201
## Francesco C Billari \U0001f1ea\U0001f1fa\U0001f1ee\U0001f1f9
## 213
## Social Research Assn
## 227
## Wojciech Jablonski
## 232
## Worka Holic
## 257
## Alexander Wenz
## 259
## Stefanie Hoherz \U0001f1ea\U0001f1fa
## 262
## IPUMS International
## 267
## Marieke Haan
## 292
## Michael Bosnjak
## 296
## Ulrich Krieger
## 298
## ASA Sociology
## 300
## AAPOR
## 301
## Jon Burton
## 328
## Sociology@Oxford
## 331
## ESRC
## 332
## Ruben van Gaalen
## 333
## Ana Slavec\U0001f426
## 340
## ECSR Sociology
## 342
## Bernd Weiss
## 344
## Dr. Annie Rights Research
## 346
## Jana Javornik
## 365
## U-M ISR
## 374
## Gerry Nicolaas
## 380
## Damiano Uccheddu
## 398
## Population Europe
## 401
## Eiji Matsuda
## 409
## Yfke \U0001f609ngena
## 411
## NCRM
## 419
## UM SurveyMethodology
## 422
## Florian Keusch
## 426
## TSE15 Conference
## 427
## bruno arpino
## 432
## Sergi Vidal
## 440
## Insights Association
## 441
## Emilio Zagheni
## 480
## Demografía (CSIC)
## 487
## Kyley McGeeney
## 494
## Bart Meuleman
## 510
## Francesco Rampazzo
## 522
## MA_Sociodemo_UPF
## 525
## Renata Franc
## 526
## Frauke Kreuter
## 528
## Verena Halbherr
## 538
## Ansgar Hudde
## 545
## CESSDA ERIC
## 551
## Sarah E. Patterson
## 557
## Emily Gilbert
## 564
## EuropeanValuesStudy
## 565
## UK Data Archive
## 578
## SERISS EU
## 584
## Población CSIC
## 585
## Yamil Nares
## 588
## ESS_Deutschland
## 628
## Agnese Vitali
## 631
## Elena Ambrosetti
## 635
## Ined
## 653
## ISER
## 655
## Webdatanet COST
## 657
## Valeria Bordone
## 661
## Alessandro Di Nallo
## 664
## Carlos E. Lagorio
## 669
## Anna Brown
## 670
## Alice Goisis
## 684
## NCCR LIVES
## 687
## Daniel Oberski
## 699
## ESS ERIC
## 724
## DemoLab_UEvora
## 727
## UM SRC
## 728
## Barry Schouten
## 732
## Ilya Kashnitsky
## 742
## CED Barcelona
## 744
## SRMS of ASA
## 761
## DemoSoc UPF
## 762
## Rene Bautista
## 765
## Roberta Rù
## 772
## mel bartley
## 773
## CREW
## 777
## BigSurv18
## 780
## CPC
## 783
## SUDA
## 786
## Aïda Solé Auró
## 789
## Jessica Holzberg \U0001f937\U0001f3fc♀️
## 791
## Alison Park
## 793
## Survey Practice
## 795
## Diederik Boertien
## 799
## Maria Sironi
## 802
## Bad Survey Question
## 803
## Léa Pessin
## 816
## Prof Peter Lynn
## 824
## Rory Fitzgerald
## 826which(coreness(g)==1) # what is the periphery of the network?## Mike McCulloch Business Strategy Prerit Saxena
## 19 25 26
## United Way of LebCo Mike Hine Remco Ploeg
## 29 52 108
## Daniel Liria Campón ۞♀ Ben Carlos Thypin Palmer Gibbs
## 110 152 174
## Encuestas MURAL SpaethCommunications Score and Change
## 185 198 205
## YouThisMe Ernesto Treviño Ronz Opinno
## 225 250 271
## MDMroczkowski #SherDilKejriwal Aleksander Beryozkin
## 362 381 394
## FB Network Caucus of Working Ed Adam Bulley
## 404 407 447
## Working Washington TxGenJobs The_Quipper
## 464 491 492
## CSS at Columbia Now U Know Training Typ A Marketing
## 542 543 550
## Kyle Wackrow Chiara Pensato UCT IP Unit
## 614 701 721
## Sheila Cherry UNC European Studies AERA MMR SIG
## 739 766 767
## Dave Saunders
## 790# looking at what predicts being in the core
df$k <- coreness(g)
# text?
recsm <- dfm(corpus(df, text_field="description"))
head(textstat_keyness(recsm, target=docvars(recsm)$k==50,
measure="lr"), n=20)## feature G2 p n_target n_reference
## 1 survey 97.301355 0.000000e+00 50 39
## 2 research 45.451824 1.564393e-11 50 98
## 3 demography 29.165565 6.644978e-08 14 8
## 4 european 20.252629 6.786013e-06 12 10
## 5 population 19.832949 8.451324e-06 9 4
## 6 the 19.701384 9.053578e-06 55 187
## 7 social 16.926445 3.885647e-05 32 90
## 8 methodologist 16.608238 4.595099e-05 9 6
## 9 methodology 13.710744 2.132311e-04 10 11
## 10 tweeting 13.632185 2.223410e-04 6 2
## 11 sociology 12.787468 3.489490e-04 11 15
## 12 demographic 12.389435 4.317699e-04 5 1
## 13 surveys 11.981985 5.371734e-04 7 5
## 14 demographer 11.807091 5.900556e-04 6 3
## 15 longitudinal 10.278960 1.345557e-03 5 2
## 16 in 10.240204 1.374124e-03 40 154
## 17 ; 9.055755 2.618693e-03 15 39
## 18 issues 8.704637 3.174016e-03 5 3
## 19 methods 8.360645 3.834345e-03 12 26
## 20 eric 7.837957 5.116039e-03 3 0head(textstat_keyness(recsm, target=docvars(recsm)$k<5,
measure="lr"), n=20)## feature G2 p n_target n_reference
## 1 to 12.417801 0.0004252607 30 99
## 2 we 10.224971 0.0013855194 13 27
## 3 sustainable 9.061844 0.0026099863 4 1
## 4 healthcare 8.946449 0.0027800950 5 3
## 5 teacher 7.984424 0.0047181513 3 0
## 6 job 7.984424 0.0047181513 3 0
## 7 the 7.536871 0.0060448941 44 198
## 8 a 7.308858 0.0068615529 31 127
## 9 senior 5.801002 0.0160170430 5 6
## 10 environmental 5.653152 0.0174240275 3 1
## 11 ! 5.573371 0.0182356170 11 30
## 12 your 5.349333 0.0207301972 6 10
## 13 development 5.211520 0.0224377126 7 14
## 14 all 4.806647 0.0283501533 8 19
## 15 ma 4.272069 0.0387437355 3 2
## 16 templates 4.214346 0.0400835086 2 0
## 17 very 4.214346 0.0400835086 2 0
## 18 person 4.214346 0.0400835086 2 0
## 19 developing 4.214346 0.0400835086 2 0
## 20 #publicidad 4.214346 0.0400835086 2 0If you want to learn more about this technique, we recently published a paper in PLOS ONE where we use it to study large-scale Twitter networks in the context of protest events.
In case you’re curious, here’s the code I used to collect the data:
library(tweetscores)
options(stringsAsFactors=F)
oauth_folder = "~/Dropbox/credentials/twitter"
accounts <- getFriends("RECSM_UPF", oauth=oauth_folder)
# creating folders (if they do not exists)
try(dir.create("friends"))
# first check if there's any list of friends already downloaded to 'outfolder'
accounts.done <- gsub(".rdata", "", list.files("friends"))
accounts.left <- accounts[accounts %in% accounts.done == FALSE]
accounts.left <- accounts.left[!is.na(accounts.left)]
# loop over the rest of accounts, downloading friend lists from API
while (length(accounts.left) > 0){
# sample randomly one account to get friends
new.user <- sample(accounts.left, 1)
#new.user <- accounts.left[1]
cat(new.user, "---", length(accounts.left), " accounts left!\n")
# download followers (with some exception handling...)
error <- tryCatch(friends <- getFriends(user_id=new.user,
oauth=oauth_folder, sleep=0.5, verbose=FALSE), error=function(e) e)
if (inherits(error, 'error')) {
cat("Error! On to the next one...")
accounts.left <- accounts.left[-which(accounts.left %in% new.user)]
next
}
# save to file and remove from lists of "accounts.left"
file.name <- paste0("friends/", new.user, ".rdata")
save(friends, file=file.name)
accounts.left <- accounts.left[-which(accounts.left %in% new.user)]
}
# keeping only those for which we have the name
accounts <- gsub(".rdata", "", list.files("friends"))
# reading and creating network
edges <- list()
for (i in 1:length(accounts)){
file.name <- paste0("friends/", accounts[i], ".rdata")
load(file.name)
if (length(friends)==0){ next }
chosen <- accounts[accounts %in% friends]
if (length(chosen)==0){ next }
edges[[i]] <- data.frame(
source = accounts[i], target = chosen)
}
edges <- do.call(rbind, edges)
nodes <- data.frame(id_str=unique(c(edges$source, edges$target)))
# adding user data
users <- getUsersBatch(ids=nodes$id_str, oauth=oauth_folder)
nodes <- merge(nodes, users)
library(igraph)
g <- graph_from_data_frame(d=edges, vertices=nodes, directed=TRUE)
g
names(nodes)[1:2] <- c("Id", "Label")
names(edges)[1:2] <- c("Source", "Target")
write.csv(nodes, file="../data/recsm-nodes.csv", row.names=FALSE)
write.csv(edges, file="../data/recsm-edges.csv", row.names=FALSE)