Mining Influencers in the German Twittersphere – Mapping a Language-Based Follow Network
0 likes388 views
The document discusses research on mining influencers in the German Twitter sphere, focusing on the follower/followee network and its implications for content exposure and community formation. It outlines research methods for sampling influential accounts, community detection, and keyword extraction, while addressing API limitations and the potential impact of public accounts on reach and visibility. The findings highlight the presence of various topical communities and the challenges of detecting bots within the network.
Mining Influencers in the German Twittersphere – Mapping a Language-Based Follow Network
- 1. Mining Influencers in the German Twittersphere Mapping a Language-Based Follow Network Felix Victor Münch1 , Ben Thies1 , Cornelius Puschmann1 , Axel Bruns2 1 Leibniz Institute for Media Research | Hans-Bredow-Institut (HBI), Germany 2 Digital Media Research Centre (DMRC), Queensland University of Technology (QUT), Australia IC2 S2 , July 2019, Amsterdam
- 2. Problem ‘I can’t get no population …’ ● follow/friend networks of Online Social Networks (OSNs) arguably main predictor for content exposure (despite sponsored content and algorithmic sorting of timelines) ● APIs too restrictive for collection of comprehensive follow networks
- 3. Opportunities Possible Research Questions ● “Are there filter bubbles/echo chambers?” ● “Are there social and/or topical communities/issue publics?” ● “Who can spread which content most efficiently?” ● “Can we predict the spread of (fake) news?” ● “Who let the bots out? And where?”
- 4. Background
- 5. The Australian Twittersphere Bruns, A., Moon, B., Münch, F. V., & Sadkowsky, T. (2017). The Australian Twittersphere in 2016: mapping the follower/followee network. Social Media + Society, 3(4). https://doi.org/10.1177/2056305117748162 Münch, F. V. (2019). Measuring the Networked Public – Exploring Network Science Methods for Large Scale Online Media Studies. Queensland University of Technology. https://doi.org/10.5204/thesis.eprints.125543
- 6. Method: Sample the influentials
- 7. Our adaptation of the ‘rank degree’ method Based on: Salamanos, N., Voudigari, E., & Yannakoudakis, E. J. (2017). Deterministic graph exploration for efficient graph sampling. Social Network Analysis and Mining, 7(1), 24. https://doi.org/10.1007/s13278-017-0441-6 Bottom: Original graph without walked edges. Starting nodes (seeds) are drawn randomly (1) and walker move to their friend with the highest in-degree (2-6). Walked edges get removed/‘burned’. Top: Current sample at each step. Walked (and symmetric) edges are added to sample. 1 2 3 4 5 6
- 8. Our adaptation of the ‘rank degree’ method Main adaptations (amongst others) mostly due to API restrictions: ● Undirected → Directed ● Fewer walkers (200) ● Walkers do not collapse when ending up on the same node ● Last 5000 friends only ● ‘Degree’ stays constant and is equal to follower count reported by Twitter API ● Only collect edges to accounts with German as their interface language (not possible anymore due to API changes ¯_(ツ)_/¯ … we work on a solution.)
- 12. Coverage Distribution of public accounts with > 1 friend in the test sample over the percentage of their friends that can be found in the influencer sample (left, filtered for in-degree >= 1, leaving 199,180 accounts) / baseline sample (right, same size, randomly drawn from German accounts in global dataset)
- 13. Coverage Ranked distribution of the percentage of ‘friends’ of accounts in a random sample (n=1000, filtered for having at least 2 ‘friends’) found in our influencer sample (excl. nodes with in-degree 0) and a random sample of the same size (181k accounts)
- 14. Reach Ranked distribution of the percentage of accounts reached in a random sample (n=1000, filtered for having at least 2 ‘friends’) by accounts in our influencer sample (excl. nodes with in-degree 0) and by accounts in a random sample of the same size (181k accounts)
- 15. Test study: Community detection and keyword extraction
- 16. Community detection with infomap 3-core of our sample network; coloured by communities detected with the infomap community detection algorithm; node size represents Page Rank
- 17. Keyword extraction with chi-squared criterion # active accounts keywords top accounts tag short tag 4 2015 e3, stream, xd, e32019, nintendo, twitch, game, crossing, pc, zelda, animal, gameplay, cyberpunk2077, games, switch, xbox, trailer, cyberpunk, gaming, xboxe3, uff, nice, geil, keanu, pk, spiele, live, nen, lol, mega unge, dagibee, Gronkh, MelinaSophie, LeFloid, iBlali, Taddl, rewinside, HandIOfIBlood, PietSmiet YouTubers & Gaming Youtube & Games 3 1855 berlin, innen, spd, berliner, studie, unternehmen, diskutieren, cdu, fordern, themen, wichtiger, bundesregierung, deutschen, digitalisierung, thema, wurde, wurden, annefrank, klimaschutz, mehr, juni, zeigt, deutschland, interview, politik, brandenburg tazgezwitscher, Die_Gruenen, Tagesspiegel, c_lindner, gutjahr, dunjahayali, sigmargabriel, sixtus, HeikoMaas, spdde German politics German Politics 11 1414 frauenstreik, schweiz, schweizer, glarner, svp, bern, frauenstreik2019, zürich, kanton, grosse, basel, nationalrat, frauen NZZ, 20min, viktorgiacobbo, Blickch, tagesanzeiger, srfnews, MikeMuellerLate, watson_news, migros, srf3 Swiss politics / women's strike Swiss Politics 2 1044 saison, trainer, bundesliga, neuzugang, spieler, dfb, fc, gerest, em, wechselt, estland, wechsel, transfer, tor, sieg, mannschaft, wm, cup, liga DFB_Team, FCBayern, ToniKroos, MarioGoetze, esmuellert_, Podolski10, Manuel_Neuer, Bundesliga_DE, ZDFsport, JB17Official German football Soccer 17 767 övp, spö, fpö, wien, österreich, bierlein, oenr, österreichs, ibiza, wiener, strache, kickl, türkis, hofer, parlament, nationalrat, zib2, abdullah, mandat, wahlkampf, zentrum, bundeskanzlerin, heinz, österreicher, glyphosat, antrag, blau florianklenk, sebastiankurz, IngridThurnher, kesslermichael, HannoSettele, vanderbellen, Gawhary, HBrandstaetter, HHumorlos, michelreimon Austrian politics Austrian Politics 33 751 menschen, nazi, merz, deutschland, afd, wer, akk, cdu, spd, jahre, leben, wäre, grünen, obwohl, jemand, klar, nazis, ja, liebe, wähler, bitte, viele, immer, mann, wissen, wünsche, herr, seit ntvde, Muhterem_Aras, munich_startup, Literaturtest, _schwarzeKatze, bmzimmermann, ninjawarriorrtl, cesurmilusoy, MetalabVie, S_chill_ing NTV (news channel) NTV 6 720 album, keanu officiallyjoko, damitdasklaas, siggismallz, thisiscro, latenightberlin, gamescom, EtienneToGo, ralphruthe, TheRocketBeans entertainment Entertainment 20 563 saschalobo, StefanOsswald, CarstenRossiKR, ragnarh, cbgreenwood, breitenbach, BBDO, Ugugu, ring2, julianheck Digital Communication DigiCom 22 510 Kachelmann, schmitt_it, RomeoMicev, Perspektive360, paulespcforumde, naturkosmetix, TUIDeutschland, glockendoktor, nachtnebel, HaraldKlein ? ? 13 453 lt, bett, morgens, hast, schön, hasse, müde, essen, ja, möchte, manchmal, mama, bitte, frau, nachts, immer, bier, nein, kaffee, gern, gar, jemand, weiß, mal, geh, glaube, ach, scheiße, tweets, hund, kinder, hätte, abends KuttnerSarah, Regendelfin, vergraemer, DrWaumiau, HappySchnitzel, katjaberlin, ArminRohde, RenateBergmann, hashcrap, peterbreuer "Feuilleton" / authors / copy Writers Authors 23 429 10jahrejk, joko, klaas, mtv, canadiangp, hitzekindofmagic, fernsehen ProSieben, MattBannert, newshausen, haveonenme, Mone_Horan, about_riki_, delay1, sarahofer8, sweettweetangie, JoanBleicher Pro7 (Private TV broadcaster) Pro7 42 376 dessau, roßlau, afd, görlitz, islam, vergewaltigt, migranten, asylbewerber, gefährder, abgelehnter, sed, wippel, patrioten, greta, niger, hosni, stärkste, grüne, fridayforfuture, afrikaner, rosslau, linke, gretathunberg, asylbewerbe, verbrechen, altparteien, merkel, linksradikale, grünen, habeck, schweigt, zerreißen, wählt, mädchen, flüchtling, sachsen, vergewaltigung, maas, bürger, islamistischer, sexuell DonJoschi, AfD, MSF_austria, Alice_Weidel, SteinbachErika, Joerg_Meuthen, Beatrix_vStorch, GrumpyMerkel, krone_at hard rights / migration / refugees Hard Right 30 369 mydirtyhobby, femdom, boobs, latex, milf, mistress, cock, anal, tits, blowjob, busty, fetish, livecam, pornstar, mdh, sexy, findom, highheels, clip, manyvids, cam, cumshot, cum, webcam, pussy, goddess, dirty, bdsm, porn, hot, horny, booty, slave Erotik_Center, AnnyAuroraPorn, texas_patti, LenaNitro1, sandy226, Julietta_com, ModelRoxxyX, swo2212, LucyCatOfficial, SuziAnneVX Porn Porn
- 18. Tagged Community graph Community graph of communities in the 3-core of our sample with over 300 accounts, at least 80 active accounts during the examined time frame, and edges with a weight of at least 150; edge width represents weight; edge direction follows clockwise curvature; edges coloured by source node; node size represents the number of accounts in each community
- 19. Outlook ● Adaptation to API changes ● Bootstrapping the seed pool ● Other language-based spheres ● Topical mining ● Other community detection methods ● Bot detection
- 20. Feedback and contributions welcome RaDICeS Rank Degree Influencer Core Sampler https://github.com/FlxVctr/RADICES @FlxVctr, @BenAThies, @cbpuschmann, @snurb_dot_info
- 21. Director’s Cut / Backup Slides
- 22. Interesting 🤔 Münch, F. V. (2019). Measuring the Networked Public – Exploring Network Science Methods for Large Scale Online Media Studies. Queensland University of Technology. https://doi.org/10.5204/thesis.eprints.125543
- 23. Coverage Count, mean, standard deviation, minimum, quartiles, and maximum of the number of friends and the percentages of friends in the influencer and baseline sample for public accounts in the test sample with at least 2 friends. n = 597 number of friends percent of friends in influencer sample percent of friends in baseline sample mean 57 40 0.54 std 160 30 2.7 min 2 0 0 25% 7 11 0 50% 18 40 0 75% 42 65 0 max 1988 100 50
- 24. Twitter is not representative for general population – but for itself https://www.pewinternet.org/2019/04/24/sizing-up-twitter-users/
- 25. Dominance of an active and influential elite https://www.pewinternet.org/2019/04/24/sizing-up-twitter-users/