Identifying influential twitter users
Download as PPTX, PDF•1 like•517 views
This study analyzed influential Twitter users discussing Sejong City, South Korea by identifying key users, examining their activities, relationships, and keywords. The researchers found that influential users included media outlets and ordinary users who frequently posted and had many followers and followings, indicating they addressed public issues and had influence. Influential users tended to interact more than media outlets. Keyword analysis showed discussions focused on politicians, the Sejong City law, and other social and political issues.
Identifying influential twitter users
- 1. Chien-leng Hsu (Post-doctoral research fellow)Se Jung Park (PhD student)Han Woo Park (Associate Professor)Department of Media & Communication, WCU Webometrics Institute, Yeungnam [email protected] http://www.hanpark.nethttp://english-webometrics.yu.ac.krPresented at the 5th Complexity Conference, 27 Nov 2010, Seoul, KoreaIdentifying influential Twitter usersThe case of Sejong City in South Korea
- 2. About this studyThis research explores influential Twitter users and Tweets by:Using Sejong City (세종시) as the case studyUsing different measurement methodsStudying topics (keywords) mentioned in the Tweets
- 3. Key Users on Twitter CommunitiesThe 2-step flow of communication theory (Katz & Lazarsfeld, 1964)(Online) opinion leaders:determinants of rapid & sustained behaviorchange of members in a community (Valent & Davis, 1999)Park, Jeong & Han (2008)practices (political) participation deligentlyaggressively expresses opinions
- 4. Identifying Key Twitter UsersThe “network structure” approach: fails to identify influential Twitter users (Leavitt et al, 2009; Haddadi et al, 2010) The “actor relation” approach:content reachabilityFisher & Gilbert (2009) ➭ replies, retweets, mentions & attributionsThe majority of users: silent & passivea user’s influence: information forwarding activity (Romero et al, in submission)Trace influential user over time
- 5. The Sejong City ProjectThe original plan (Moo-Hyun Roh in 2005):To allocate 2/3 of government offices to Sejong, Chungnam (충남)Necessary for regional developmentThe excessive centralization of Seoul & its vicinity➭ limited innovation potential (Shapiro, So & Park, 2010)The revised plan (Myung-Bak Lee):A center for education, scientific research & high-tech industriesPartitioning the capital would weaken Korea’s competitiveness & innovation capability
- 6. Research QuestionsWho are the influential users who produce Tweets related to the Sejong City project?What are activities of the influential users?What is the relationship between the influential users?What are the keywords frequently used by the influential users in the Sejong City issue network?
- 7. Data collection & analytical techniquesData collectionDates of collection: 15 March ~ 12 April 2010Twitter scraper: An automated computer program to retrieve Tweets from Twtkr (twitterkr.com)Twitter API: Twitter user’s public dataAnalytical techniquesBasic data:LocationNumber of TweetsLists of followingsLists of followersPearson correlation testFour posting activities:Normal tweetsBeing retweeted by othersBeing replied by othersBeing mentioned by othersKrkwic (keywords analysis)
- 8. (I) Identification of influential users
- 9. (II) Twitter activities of the influential users
- 10. (III) Relationships between the influential users
- 11. (IV) Keywords in the issue network of Sejong City
- 12. Amendment of Sejong City law & politiciansCritical reviews on Sejong City lawControversies & solutionsAgreement & social welfareOther social & political issuesConflicts between political partiesPolitical ideologies & concerns on national debtNational policies
- 13. Discussions (I)Influential users include media outlets & ordinary usersCorrelation tests:The occurrence of Tweets vs. the number of Tweets ➭ significantly correlated (Pearson correlation=0.663, p<.01)➭ Influential users tended to address public issuesThe number of followers vs. the number of followings➭ significantly correlated (Pearson correlation=0.871, p<.01)➭ Influential users had mutual ties in the networkInfluential users are likely to act as news brokers & deliver their views in a single-issue communityHaving mutual relations with other influential users may allow an influetial user to make his/her own opinions available to a wider audience
- 14. Discussions (II)Referral activities/relationshipsMedia outlets ➭ normal tweets ➭ messages were not circulated well among other usersOrdinary usersnormal tweets, retweets, mentions & replies More likely to interact with the indirect presence of media outletsKeyword networkPoliticians, government projects & social-political issues mentionedInfluential user some keywords specific to his/her clustersimilar keywords used ➭ a sense of community
- 15. Thank you.