Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Visual Analysis of Topic Competition on Social Media

3,679 views

Published on

How do various topics compete for public attention when they are spreading on social media? What roles do opinion leaders play in the rise and fall of competitiveness of various topics? In this study, we propose an expanded topic competition model to characterize the competition for public attention on multiple topics promoted by various opinion leaders on social media. To allow an intuitive understanding of the estimated measures, we present a timeline visualization through a metaphoric interpretation of the results. The visual design features both topical and social aspects of the information diffusion process by compositing ThemeRiver with storyline style visualization. ThemeRiver shows the increase and decrease of competitiveness of each topic. Opinion leaders are drawn as threads that converge or diverge with regard to their roles in influencing the public agenda change over time. To validate the effectiveness of the visual analysis techniques, we report the insights gained on two collections of Tweets: the 2012 United States presidential election and the Occupy Wall Street movement.

The slide deck was made by Panpan Xu and presented by her in IEEE VAST 2013.

More details about this project can be found from the project page:
http://www.ycwu.org/projects/vast13.html

Published in: Social Media, Education, Business
  • Be the first to comment

Visual Analysis of Topic Competition on Social Media

  1. 1. … VAST 13 … Visual Analysis of Topic Competition … on Social Media Panpan Xu1, Yingcai Wu2, Enxun Wei2, Tai-Quan Peng3, Shixia Liu2, Jonathan J.H. Zhu4, Huamin Qu1 1 Hong Kong University of Science and Technology 2 Microsoft Research Asia 3 Nanyang Technological University 4 City University of Hong Kong 1
  2. 2. On Social Media: Diffusion of multiple topics Google Ripples The Interaction: Do people get distracted away from some topics when something more “eyecatching” is happening? The Influence: How do the opinion leaders (influential users) affect the interaction by recruiting the public attention for some topics? INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 2
  3. 3. Google Ripples [F. Viégas et al. 11] Whisper [N. Cao et al. 12] INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 3
  4. 4. Agenda-setting [M. E. McCombs and D. L. Shaw 72] Topic competition [J. Zhu 92] Two-step information flow The ability of the news media (e.g. TV and newspaper) to influence the salience of topics on the public agenda. The addition of any new topic onto the public agenda comes at the cost of other topic(s). The information reaches the masses via intermediaries. [S. Wu et.al 11] INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 4
  5. 5. Agenda-setting [M. E. McCombs and D. L. Shaw 72] Topic competition [J. Zhu 92] Two-step information flow The ability of the news media (e.g. TV and newspaper) to influence the salience of topics on the public agenda. The addition of any new topic onto the public agenda comes at the cost of other topic(s). The information reaches the masses via intermediaries. [S. Wu et.al 11] INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 5
  6. 6. Agenda-setting [M. E. McCombs and D. L. Shaw 72] Topic competition [J. Zhu 92] Two-step information flow [S. Wu et al. 11] The ability of the news media (e.g. TV and newspaper) to influence the salience of topics on the public agenda. The addition of any new topic onto the public agenda comes at the cost of other topic(s). The information reaches the masses via intermediaries (opinion leaders). INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 6
  7. 7. Combine quantitative modeling and interactive visualization Healthcare Extract time varying measurements on • topic competitiveness • each opinion leader group’s influence on each topic • topic transition trend of each opinion leader group #china #debate Visualize • the dynamic relation between topics and opinion leader groups • textual contents of the posts INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 7
  8. 8. Combine quantitative modeling and interactive visualization Topic Transition Analysis Topic User group Text Search Topic Competition Modeling Timeline Visualization Word Cloud Raw Tweets List Time Series: Stream of tweets Collection of Tweets INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 8
  9. 9. Combine quantitative modeling and interactive visualization Topic Transition Analysis Topic User group Text Search Topic Competition Modeling Timeline Visualization Word Cloud Raw Tweets List Time Series: Stream of tweets Collection of Tweets INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 9
  10. 10. Combine quantitative modeling and interactive visualization Topic Transition Analysis Topic User group Text Search Collection of Tweets Topic Competition Modeling Time Series: Stream of tweets Timeline Visualization Word Cloud Raw Tweets List • Time-varying topic competitiveness • Each opinion leader group’s influence • Topic transition trend INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 10
  11. 11. Combine quantitative modeling and interactive visualization Topic Transition Analysis Topic User group Text Search Topic Competition Modeling Timeline Visualization Word Cloud Raw Tweets List Time Series: Stream of tweets Collection of Tweets INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 11
  12. 12. Topic Competition Model for traditional media: recruiting effect distraction effect [J. Zhu 92] INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 12
  13. 13. Topic Competition Model for traditional media: recruiting effect [J. Zhu 92] INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 13
  14. 14. Topic Competition Model for traditional media: distraction effect [J. Zhu 92] INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 14
  15. 15. The Extended Topic Competition Model: Two step information flow Heterogeneous influence (news media, grassroots) INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 15
  16. 16. The Extended Topic Competition Model: Two step information flow Heterogeneous influence (news media, grassroots) recruiting effect distraction effect INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 16
  17. 17. T-1 T Topic Transition Estimation … … … Transition matrix … INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 17
  18. 18. Topic Transition Analysis Timeline Output of Analysis and Modeling Step: Topic User group Topic Competition Modeling Visualization Word Cloud Raw Tweets List Time varying competitiveness of each topic Time Series: TimeText Search opinion leader groups’ influence on each topic varying volume of tweets The topic transition trend of the opinion leader groups between adjacent time stamps. Collection of Tweets INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 18
  19. 19. Topic competiveness Timeline view INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 19
  20. 20. Topic competiveness + Recruitment effect of different opinion leaders + Topic transition trend Media Political Figures Grassroots Timeline view Word Cloud INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 20
  21. 21. Word cloud filterable by: • • • Topic Time interval Opinion leader group Sparkline: • Time varying saliency of a word INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 21
  22. 22. Dataset: 2012 Presidential Election; 89, 174, 308 tweets; May 01 – Nov 10 Six general topics : welfare/society, defense/international issues, economy, election (general), election (horse race), law/social relations * Three opinion leader groups: media , political figures, and grassroots * *identified collaboratively with media researchers INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 22
  23. 23. Election (general) INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 23
  24. 24. INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 24
  25. 25. INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 25
  26. 26. INTRO / SYSTEM / MODEL / DESIGN / CASE STUDY 26
  27. 27. Visual analysis framework: Topic Transition Analysis Topic Topic Competition the topic competition on social Modeling User group Timeline Visualization Word Cloud Model media, the influence of opinion Raw Tweets List leader groups, and the topic transition trends. Text Search Time Series: volume of tweets Visualize the results of the models and allow for further exploration to Collection of Tweets form explanations. SUMMARY / LIMITATIONS & FUTURE WORK 27
  28. 28. Manual process to collect keywords and categorize opinion leaders more efficient ways? Time series modeling + the structural factors of social network ? Competition & cooperation other modes of interaction among topics? SUMMARY / LIMITATIONS & FUTURE WORK 28
  29. 29. Thank You for Attention ! 29

×