#mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks
1 like802 views
The document discusses user behavior across multiple social networks, highlighting that 74% of internet users engage with online social networks and the average user maintains around 5.54 accounts. It outlines a dataset involving six social networks from 2011 to 2014, analyzing user profiles, posts, and cross-sharing activities. The findings indicate variances in user activity levels and the use of different platforms for personal versus work-related content.
![23
Topic Modeling
Topic 1
• love
• father
• mother
• vacation
• dinner
Topic 1
• love
• father
• mother
• vacation
• dinner
LDA
1. Family
2. Technology
3. Music
4. <Unknown>
.
.
.
50. Food
Collection of Documents
(posts)
Top words that
belong to a cluster Inferred topics
Topic 1
• love
• father
• mother
• vacation
• dinner
• brother
• […]
• Latent Dirichlet Allocation (LDA)(Blei et al., 2003)
Posts - Topical Analysis](https://image.slidesharecdn.com/asonampresentation-150913190240-lva1-app6891/85/mytweet-via-Instagram-Exploring-User-Behaviour-Across-Multiple-Social-Networks-23-320.jpg)
#mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks
- 1. Web Information Retrieval / Natural Language Processing Group 1 #mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks Bang Hui Lim, Dongyuan Lu Tao Chen, Min-yen Kan
- 2. 2 Background Introduction 1. http://www.statista.com/statistics/272014/global-social-networks-ranked-by-number-of-users/ 2. http://www.pewinternet.org/fact-sheets/social-networking-fact-sheet/ 3. http://www.globalwebindex.net/blog/internet-users-have-average-of-5-social-media-accounts Numberofusers/million 0 400 800 1200 1600 Active users worldwide 1 • 74% of Internet users use Online Social Networks (OSN)2 • Average user has 5.54 Social Media accounts3 • Uses 2.82 sites actively
- 3. 3 • Most research done on single OSN • Holistic modelling of users • Multi OSN research: • Forecasting evolution of trending topics across different OSNs (Althoff et al. 2013) • Internetwork interactions (Chen et al. 2014) • How users behave across Image-based and Text-based networks (Ottoni et al. 2014) Motivation Introduction
- 4. 4 • 6 OSNs: Flickr, Google+, Instagram, Tumblr, Twitter and Youtube • Multi-network analysis of user behaviour • Cross network interactions • Publicly available data • No image / video analysis Scope Introduction
- 5. 5 3 ways to cross-share 1. Native feature Instagram 2. Third party app Hootsuite 3. Copy and paste Twitter to Facebook Introduction
- 6. 6 • Introduction • Dataset • User Profile • Posts - Cross-sharing - Temporal Analysis - Topic Analysis • Conclusion Outline
- 8. 8 • 6 OSNs • 2011 - 2014 • 32 K Users • 4 accounts / user Dataset Dataset Flickr Google+ Instagram Tumblr Twitter Youtube 11.9K 27.8K 16.7K 20.4K19.6K 14.5K Users Flickr Google+ Instagram Tumblr Twitter Youtube 1.3M 88.4M 9M2.8M2.6M14.8M Posts
- 9. 9 User Statistics Twitter Google Instagra Tumblr Flickr YouTube Twitter 79.4 76.4 65.2 64.4 56.2 Google 96.4 73.5 61.7 61.0 65.0 Instag 96.7 76.8 68.5 60.4 51.0 Tumblr 96.0 74.9 78.8 59.4 49.2 Flickr 96.0 74.8 71.0 60.1 53.3 YouTub 95.5 84.1 68.4 56.6 60.9 also use: %ofuserswhouse: Dataset
- 10. 10 • 40% of users are active on any given day • More networks utilised on days with higher activity Activity Statistics Dataset Average number of networks used, daily (2, 0.9) (2.75, 0.9)
- 11. 11 • Introduction • Dataset • User Profile • Posts - Cross-sharing - Temporal Analysis - Topic Analysis • Conclusion Outline
- 12. 12User Profile 👤 I’m a Digital Media Specialist passionate about self education, lifelong learning... Explore Dream Create. Knowledge is freedom. I run a website called DIY Genius that helps young people self education. All my photographs are posted under the creative commons non commercial attribution... I’m interested in digital media, adventure sports, and mountains. A collection of videos I’ve filmed on my iPhone while hiking skiing and biking in the mountains.
- 13. 13 • Pairwise Jaccard Coefficient Self-description Similarity User Profile
- 14. 14 • Introduction • Dataset • User Profile • Posts - Cross-sharing - Temporal Analysis - Topic Analysis • Conclusion Outline
- 15. 15 • Multicasting user activity over multiple social networks. • Source-sink relationship between OSNs Cross-sharing Posts - Cross-sharing Source Sink
- 16. 16 Source - Sink Graph Posts - Cross-sharing
- 17. 17 • Introduction • Dataset • User Profile • Posts - Cross-sharing - Temporal Analysis - Topic Analysis • Conclusion Outline
- 18. 18 • Different peaks for activity levels on weekend and on weekdays Time of Day Posts - Temporal Analysis Weekday Weekend
- 19. 19 » Different uses for OSNs - personal vs work Day of Week Posts - Temporal Analysis
- 20. 20 • Introduction • Dataset • User Profile • Posts - Cross-sharing - Temporal Analysis - Topic Analysis • Conclusion Outline
- 21. 21 The “Average user” Posts - Topical Analysis
- 22. 22 • User description keywords • 3 professions: Developer, Producer, Marketing expert • How do different professions use different OSNs? • OSN for work, OSN for personal use Meso-Level Groups: Profession Posts - Topical Analysis
- 23. 23 Topic Modeling Topic 1 • love • father • mother • vacation • dinner Topic 1 • love • father • mother • vacation • dinner LDA 1. Family 2. Technology 3. Music 4. <Unknown> . . . 50. Food Collection of Documents (posts) Top words that belong to a cluster Inferred topics Topic 1 • love • father • mother • vacation • dinner • brother • […] • Latent Dirichlet Allocation (LDA)(Blei et al., 2003) Posts - Topical Analysis
- 24. 24 Matching Developer Technology . . Mobile Gadgets . . Food TopicsProfession 👤 “New Ubuntu image available on Digital Ocean. Sweet!” “I love taco bell :D” Posts LDA • Match topics to professions manually Posts - Topical Analysis Work related Non-work related
- 25. 25 Workaholic: Top 2 frequently topics are work related Many People are Workaholics! 65% 70% 75% 80% 85% 90% Producer Marketing Expert Developer UserPercentage Posts - Topical Analysis
- 26. 26 OSNs for Work Related Posts UserPercentage 0% 10% 20% 30% 40% Twitter Google+ Youtube Tumblr Instagram Flickr Producer Marketing Expert Developer Posts - Topical Analysis
- 27. 27 • Introduction • Dataset • User Profile • Posts - Cross-sharing - Temporal Analysis - Topic Analysis • Conclusion Outline
- 28. 28 • 6 OSNs: Flickr, Google+, Instagram, Tumblr, Twitter and Youtube • Most users describe themselves differently. • OSN cross-sharing directionality - sink and source • YouTube and Instagram are popular content originators • Twitter is a content aggregator • OSNs for work and personal use • Dataset will be available at: http://wing.comp.nus.edu.sg/ downloads/aboutme Conclusion Conclusion
- 29. 29 👤 I’m a Digital Media Specialist passionate about self education, lifelong learning... Explore Dream Create. Knowledge is freedom. I run a website called DIY Genius that helps young people self education. All my photographs are posted under the creative commons non commercial attribution... I’m interested in digital media, adventure sports, and mountains. A collection of videos I’ve filmed on my iPhone while hiking skiing and biking in the mountains. Conclusion
- 30. Web Information Retrieval / Natural Language Processing Group 30 Thank you!