1. 1 From Sentiment to Emotion Analysis in Social Networks Jie Tang Department of Computer Science and Technology Tsinghua University, China

2. 2 Networked World 1.3 billion users 640 million minutes/month 1.3 billion users 640 million minutes/month 248 million users influencing our daily life 248 million users influencing our daily life 800 million QQ users 549 million wechat users - revenue-Q1 2015 =3.6B 800 million QQ users 549 million wechat users - revenue-Q1 2015 =3.6B 640 million users 9K tweets/second 640 million users 9K tweets/second [1] http://www.statisticbrain.com/ 244 million active users 14 billion items/year 244 million active users 14 billion items/year 350 million active users 57 billion on 11/11 350 million active users 57 billion on 11/11

3. 3 Opinion Mining Innovation diffusion Business intelligence Info. Space Social Space Interaction Understanding the mechanism of interaction dynamics Info. Space vs. Social Space Social Networks

4. 4 Roadmap tie Social role User-level Tie-level Structure-level Influence

5. 5 Let us start with sentiment analysis…

6. 6 “Love Obama” I love Obama Obama is great! Obama is fantastic I hate Obama, the worst president ever He cannot be the next president! No Obama in 2012! Positive Negative

7. 7 Homophily Homophily —“birds of a feather flock together” –A user in the social network tends to be similar to their connected neighbors. Originated from different mechanisms –Influence Indicates people tend to follow the behaviors of their friends –Selection Indicates people tend to create relationships with other people who are already similar to them –Confounding variables Other unknown variables exist, which may cause friends to behave similarly with one another.

8. 8 Twitter Data Twitter –1,414,340 users and 480,435,500 tweets –274,644,047 t-follow edges and 58,387,964 @ edges [1] Chenhao Tan, Lillian Lee, Jie Tang, Long Jiang, Ming Zhou, and Ping Li. User-level sentiment analysis incorporating social networks. In KDD’11, pages 1397–1405, 2011.

9. 9 Influence Shared sentiment conditioned on type of connection.

10. 10 Selection Connectedness conditioned on labels

11. 11 Factor Graph Model Tweets by user v 3 The problem is cast as classifying sentiments by considering both content and network structure. Social link User-specific attributes

12. 12 Factor Graph Model (cont.) +

13. 13 SampleRank (“Learning”) likelihood ratio of new sample Y new and previous label Y for all users Relative performance between new sample Y new and previous label Y on labeled user only. Update model parameters when two results are inconsistent

14. 14 Results for Sentiment Analysis Twitter –1,414,340 users and 480,435,500 tweets –274,644,047 t-follow edges and 58,387,964 @ edges Baseline –SVM Vote Measures –Accuracy and Macro F1

15. 15

16. 16 Performance

17. 17 Performance Analysis in Different Topics

18. 18 Results of Different Learning Algorithms

19. 19

20. 20 How Do Your Friends on Social Media Disclose Your Emotions?

21. 21 Was Anna Happy When She Published This Photo On Flickr?

22. 22 Was Anna Happy When She Published This Photo On Flickr? A lovely doorplate Anna: a girl who just graduated

23. 23 Was Anna Happy When She Published This Photo On Flickr?

24. 24 Problem [1] Yang Yang, Jia Jia, Shumei Zhang, Boya Wu, Qicong Chen, Juanzi Li, Chunxiao Xing, and Jie Tang. How Do Your Friends on Social Media Disclose Your Emotions? In AAAI'14. pp. 306-312.

25. 25 Emotion Learning Method [1] Yang Yang, Jia Jia, Shumei Zhang, Boya Wu, Qicong Chen, Juanzi Li, Chunxiao Xing, and Jie Tang. How Do Your Friends on Social Media Disclose Your Emotions? In AAAI'14. pp. 306-312.

26. 26 Flickr Data 354,192 images posted by 4,807 users –For each image, we also collect its tags and all comments. –Thus we get 557,177 comments posted by 6,735 users in total Infer emotion of users by considering both image and tag/comments

27. 27 Emotion Inference SVM: regards the visual features of images as inputs and uses a SVM as a classifier. PFG: considers both color features and social correlations among images. LDA+SVM: first uses LDA to extract latent topics from comments, then uses visual features, topic distributions, and social ties as features to train a SVM. Averagely +37.4% in terms of F1

28. 28 To What Extend Your Friends Can Disclose Your Emotions? -Comments stands for the proposed method ignoring comment information -Tie ignores social tie information Fear images have similar visual features with Sadness and Anger. Homophily suggests that friends with similar interests tend to have similar understanding of disgust

29. 29 Image Interpretations Our model demonstrates how visual features distribute over different emotions. (e.g., images representing Happiness have high saturation) Positive emotions attract more response (+4.4 times) and more easily to influence others compared with negative emotions.

30. 30 Summary & Open Questions? Social networks bring revolutionary changes to the Web and unprecedented opportunities for us One question: what drives users’ sentiments?

31. 31 Sentiment vs. Emotion Charles Darwin: –Emotion serves as a purpose for humans in aiding their survival during the evolution. [1] Emotion is the driving force of user’s sentiments… Emotion stimulates the mind 3000 times quicker than rational thought! [1] Charles Darwin. The Expression of Emotions in Man and Animals. John Murray, 1872.

32. 32 Potential Directions From sentiment to emotion analysis? Add social theories into emotion analysis? Sentiment/emotion analysis for “Social Good”?

33. 33 Related Publications Chenhao Tan, Lillian Lee, Jie Tang, Long Jiang, Ming Zhou, and Ping Li. User-level sentiment analysis incorporating social networks. In KDD’11, pages 1397–1405, 2011. Yang Yang, Jia Jia, Shumei Zhang, Boya Wu, Qicong Chen, Juanzi Li, Chunxiao Xing, and Jie Tang. How Do Your Friends on Social Media Disclose Your Emotions? In AAAI'14. pp. 306- 312. Jie Tang, Yuan Zhang, Jimeng Sun, Jinghai Rao, Wenjing Yu, Yiran Chen, and ACM Fong. Quantitative Study of Individual Emotional States in Social Networks. IEEE Transactions on Affective Computing (TAC), 2012, Volume 3, Issue 2, Pages 132-144. (Selected as the Spotlight Paper) Xiaohui Wang, Jia Jia, Jie Tang, Boya Wu, Lianhong Cai, and Lexing Xie. Modeling Emotion Influence in Image Social Networks. IEEE Transactions on Affective Computing (TAC), Volume 6, Issue 3, 2015, Pages 286-297. Yuan Zhang, Jie Tang, Jimeng Sun, Yiran Chen, and Jinghai Rao. MoodCast: Emotion Prediction via Dynamic Continuous Factor Graph Model. In ICDM’10. pp. 1193-1198. Jia Jia, Sen Wu, Xiaohui Wang, Peiyun Hu, Lianhong Cai, and Jie Tang. Can We Understand van Gogh’s Mood? Learning to Infer Affects from Images in Social Networks. In ACM MM, pages 857-860, 2012. Xiaohui Wang, Jia Jia, Peiyun Hu, Sen Wu, Lianhong Cai, and Jie Tang. Understanding the Emotional Impact of Images. (Grand Challenge) In ACM MM. pp. 1369-1370. (Grand Challenge 2nd Prize Award)

34. 34 Thank you ！ Collaborators: Lillian Lee, Chenhao Tan (Cornell) Jinghai Rao (Nokia) Jimeng Sun (IBM/GIT) Ming Zhou, Long Jiang (Microsoft) Yuan Zhang, Jia Jia, Yang Yang, Boya Wu, Xiaohui Wang (THU) Jie Tang, KEG, Tsinghua U, http://keg.cs.tsinghua.edu.cn/jietanghttp://keg.cs.tsinghua.edu.cn/jietang Download all data & Codes, http://aminer.org/emotionhttp://aminer.org/emotion