From Sentiment to Emotion Analysis in Social Networks

Transcription

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

2 From Info. Space to Social Space Info. Space! Revolutionary changes! 1.Social Tie & Group Interaction! 2.Social Influence 3.Collective Intelligence! Social Space! 2

3 Revolutionary Changes Social Networks Search Education O2O... Embedding social in search: Google plus FB graph search Bing s influence Human Computation: CAPTCHA + OCR MOOC Duolingo (Machine Translation) The Web knows you than yourself: Contextual computing Big data marketing More 3

4 4 Let us start with sentiment analysis

5 Love Obama I love Obama I hate Obama, the worst president ever Obama is fantastic Obama is great! No Obama in 2012! He cannot be the next president! Positive Negative 5

6 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. 6

7 Twitter Twitter Data 1,414,340 users and 480,435,500 tweets 274,644,047 t-follow edges and edges [1] Chenhao Tan, Lillian Lee, Jie Tang, Long Jiang, Ming Zhou, and Ping Li. User-level sentiment analysis incorporating social 7 networks. In KDD 11, pages , 2011.

8 Influence Shared sentiment conditioned on type of connection. 8

9 Selection Connectedness conditioned on labels 9

10 One question: what drives users sentiments? 10

11 Sentiment vs. Emotion Emotion is the driving force of user s sentiments Charles Darwin: Emotion serves as a purpose for humans in aiding their survival during the evolution. [1] Emotion stimulates the mind 3000 times quicker than rational thought! [1] 11 Charles Darwin. The Expression of Emotions in Man and Animals. John Murray, 1872.

12 Happy System Can we predict users emotion? 12

13 The Old Summer Palace Dorm? Observations (cont.)? Classroom??? GYM Activity correlation Location correlation (Red-happy) Karaoke 13

14 Observations (a) Social correlation (a) Implicit groups by emotions (c) Calling (SMS) correlation 14

15 Observations (cont.) Temporal correlation 15

16 16 Methodologies

17 MoodCast: Dynamic Continuous Factor Graph Model MoodCast Social correlation g(.) Jennifer Allen Mike Temporal correlation h(.) Jennifer yesterday Neutral Allen Happy Jennifer today Happy Neutral Mike Predict Jennifer tomorrow? Attributes f(.) location call sms Our solution 1. We directly define continuous feature function; 2. Use Metropolis-Hasting algorithm to learn the factor graph model. [1] Jie Tang, Yuan Zhang, Jimeng Sun, Jinghai Rao, Wenjing Yu, Yiran Chen, and ACM Fong. Quantitative Study of Individual 17 Emotional States in Social Networks. IEEE TAC, 2012, Volume 3, Issue 2, Pages

18 Problem Formulation Time t G t =(V, E t, X t, Y t ) Emotion: Sad Time t-1, t-2 Attributes: - Location: Lab - Activity: Working Learning Task: 18

19 Dynamic Continuous Factor Graph Model Time t Time t : Binary function 19

20 Learning with Factor Graphs y 5 y 4 y ' 3 y 3 y 2 y 1 Attribute Social Temporal 20

21 MH-based Learning algorithm [1] Yuan Zhang, Jie Tang, Jimeng Sun, Yiran Chen, and Jinghai Rao. MoodCast: Emotion Prediction via Dynamic Continuous 21 Factor Graph Model. In ICDM 10. pp

22 Still Challenges Q1: Are there any other social factor that may affect the prediction results? Q2: How to scale up the model to large networks? 22

23 Q1: Conformity Influence I love Obama Positive Negative Obama is fantastic 3. Group conformity Obama is great! 1. Peer influence 2. Individual [1] Jie Tang, Sen Wu, and Jimeng Sun. Confluence: Conformity Influence in Large Social Networks. In KDD 13,

24 Conformity Factors Individual conformity A specific action performed by user v at time t Peer conformity All actions by user v Group conformity 24

25 Q2: Distributed Learning Master Global update Slave Compute local gradient via random sampling Graph Partition by Metis Master-Slave Computing Inevitable loss of correlation factors! 25

26 Random Factor Graphs Slave: Distributedly compute Gradient via LBP Gradients Parameters Master: Optimize with Gradient Descent Master-Slave Computing 26

27 Model Inference Calculate marginal probability in each subgraph Aggregate the marginal probability and normalize 27

28 Theoretical Analysis Θ * : Optional parameter of the complete graph Θ: Optional parameter of the subgraphs P s,j : True marginal distributions on the complete graph G * s,j : True marginal distributions on subgraphs Let E s,j = log G * s,j log P s,j,we have: 28

29 29 Experiments

30 Twitter Results for Sentiment Analysis 1,414,340 users and 480,435,500 tweets 274,644,047 t-follow edges and edges Baseline SVM Vote Measures Accuracy and Macro F1 30

31 31 Performance

32 32 Results of Different Learning Algorithms

33 33

34 Data Set Baseline SVM Results for Emotion Analysis SVM with network features Naïve Bayes Naïve Bayes with network features Evaluation Measure: Precision, Recall, F1-Measure #Users Avg. Links #Labels Other MSN ,869 >36,000hr LiveJournal 469, ,665,166 34

35 35 Performance Result

36 Factor Contributions Mobile All factors are important for predicting user emotions 36

37 Online Applications: Emotion Analysis on Flickr 37

38 38

39 Ø Framework: Images -Aesthetic Effects -Emotions Ø Model: Factor Graphs for images in Social Networks [1] 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 Multimedia. pp [239 ] Grand Challenge 2nd Prize Award

40 App1: Emotion Distribution on Flickr Before Thanksgiving 2011 VS During Thanksgiving holiday 100,000 Images from Flickr Happy, Cheerful, and Peaceful 40

41 App2: Modify Images with Emotional Words More than 180 different effects Happy Summer? Natural Autumn? Original Image Clear Winter? 41

42 42 Summary

43 Summary Social networks bring revolutionary changes to the Web and unprecedented opportunities for us Emotion stimulates minds 3000 times faster than rational thoughts! Embedding social theories into sentiment/ emotion analysis can benefit many applications 43

44 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 , 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 (Selected as the Spotlight Paper) Yuan Zhang, Jie Tang, Jimeng Sun, Yiran Chen, and Jinghai Rao. MoodCast: Emotion Prediction via Dynamic Continuous Factor Graph Model. In ICDM 10. pp 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 , 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 (Grand Challenge 2nd Prize Award) 44

45 Thanks you! Collaborators: Lillian Lee, Chenhao Tan (Cornell) Ming Zhou, Long Jiang (Microsoft), Yuan Zhang (MIT) Jimeng Sun (IBM), Jinghai Rao (Nokia) Sen Wu, Jia Jia, Xiaohui Wang, Yiran Chen, Wenjing Yu (THU) Jie Tang, KEG, Tsinghua U, Download data & Codes,