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.

Machine Leaning & Social Media

394 views

Published on

Cover Social media for visually challenged, fake news / mis information, slefie deaths, killfie, telephone scams, gab, code mixed content, stance prediction, hate speech, identity resolution,

Published in: Engineering
  • Be the first to comment

Machine Leaning & Social Media

  1. 1. ML & Social Media 4th Summer School on Machine Learning July 13, 2019 Ponnurangam Kumaraguru (“PK”) IIIT Delhi TEDx & ACM Distinguished Speaker Linkedin/in/ponguru/ fb/ponnurangam.kumaraguru @ponguru
  2. 2. 2
  3. 3. Keywords you got to know in last 120hrs? 3
  4. 4. 4
  5. 5. Top sites Alexa… 5
  6. 6. 6
  7. 7. 7
  8. 8. 8
  9. 9. 9 2009
  10. 10. 10
  11. 11. 11
  12. 12. 12
  13. 13. Non-trustworthy Content FAKE 13 $ RUMORS
  14. 14. Methodology 14
  15. 15. Credibility Modeling 15 Feature set Features (45) Tweet meta-data Number of seconds since the tweet; Source of tweet (mobile / web/ etc); Tweet contains geo-coordinates Tweet content (simple) Number of characters; Number of words; Number of URLs; Number of hashtags; Number of unique characters; Presence of stock symbol; Presence of happy smiley; Presence of sad smiley; Tweet contains `via'; Presence of colon symbol Tweet content (linguistic) Presence of swear words; Presence of negative emotion words; Presence of positive emotion words; Presence of pronouns; Mention of self words in tweet (I; my; mine) Tweet author Number of followers; friends; time since the user if on Twitter; etc. Tweet network Number of retweets; Number of mentions; Tweet is a reply; Tweet is a retweet Tweet links WOT score for the URL; Ratio of likes / dislikes for a YouTube video
  16. 16. Implementation
  17. 17. Feedback by Users 17
  18. 18. Harvard (1839) – Harvard – Harvard – Harvard – MIT – Northwestern – UIUC – WUSL – CMU (2009) – IIITD (2015) 18
  19. 19. Different methods – #Hashtag level – Tweet level – SVM – Decision tree – Sentiment analysis – Text CNN – LSTM – Autoencoders – Language models – Knowledge Graph – Multimodal – GROVER 19 https://grover.allenai.org/
  20. 20. Different in Facebook… 20
  21. 21. Facebook Inspector 21
  22. 22. Harvard (1839) – Harvard – Harvard – Harvard – MIT – Northwestern – UIUC – WUSL – CMU (2009) – IIITD (Nov 14, 2017) 22
  23. 23. Harvard (1839) – Harvard – Harvard – Harvard – MIT – Northwestern – UIUC – WUSL – CMU (2009) – IIITD (April 25, 2019) 23
  24. 24. Pittsburgh Shooting / Gab post 24
  25. 25. Hate speech 25
  26. 26. Code mixed content 26
  27. 27. Code mixed content 27
  28. 28. Stance prediction 28
  29. 29. De-duplicating audience Social audience = 437,632 + 153,000 + 805,097 or less?? 29
  30. 30. 30
  31. 31. 31
  32. 32. Heuristic Identity Search 32 cerc.iiitd.ac.in Profile Content Self-mention Network Syntactic and Image Search Linking If self-identified / returned by more than one search method No Yes Candidate Identities name, location, username mobile no, post, friends, followers Paridhi Jain, Ponnurangam Kumaraguru, and Anupam Joshi. 2013. @I seek ‘fb.me’: Identifying Users across Multiple Online Social Networks. In Proceedings of the 22nd International Conference on World Wide Web, WWW ’13 Companion. ACM, New York, NY, USA, 1259- 1268. DOI=http://dx.doi.org/10.1145/2487788.2488160 [Honorable Mention Award}
  33. 33. Harvard (1839) – Harvard – Harvard – Harvard – MIT – Northwestern – UIUC – WUSL – CMU (2009) – IIITD (2016) 33
  34. 34. WTF / Recommendations…. 34
  35. 35. YouTube Recommendations…. 35
  36. 36. To understand users / customers – “Show me who your friends are and I’ll tell you who you are?” 36
  37. 37. To understand users / customers – “Show me who your friends are and I’ll tell you who you are?” 37
  38. 38. To understand users / customers – “Show me who your friends are and I’ll tell you who you are?” 38
  39. 39. To understand users / customers – Interest graph 39
  40. 40. 40 Selfies vs Potential KillFies
  41. 41. 41 Selfies vs Potential KillFies
  42. 42. 42
  43. 43. 439th International Workshop on Modeling Social Media (MSM), 2018 @ WWW
  44. 44. 44
  45. 45. 45 http://bit.ly/saftie-cam
  46. 46. Sample 46
  47. 47. Takeaways – Social Media is a powerful tool – Business / Government can use the analysis to their benefits – You should use it for your benefits J -You tried doing analysis on your accounts? – Lots of challenges and opportunities! – Will be happy to interact more, if needed 47
  48. 48. 48 pk@iiitd.ac.in http://precog.iiitd.edu.in/ https://www.instagram.com/pkatiiitd/ https://fb.com/ponnurangam.kumaraguru @ponguru Linkedin/in/ponguru/

×