1 / 29

Stemming the spread of rumors in a social network

Stemming the spread of rumors in a social network. SocioElite. Akshay Kumar | IIT Kanpur Khushi Gupta | IIT Guwahati Shubham Gupta | IIT Kanpur Balaji Vasan Srinivasan | Adobe Research. Social Media - Lots of upsides!. Provides an excellent platform to share information.

roth-pittman
Télécharger la présentation

Stemming the spread of rumors in a social network

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Stemming the spread of rumors in a social network SocioElite Akshay Kumar | IIT Kanpur Khushi Gupta | IIT Guwahati Shubham Gupta | IIT Kanpur Balaji Vasan Srinivasan | Adobe Research

  2. Social Media - Lots of upsides!

  3. Provides an excellent platform to share information

  4. Not all information is positive or reliable

  5. What if ? • The Egyptian Government had a mechanism to limit the spread of the anti-campaign • Could the revolution have been avoided? • Nestle had a way to nullify GreenPeace’s campaign • Could Nestle have saved it’s reputation?

  6. Problem Statement Given a rumor/negative campaign in a social network, identify nodes critical to its flow and design a mechanism to control the spread. Objectives:

  7. Proposed Approach Part 2: Campaign source and spread estimation Part 1: Diffusion modeling Part 3: Seeding and targeting positive campaigns

  8. Demo

  9. Proposed Approach Part 2: Campaign source and spread estimation Part 1: Diffusion modeling Part 3: Seeding and targeting positive campaigns

  10. Proposed Approach Part 2: Campaign source and spread estimation Part 1: Diffusion modeling Part 3: Seeding and targeting positive campaigns

  11. Data Set • Twitter data (from MMI Social Media) • 571 nodes • For each node: • Extract interests based on the tweets • Edge-weight • Reflects the interest overlap – based on topic models

  12. Proposed Approach Part 2: Campaign source and spread estimation Part 1: Diffusion modeling Part 3: Seeding and targeting positive campaigns

  13. Campaign Source Estimation: Monitor Nodes Positive Monitors Negative Monitors

  14. Source Identification : Approach 1

  15. Experiment 1: Error in Information Source Detection

  16. Source Identification : Approach 2

  17. Proposed Approach Part 2: Campaign source and spread estimation Part 1: Diffusion modeling Part 3: Seeding and targeting positive campaigns

  18. Measuring “Susceptibility” Not Infected Vulnerable Infected and dead

  19. Susceptibility Score: Approach 1

  20. Susceptibility Score: Approach 2 A B w pgB pgA A1 B1 w pgA pgB A2 B2

  21. Results and analysis

  22. Experiment1: Percentage Susceptible Nodes Saved

  23. Experiment2: Percentage Infections Avoided

  24. Papers and IDs

  25. Internship is not all about work!

  26. We were travelling…

  27. We were dancing and partying…

  28. Amidst all these, there was some time for serious work!?!?

More Related