![Rumour Detection Continued.
AI approach based on Key phrases
Rumors are basically judge on the key phrases it has –
“Is this true?”
“Really?”
“What?
The paper proposes algorithm for identifying newly emerging,
controversial topics that is scalable to massive stream of posts i.e. signal
posts.
Then it identifies a set of regular expressions that define the set of signal
posts. For Example: is (that | this | it) true? , wh[a]*t[?!][?1]*](https://image.slidesharecdn.com/rumourdetection-190127144933/85/Rumour-detection-7-320.jpg)
Rumour detection
- 1. Rumour Detection: Case Study on Facebook By: Lokesh Kumar IT4 11510565 NIT, Kurukshetra
- 2. Content What is Rumour? How it can spread? Problem Overview Rumour Detection Related work Case study on facebook rumours Conclusion References
- 3. What is Rumour? Rumours are Controversial and fact checkable statement. Rumours are powerful, pervasive and persistent force that affects people and group. Rumour is a statement that is unverified at the time of circulation and either unverified or verified to be false after some time.
- 4. How It can spread? Rumours or fake news spread much more quickly and more wider than the real news on an online platform. Rumours got more reviews, likes and comments than those with accurate content. Viewers have limited attention and are saturated with content choices, it often appears as though fake information is more appealing or engaging to viewers. This problem is getting worse by 2022, People in developed economic could be encountering more fake news than real information.
- 5. Problem overview The large use of Online Social Networking has provided fertile soil for the émergence and fast spread of rumors. It is difficult to determine all of the messages or posts on social media are truthful. Every 60 seconds on Facebook: 510,000 comments are posted, 293,000 statuses are updated, and 136,000 photos are uploaded.
- 6. Rumour Detection Human intelligence is the real key • The best way to combat the spread of fake news may be to depend on people. • When someone sees an enraging post, that person would do better to investigate the information, rather than sharing it immediately. • The act of sharing also lends credibility to a post: When other people see it, they register that it was shared by someone they know and presumably trust at least a bit, and are less likely to notice whether the original source is questionable.
- 7. Rumour Detection Continued. AI approach based on Key phrases Rumors are basically judge on the key phrases it has – “Is this true?” “Really?” “What? The paper proposes algorithm for identifying newly emerging, controversial topics that is scalable to massive stream of posts i.e. signal posts. Then it identifies a set of regular expressions that define the set of signal posts. For Example: is (that | this | it) true? , wh[a]*t[?!][?1]*
- 8. Related Work Tracking rumors on Facebook requires two types of information: a corpus of known rumors, and a sample of reshare cascades circulating on Facebook which can be matched to the corpus. The website Snopes.com has diligently documented thousands of rumors, and provides the starting point for our analysis. To match known rumors to this anonymised set of reshare cascades, we identify uploads and reshares that have been snoped — someone linked to a Snopes.com article in a comment. Those comments are posted by people to either warn their friends that something they posted is inaccurate or to the contrary, to validate that a rumor, though hard to believe, is in fact true.
- 9. Related Work They gathered 250K comments, posted during July and August 2013 on 17K individual cascades, containing 62 million shares. One large cascade shows a rumor diffusing as reshares prompt more reshares, forming long chains:
- 10. Related work The cascade above was frequently snoped, as can be seen from the lower-right branch with the reshares being snoped highlighted in red.
- 11. Related work Although false rumors are predominant (62% of cascades have been tagged by Snopes as false), we observe that true rumors are more viral, in the sense that they result in larger cascades, achieving on average 163 shares per upload, whereas false rumors only have an average of 108 shares per upload.¹ if the rumor is false, there is a greater likelihood that they will delete the reshare (they are 4.4 times more likely to delete it). However, they are also more likely to retract the share even if the rumor is true or partly true, potentially because they realize that the story is old.
- 12. Rumours on Facebook CASE 1: UNESCO declared India's national anthem, 'Jana Gana Mana,' to be the world's best. In March 2016, a message claiming that UNESCO had named India’s “Jana Gana Mana” as the best anthem in the world began circulating on Facebook. Why it spread out ?? Lack of knowledge & Information Keen to share before others do Too much patriotic(emotions)
- 13. Rumours on facebook CASE 2: Social media(Facebook) rumours lead to mob lynching of two men in India The two had gone to a picnic spot in the area to visit a waterfall and were attacked on their return by a mob who accused them of being child abductors in June 2018. According to local accounts, the people responsible for killing the two men not only filmed one of them begging for mercy, but also posted the videos on Facebook in addition to claiming responsibility for the murders. Rumours of children being kidnapped and killed, allegedly for their body parts, spread over Facebook and WhatsApp, have recently gathered momentum across India resulting in at least six people being killed by vigilante mobs in as many weeks.
- 14. Conclusion It is clear that online social platform are the fastest place to spread rumour much wider. The main reasons for spreading these rumours is lack of information, being too much social etc. These rumours scatter a lot of fake information over internet. These rumours can be deadly for person’s life. To overcome these problem, there is need of improving the knowledge of users and tools to verify these rumours.
- 15. References: https://theconversation.com/how-artificial-intelligence-can-detect-and-create- fake-news-95404 https://www.irishtimes.com/news/world/asia-pacific/social-media-rumours-lead- to-mob-lynching-of-two-men-in-india-1.3527063 https://www.snopes.com/fact-check/unesco-india-national-anthem/ https://www.fastcompany.com/40566786/heres-how-facebook-uses-ai-to-detect- many-kinds-of-bad-content https://www.facebook.com/notes/facebook-data-science/the-strange-truth-about- fiction/10152215561458859 Thank You !!!