Classification or clustering algorithms and how to apply them to existing big data from social networks can help in this. Precise methods and work processes are desired.
Here is some literature. If I had to design an algorithm, I'd assemble timelines of the occurrences of rather rare words or phrases, and determine who started them. For example, if a person is influential and writes 'frog', other members will likely pick the word and discuss about frogs for a while.
https://techxplore.com/news/2020-06-deep-framework-key-players-complex.html
https://www.technologyreview.com/2010/09/03/200577/how-to-tell-who-is-influencing-whom-in-a-group-discussion/
https://www.stern.nyu.edu/experience-stern/news-events/measure-social-networks
https://www.eurekalert.org/news-releases/549282
https://aclanthology.org/N06-1027.pdf
Article Identification of influential spreaders in complex networks
https://www.cmu.edu/joss/content/articles/volume8/Welser/
https://www.technologyreview.com/2012/11/28/181428/good-samaritan-index-identifies-web-users-who-help-others-most/
https://www.forbes.com/sites/kashmirhill/2012/07/20/using-twitter-to-help-expose-psychopaths/
Regards,
Joachim
- Badges
- Science topic