Supporting Experts to Handle Tweet Collections About Significant Events
We introduce Relevancer that processes a tweet set and enables generating an automatic classifier from it. Relevancer satisfies information needs of experts during significant events. Enabling experts to combine automatic procedures with expertise is the main contribution of our approach and the added value of the tool. Even a small amount of feedback enables the tool to distinguish between relevant and irrelevant information effectively. Thus, Relevancer facilitates the quick understanding of and proper reaction to events presented on Twitter.
KeywordsSocial media Text mining Machine learning Twitter
COMMIT, Statistics Netherlands, and Floodtags supported our work.
- 2.Hürriyetoğlu, A., van den Bosch, A., Oostdijk, N.: Using relevancer to detect relevant tweets: the Nepal earthquake case. In: Working Notes of FIRE 2016 - Forum for Information Retrieval Evaluation, Kolkata, India. December, 2016. http://ceur-ws.org/Vol-1737/T2-6.pdf
- 3.Hürriyetoğlu, A., van den Bosch, J.W.A., Oostdijk, N.: Analysing the role of key term inflections in knowledge discovery on twitter. In: Proceedings of the 1st International Workshop on Knowledge Discovery on the WEB, Cagliari, Italy, September, 2016. http://www.iascgroup.it/kdweb2016-program/accepted-papers.html
- 5.Olteanu, A., Castillo, C., Diaz, F., Vieweg, S.: CrisisLex: A lexicon for collecting and filtering Microblogged communications in crises, pp. 376–385. The AAAI Press (2014)Google Scholar