Exemplar-Based Topic Detection in Twitter Streams


  • Ahmed Elbagoury University of Waterloo
  • Rania Ibrahim University of Waterloo
  • Ahmed Farahat University of Waterloo
  • Mohamed Kamel University of Waterloo
  • Fakhri Karray University of Waterloo




Topic Detection, Exemplar-based Representation, Twitter Analytics


Detecting topics in Twitter streams has been gaining an increasing amount of attention. It can be of great support for communities struck by natural disasters, and could assist companies and political parties understand users' opinions and needs. Traditional approaches for topic detection focus on representing topics using terms, are negatively affected by length limitation and the lack of context associated with tweets.In this work, we propose an Exemplar-based approach for topic detection, in which detected topics are represented using a few selected tweets. Using exemplar tweets instead of a set of key words allows for an easy interpretation of the meaning of the detected topics. Experimental evaluation on benchmark Twitter datasets shows that the proposed topic detection approach achieves the best term precision. It does this while maintaining good topic recall and running time compared to other approaches.




How to Cite

Elbagoury, A., Ibrahim, R., Farahat, A., Kamel, M., & Karray, F. (2021). Exemplar-Based Topic Detection in Twitter Streams. Proceedings of the International AAAI Conference on Web and Social Media, 9(1), 610-613. https://doi.org/10.1609/icwsm.v9i1.14651