Detecting a Tweet’s Topic within a Large Number of Portuguese Twitter Trends

Authors Hugo Rosa, João Paulo Carvalho, Fernando Batista

Thumbnail PDF


  • Filesize: 0.48 MB
  • 15 pages

Document Identifiers

Author Details

Hugo Rosa
João Paulo Carvalho
Fernando Batista

Cite AsGet BibTex

Hugo Rosa, João Paulo Carvalho, and Fernando Batista. Detecting a Tweet’s Topic within a Large Number of Portuguese Twitter Trends. In 3rd Symposium on Languages, Applications and Technologies. Open Access Series in Informatics (OASIcs), Volume 38, pp. 185-199, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2014)


In this paper we propose to approach the subject of Twitter Topic Detection when in the presence of a large number of trending topics. We use a new technique, called Twitter Topic Fuzzy Fingerprints, and compare it with two popular text classification techniques, Support Vector Machines (SVM) and k-Nearest Neighbours (kNN). Preliminary results show that it outperforms the other two techniques, while still being much faster, which is an essential feature when processing large volumes of streaming data. We focused on a data set of Portuguese language tweets and the respective top trends as indicated by Twitter.
  • topic detection
  • social networks data mining
  • Twitter
  • Portuguese language


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail