Content and style features for automatic detection of users’ intentions in tweets

Helena Gómez-Adorno, David Pinto, Manuel Montes, Grigori Sidorov, Rodrigo Alfaro

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

The aim of this paper is to evaluate the use of content and style features in automatic classification of intentions of Tweets. For this we propose different style features and evaluate them using a machine learning approach. We found that although the style features by themselves are useful for the identification of the intentions of tweets, it is better to combine such features with the content ones. We present a set of experiments, where we achieved a 9.46 % of improvement on the overall performance of the classification with the combination of content and style features as compared with the content features.

Keywords

  • Detection of intention
  • Short texts
  • Text classification
  • Twitter

Fingerprint

Dive into the research topics of 'Content and style features for automatic detection of users’ intentions in tweets'. Together they form a unique fingerprint.

Cite this