Detecting speculations, contrasts and conditionals in consumer reviews

Maria Skeppstedt, Teri Schamp-Bjerede, Magnus Sahlgren, Carita Paradis, Andreas Kerren

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

5 Citations (SciVal)

Abstract

A support vector classifier was compared to a lexicon-based approach for the task of detecting the stance categories speculation, contrast and conditional in English consumer reviews. Around 3,000 training instances were required to achieve a stable performance of an F-score of 90 for speculation. This outperformed the lexicon-based approach, for which an Fscore of just above 80 was achieved. The machine learning results for the other two categories showed a lower average (an approximate F-score of 60 for contrast and 70 for conditional), as well as a larger variance, and were only slightly better than lexicon matching. Therefore, while machine learning was successful for detecting speculation, a well-curated lexicon might be a more suitable approach for detecting contrast and conditional.
Original languageEnglish
Title of host publication6th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, WASSA 2015 : Workshop proceedings
EditorsBalahur Alexandra, van der Goot Erik, Vossen Piek, Montoyo Andrés
PublisherAssociation for Computational Linguistics
Pages162-168
Number of pages7
ISBN (Print)978-1-941643-32-7
Publication statusPublished - 2015
Event6th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA '15) - Lisbon
Duration: 2015 Sep 17 → …

Conference

Conference6th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA '15)
Period2015/09/17 → …

Subject classification (UKÄ)

  • Languages and Literature
  • Computer Science

Keywords

  • consumer reviews
  • support vector classifier
  • stance

Fingerprint

Dive into the research topics of 'Detecting speculations, contrasts and conditionals in consumer reviews'. Together they form a unique fingerprint.

Cite this