Measuring the Effect of Discourse Structure on Sentiment Analysis - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Measuring the Effect of Discourse Structure on Sentiment Analysis

Abstract

The aim of this paper is twofold: measuring the effect of discourse structure when assessing the overall opinion of a document and analyzing to what extent these effects depend on the corpus genre. Using Segmented Discourse Representation Theory as our formal framework, we propose several strategies to compute the overall rating. Our results show that discourse-based strategies lead to better scores in terms of accuracy and Pearson’s correlation than state-of-the-art approaches.
Fichier principal
Vignette du fichier
chardon_12686.pdf (171.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01229070 , version 1 (16-11-2015)

Identifiers

  • HAL Id : hal-01229070 , version 1
  • OATAO : 12686

Cite

Baptiste Chardon, Farah Benamara, Yannick Mathieu, Vladimir Popescu, Nicholas Asher. Measuring the Effect of Discourse Structure on Sentiment Analysis. 14th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2013), Mar 2013, Samos, Greece. pp. 25-37. ⟨hal-01229070⟩
90 View
523 Download

Share

Gmail Facebook Twitter LinkedIn More