Prédire l'intensité de contradiction dans les commentaires : faible, forte ou très forte ?

Abstract : This paper investigates contradiction intensity in reviews exploiting different features such as variation of ratings and variation of polarities around specific entities (e.g. aspects, topics). Firstly, aspects are identified according to the distributions of the emotional terms in the vicinity of the most frequent nouns in the reviews collection. Secondly, the polarity of each review segment containing an aspect is estimated. Only resources containing these aspects with opposite polarities are considered. Finally, some features are evaluated, using feature selection algorithms, to determine their impact on the effectiveness of contradiction intensity detection. The selected features are used to learn some state-of-the-art learning approaches. The experiments are conducted on the Massive Open Online Courses data set containing 2244 courses and their 73,873 reviews, collected from coursera.org. Results showed that variation of ratings, variation of polarities, and reviews quantity are the best pre-dictors of contradiction intensity. Also, J48 was the most effective learning approach for this type of classification.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01872267
Contributor : Ismail Badache <>
Submitted on : Tuesday, September 11, 2018 - 6:09:14 PM
Last modification on : Tuesday, April 16, 2019 - 1:41:21 AM
Document(s) archivé(s) le : Wednesday, December 12, 2018 - 3:59:37 PM

File

2019_AFIA_BADACHE.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01872267, version 1

Citation

Ismail Badache, Sébastien Fournier, Adrian-Gabriel Chifu. Prédire l'intensité de contradiction dans les commentaires : faible, forte ou très forte ?. Bulletin de l'Association Française pour l'Intelligence Artificielle, AFIA, A paraître. ⟨hal-01872267⟩

Share

Metrics

Record views

51

Files downloads

102