Predicting Contradiction Intensity: Low, Strong or Very Strong?

Abstract : Reviews on web resources (e.g. courses, movies) become increasingly exploited in text analysis tasks (e.g. opinion detection, controversy detection). 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 predictors of contradiction intensity. Also, J48 was the most effective learning approach for this type of classification.
Type de document :
Communication dans un congrès
41st st International ACM SIGIR Conference on Research and Development in Information Retrieval SIGIR2018, Jul 2018, Ann Arbor, Michigan, United States. 〈10.1145/3209978.3210098〉
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01796060
Contributeur : Ismail Badache <>
Soumis le : lundi 4 juin 2018 - 14:32:48
Dernière modification le : mercredi 13 mars 2019 - 16:03:31
Document(s) archivé(s) le : mercredi 5 septembre 2018 - 12:27:59

Fichier

2018_SIGIR_BADACHE.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Ismail Badache, Sébastien Fournier, Adrian-Gabriel Chifu. Predicting Contradiction Intensity: Low, Strong or Very Strong?. 41st st International ACM SIGIR Conference on Research and Development in Information Retrieval SIGIR2018, Jul 2018, Ann Arbor, Michigan, United States. 〈10.1145/3209978.3210098〉. 〈hal-01796060〉

Partager

Métriques

Consultations de la notice

121

Téléchargements de fichiers

133