Salas-Zárate, María Del Pilar, López-López, Estanislao, Valencia-Garcia, Rafael, Aussenac-Gilles, Nathalie, Almela, Ángela and Alor-Hernández, Giner (2014) A study on LIWC categories for opinion mining in Spanish reviews. Journal of Information Science, 40 (6). pp. 1-13.

[thumbnail of assistant_3105901_575374099_0.pdf]
Preview
Text
Download (291kB) | Preview

Abstract

With the exponential growth of social media i.e. blogs and social networks, organizations and individual persons are increasingly using the number of reviews of these media for decision making about a product or service. Opinion mining detects whether the emotion of an opinion expressed by a user on Web platforms in natural language, is positive or negative. This paper presents extensive experiments to study the effectiveness of the classification of Spanish opinions in five categories: highly positive, highly negative, positive, negative and neutral, using the combination of the psychological and linguistic features of LIWC. LIWC is a text analysis software that enables the extraction of different psychological and linguistic features from natural language text. For this study, two corpora have been used, one about movies and one about technological products. Furthermore, we have conducted a comparative assessment of the performance of various classification techniques: J48, SMO and BayesNet, using precision, recall and F-measure metrics. All in all, findings have revealed that the positive and negative categories provide better results than the other categories. Finally, experiments on both corpora indicated that SMO produces better results than BayesNet and J48 algorithms obtaining an F-measure of 90.4% and 87.2% in each domain.

Item Type: Article
Language: English
Date: 2014
Refereed: Yes
Uncontrolled Keywords: Sentiment Analysis - Opinion Mining - Natural Language Processing With LIWC - Machine Learning
Subjects: H- INFORMATIQUE
Divisions: Institut de Recherche en Informatique de Toulouse
Site: UT1
Date Deposited: 24 Apr 2019 09:50
Last Modified: 02 Apr 2021 15:59
URI: https://publications.ut-capitole.fr/id/eprint/29715
View Item

Downloads

Downloads per month over past year