Abstract

Online product reviews are becoming common andare being used more frequently by consumers to choose themost competitive products. Negation detection is a crucial stepfor information extraction from product review texts, becausenegation can change the meaning of opinions given by consumersabout products or services. Although several approaches havebeen proposed for negation detection in product reviews, mostof these proposals have focused only on the English language.In this paper, we propose a deep learning-based proposal fornegation detection for reviews written in the Spanish language.This proposal takes advantage of transfer learning and uses a BERT-based model to perform negation detection. Performedtests using the SFU corpus for Spanish, showed an F1 score of 95.4% in the cue detection task and 91.5% in the scope resolutiontask. Our finding suggests that our BERT-based approach isfeasible to perform negation detection in Spanish.