Aspect and Opinion Terms Extraction Using Double Embeddings and Attention Mechanism for Indonesian Hotel Reviews

TL;DR

This paper presents a novel approach for extracting aspect and opinion terms from Indonesian hotel reviews using double embeddings and attention mechanisms, achieving high accuracy and outperforming previous systems.

Contribution

It introduces a new method combining double embeddings and attention for aspect and opinion term extraction in Indonesian reviews, surpassing prior state-of-the-art results.

Findings

Achieved F1-score of 0.914 for aspect terms

Achieved F1-score of 0.90 for opinion terms

Demonstrated the effectiveness of double embeddings and attention mechanisms

Abstract

Aspect and opinion terms extraction from review texts is one of the key tasks in aspect-based sentiment analysis. In order to extract aspect and opinion terms for Indonesian hotel reviews, we adapt double embeddings feature and attention mechanism that outperform the best system at SemEval 2015 and 2016. We conduct experiments using 4000 reviews to find the best configuration and show the influences of double embeddings and attention mechanism toward model performance. Using 1000 reviews for evaluation, we achieved F1-measure of 0.914 and 0.90 for aspect and opinion terms extraction in token and entity (term) level respectively.