Aspect-based sentiment analysis: natural language understanding for implicit review

Abstract

The different types of implicit reviews should be well understood so that the developed extraction technique can solve all problems in implicit reviews and produce precise terms of aspects and opinions. We propose an aspect-based sentiment analysis (ABSA) method with natural language understanding for implicit reviews based on sentence and word structure. We built a text extraction method using a machine learning algorithm rule with a deep understanding of different types of sentences and words. Furthermore, the aspect category of each review is determined by measuring the word similarity between the aspect terms contained in each review and aspect keywords extracted from Wikipedia. Bidirectional encoder representations from transformers (BERT) embedding and semantic similarity are used to measure the word similarity value. Moreover, the proposed ABSA method uses BERT, a hybrid lexicon, and manual weighting of opinion terms. The purpose of the hybrid lexicon and the manual weighting of opinion terms is to update the existing lexicon and solve the problem of weighting words and phrases of opinion terms. The evaluation results were very good, with average F1-scores of 93.84% for aspect categorization and 92.42% for ABSA.