Developing a Component Comment Extractor from Product Reviews on E-Commerce Sites

TL;DR

This paper presents a BERT-based system that extracts component and aspect comments from product reviews, using pattern matching and data augmentation to improve accuracy on e-commerce review data.

Contribution

The study introduces a novel BERT-based classification approach with a WordNet data augmentation method for extracting product component comments from reviews.

Findings

Achieved over 88% coverage of component and aspect indicators.

Improved F1-score from 0.66 to 0.76 with data augmentation.

Effective extraction of component comments from e-commerce reviews.

Abstract

Consumers often read product reviews to inform their buying decision, as some consumers want to know a specific component of a product. However, because typical sentences on product reviews contain various details, users must identify sentences about components they want to know amongst the many reviews. Therefore, we aimed to develop a system that identifies and collects component and aspect information of products in sentences. Our BERT-based classifiers assign labels referring to components and aspects to sentences in reviews and extract sentences with comments on specific components and aspects. We determined proper labels based for the words identified through pattern matching from product reviews to create the training data. Because we could not use the words as labels, we carefully created labels covering the meanings of the words. However, the training data was imbalanced on component and aspect pairs. We introduced a data augmentation method using WordNet to reduce the bias. Our evaluation demonstrates that the system can determine labels for road bikes using pattern matching, covering more than 88\% of the indicators of components and aspects on e-commerce sites. Moreover, our data augmentation method can improve the-F1-measure on insufficient data from 0.66 to 0.76.