Using Aspect Extraction Approaches to Generate Review Summaries and User Profiles

TL;DR

This paper evaluates a neural model for aspect extraction from reviews, demonstrating its effectiveness in generating review summaries and user profiles, with implications for personalized review analysis.

Contribution

It introduces and assesses a neural aspect extraction model for summarizing reviews and profiling users, showing its practical utility in real-world review analysis.

Findings

Neural model performs well in extracting aspect sentences judged by humans.

Aspect-based user profiles effectively capture user preferences.

Divergent users produce significantly different review rankings.

Abstract

Reviews of products or services on Internet marketplace websites contain a rich amount of information. Users often wish to survey reviews or review snippets from the perspective of a certain aspect, which has resulted in a large body of work on aspect identification and extraction from such corpora. In this work, we evaluate a newly-proposed neural model for aspect extraction on two practical tasks. The first is to extract canonical sentences of various aspects from reviews, and is judged by human evaluators against alternatives. A $k$-means baseline does remarkably well in this setting. The second experiment focuses on the suitability of the recovered aspect distributions to represent users by the reviews they have written. Through a set of review reranking experiments, we find that aspect-based profiles can largely capture notions of user preferences, by showing that divergent users generate markedly different review rankings.