Latent Aspect Detection from Online Unsolicited Customer Reviews

TL;DR

This paper introduces an unsupervised approach using latent Dirichlet allocation to detect hidden aspects in customer reviews, improving upon existing methods that rely on surface form detection.

Contribution

It presents a novel unsupervised method for extracting latent aspects from reviews, addressing limitations of supervised approaches in identifying implicit features.

Findings

Outperforms existing methods on benchmark datasets

Effective in detecting latent aspects without surface form cues

Enhances review analysis accuracy for product and service insights

Abstract

Within the context of review analytics, aspects are the features of products and services at which customers target their opinions and sentiments. Aspect detection helps product owners and service providers to identify shortcomings and prioritize customers' needs, and hence, maintain revenues and mitigate customer churn. Existing methods focus on detecting the surface form of an aspect by training supervised learning methods that fall short when aspects are latent in reviews. In this paper, we propose an unsupervised method to extract latent occurrences of aspects. Specifically, we assume that a customer undergoes a two-stage hypothetical generative process when writing a review: (1) deciding on an aspect amongst the set of aspects available for the product or service, and (2) writing the opinion words that are more interrelated to the chosen aspect from the set of all words available in a language. We employ latent Dirichlet allocation to learn the latent aspects distributions for generating the reviews. Experimental results on benchmark datasets show that our proposed method is able to improve the state of the art when the aspects are latent with no surface form in reviews.