Automatic Product Ontology Extraction from Textual Reviews

TL;DR

This paper introduces an automated method for extracting product ontologies from reviews, outperforming existing approaches and manual ontologies in accuracy, generalization, and practical recommendation tasks with minimal annotated data.

Contribution

The paper presents a novel automated ontology extraction technique from reviews that requires limited training data and surpasses existing methods and manual ontologies in multiple evaluations.

Findings

Outperforms WordNet, Text2Onto, and COMET in ontology quality.

Better generalization to unseen products.

Improves product recommendation accuracy.

Abstract

Ontologies have proven beneficial in different settings that make use of textual reviews. However, manually constructing ontologies is a laborious and time-consuming process in need of automation. We propose a novel methodology for automatically extracting ontologies, in the form of meronomies, from product reviews, using a very limited amount of hand-annotated training data. We show that the ontologies generated by our method outperform hand-crafted ontologies (WordNet) and ontologies extracted by existing methods (Text2Onto and COMET) in several, diverse settings. Specifically, our generated ontologies outperform the others when evaluated by human annotators as well as on an existing Q&A dataset from Amazon. Moreover, our method is better able to generalise, in capturing knowledge about unseen products. Finally, we consider a real-world setting, showing that our method is better able to determine recommended products based on their reviews, in alternative to using Amazon's standard score aggregations.