Automatic Product Ontology Extraction from Textual Reviews
This work addresses the labor-intensive process of ontology creation for product reviews, offering an automated solution that enhances knowledge extraction and recommendation systems in e-commerce.
The authors tackled the problem of manually constructing product ontologies by proposing a novel method for automatic extraction from textual reviews, which outperformed hand-crafted and existing automated ontologies in human evaluations and on an Amazon Q&A dataset, with better generalization to unseen products and improved product recommendations.
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.