A Knowledge-Driven Approach to Classifying Object and Attribute Coreferences in Opinion Mining

TL;DR

This paper presents a method that automatically mines domain-specific knowledge from reviews and uses a neural model to improve coreference classification of objects and attributes in opinion mining, reducing manual effort.

Contribution

It introduces an automated knowledge mining approach combined with a neural classifier for coreference resolution in opinion reviews, avoiding manual knowledge base creation.

Findings

Effective on five real-world domains

Improves coreference classification accuracy

Leverages both domain-specific and commonsense knowledge

Abstract

Classifying and resolving coreferences of objects (e.g., product names) and attributes (e.g., product aspects) in opinionated reviews is crucial for improving the opinion mining performance. However, the task is challenging as one often needs to consider domain-specific knowledge (e.g., iPad is a tablet and has aspect resolution) to identify coreferences in opinionated reviews. Also, compiling a handcrafted and curated domain-specific knowledge base for each domain is very time consuming and arduous. This paper proposes an approach to automatically mine and leverage domain-specific knowledge for classifying objects and attribute coreferences. The approach extracts domain-specific knowledge from unlabeled review data and trains a knowledgeaware neural coreference classification model to leverage (useful) domain knowledge together with general commonsense knowledge for the task. Experimental evaluation on realworld datasets involving five domains (product types) shows the effectiveness of the approach.