Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis

TL;DR

This paper introduces a joint model combining recursive neural networks and conditional random fields to improve the extraction of aspect and opinion terms in aspect-based sentiment analysis, outperforming previous methods.

Contribution

The paper presents a novel unified framework that learns discriminative features and propagates information between aspect and opinion terms, enhancing extraction accuracy.

Findings

Outperforms baseline methods on SemEval 2014 dataset

Effectively incorporates hand-crafted features for better performance

Achieves superior results compared to challenge-winning systems

Abstract

In aspect-based sentiment analysis, extracting aspect terms along with the opinions being expressed from user-generated content is one of the most important subtasks. Previous studies have shown that exploiting connections between aspect and opinion terms is promising for this task. In this paper, we propose a novel joint model that integrates recursive neural networks and conditional random fields into a unified framework for explicit aspect and opinion terms co-extraction. The proposed model learns high-level discriminative features and double propagate information between aspect and opinion terms, simultaneously. Moreover, it is flexible to incorporate hand-crafted features into the proposed model to further boost its information extraction performance. Experimental results on the SemEval Challenge 2014 dataset show the superiority of our proposed model over several baseline methods as well as the winning systems of the challenge.