Position-based Contributive Embeddings for Aspect-Based Sentiment Analysis

TL;DR

This paper introduces Position-based Contributive Embeddings (PosCE), a novel method that emphasizes the influence of positional words on sentiment polarity in aspect-based sentiment analysis, improving accuracy.

Contribution

The paper proposes PosCE, a new embedding technique inspired by game theory, to better incorporate positional information in ABSA, enhancing model performance.

Findings

Improved accuracy and F1 scores on SemEval dataset

PosCE enhances aspect-based sentiment representation

Method effective for multimodal ABSA tasks

Abstract

Aspect-based sentiment analysis (ABSA), exploring sentiment polarity of aspect-given sentence, is a fine-grained task in the field of nature language processing. Previously researches typically tend to predict polarity based on the meaning of aspect and opinions. However, those approaches mainly focus on considering relations implicitly at the word level, ignore the historical impact of other positional words when the aspect appears in a certain position. Therefore, we propose a Position-based Contributive Embeddings (PosCE) to highlight the historical reference to special position aspect. Contribution of each positional words to the polarity is similar to the process of fairly distributing gains to several actors working in coalition (game theory). Therefore, we quote from the method of Shapley Value and finally gain PosCE to enhance the aspect-based representation for ABSA task. Furthermore, the PosCE can also be used for improving performances on multimodal ABSA task. Extensive experiments on both text and text-audio level using SemEval dataset show that the mainstream models advance performance in accuracy and F1 (increase 2.82% and 4.21% on average respectively) by applying our PosCE.