A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification

TL;DR

This paper introduces MEAN, a deep learning model that enhances sentiment classification by integrating multiple sentiment linguistic resources through attention mechanisms, leading to improved accuracy.

Contribution

It presents a novel attention network that incorporates sentiment lexicons, negation, and intensity words to better capture sentiment nuances in text.

Findings

MEAN outperforms existing models on benchmark datasets.

Incorporating multiple sentiment resources improves classification accuracy.

The model effectively captures sentiment, negation, and intensity cues.

Abstract

Deep learning approaches for sentiment classification do not fully exploit sentiment linguistic knowledge. In this paper, we propose a Multi-sentiment-resource Enhanced Attention Network (MEAN) to alleviate the problem by integrating three kinds of sentiment linguistic knowledge (e.g., sentiment lexicon, negation words, intensity words) into the deep neural network via attention mechanisms. By using various types of sentiment resources, MEAN utilizes sentiment-relevant information from different representation subspaces, which makes it more effective to capture the overall semantics of the sentiment, negation and intensity words for sentiment prediction. The experimental results demonstrate that MEAN has robust superiority over strong competitors.