$\rho$-hot Lexicon Embedding-based Two-level LSTM for Sentiment Analysis

TL;DR

This paper introduces a novel $ ho$-hot encoding and a two-level LSTM model for sentiment analysis, effectively handling complex sentiment representations and subjective annotations, especially in Chinese text datasets.

Contribution

It proposes a new $ ho$-hot encoding strategy and a two-level LSTM architecture to improve sentiment classification, addressing challenges in label quality and complex sentiment features.

Findings

Outperforms state-of-the-art algorithms on Chinese datasets

Effective incorporation of lexical cues via $ ho$-hot encoding

Addresses subjective labeling challenges in sentiment analysis

Abstract

Sentiment analysis is a key component in various text mining applications. Numerous sentiment classification techniques, including conventional and deep learning-based methods, have been proposed in the literature. In most existing methods, a high-quality training set is assumed to be given. Nevertheless, constructing a high-quality training set that consists of highly accurate labels is challenging in real applications. This difficulty stems from the fact that text samples usually contain complex sentiment representations, and their annotation is subjective. We address this challenge in this study by leveraging a new labeling strategy and utilizing a two-level long short-term memory network to construct a sentiment classifier. Lexical cues are useful for sentiment analysis, and they have been utilized in conventional studies. For example, polar and privative words play important roles in sentiment analysis. A new encoding strategy, that is, $\rho$-hot encoding, is proposed to alleviate the drawbacks of one-hot encoding and thus effectively incorporate useful lexical cues. We compile three Chinese data sets on the basis of our label strategy and proposed methodology. Experiments on the three data sets demonstrate that the proposed method outperforms state-of-the-art algorithms.