USA: Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part of Speech Dataset

TL;DR

This paper introduces a large-scale universal sentiment analysis model that leverages mutual reinforcement between word and text sentiment, supported by newly annotated datasets, and outperforms GPT-3.5-turbo in multiple sentiment classification tasks.

Contribution

It presents a novel 7-billion parameter Universal Sentiment Analysis model and four new annotated datasets, demonstrating the effectiveness of mutual reinforcement effects in sentiment analysis.

Findings

The USA model surpasses GPT-3.5-turbo on all datasets.

Mutual reinforcement effect improves sentiment classification accuracy.

New datasets enhance sentiment and POS analysis capabilities.

Abstract

Sentiment analysis is a pivotal task in the domain of natural language processing. It encompasses both text-level sentiment polarity classification and word-level Part of Speech(POS) sentiment polarity determination. Such analysis challenges models to understand text holistically while also extracting nuanced information. With the rise of Large Language Models(LLMs), new avenues for sentiment analysis have opened. This paper proposes enhancing performance by leveraging the Mutual Reinforcement Effect(MRE) between individual words and the overall text. It delves into how word polarity influences the overarching sentiment of a passage. To support our research, we annotated four novel Sentiment Text Classification and Part of Speech(SCPOS) datasets, building upon existing sentiment classification datasets. Furthermore, we developed a Universal Sentiment Analysis(USA) model, with a 7-billion parameter size. Experimental results revealed that our model surpassed the performance of gpt-3.5-turbo across all four datasets, underscoring the significance of MRE in sentiment analysis.