使用大语言模型对表演艺术领域在线回复进行情感分析。

Sentiment analysis of online responses in the performing arts with large language models.

作者信息

Seong Baekryun, Song Kyungwoo

机构信息

Department of Artificial Intelligence, University of Seoul, South Korea.

Department of Applied Statistics, Department of Statistics and Data Science, Yonsei University, South Korea.

出版信息

Heliyon. 2023 Nov 18;9(12):e22457. doi: 10.1016/j.heliyon.2023.e22457. eCollection 2023 Dec.

DOI:10.1016/j.heliyon.2023.e22457

PMID:38076147

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10709041/

Abstract

Opinion mining is a technique extracting and analyzing people's opinions from online communities, and sentiment analysis is a kind of opinion mining analyzing attitudes of people toward an object, whether positive, negative, or neutral. Sentiment analysis has evolved alongside natural language processing models and applied to targets such as movie reviews. However, the performing arts have not been subjected to sentiment analysis as movie reviews, despite the apparent need for it. In this study, we used the Korean Funnel Transformer language model to perform sentiment analysis on performing arts. This study looks at people's reactions to performing arts in online communities, not just whether they agree or disagree, and shows the problems with applying existing sentiment analysis to performing arts.

摘要

观点挖掘是一种从在线社区中提取和分析人们观点的技术，而情感分析是观点挖掘的一种，用于分析人们对某个对象的态度，无论是积极、消极还是中性的。情感分析随着自然语言处理模型的发展而发展，并应用于电影评论等目标。然而，尽管显然有必要对表演艺术进行情感分析，但表演艺术尚未像电影评论那样受到情感分析的关注。在本研究中，我们使用韩国漏斗变换器语言模型对表演艺术进行情感分析。本研究关注的是人们在在线社区中对表演艺术的反应，而不仅仅是他们是否同意，并且揭示了将现有情感分析应用于表演艺术时存在的问题。