中文情感語意分析套件CSentiPackage發展與應用

Abstract

近年來，意見與情感分析技術漸漸為大家所注意且因網路環境之餘意見發表的便利性，文本意見與情感分析技術的需求與應用也快速增加，然而在中文上，並沒有公開可利用的意見與情感分析工具。本文介紹一個供研究使用免費且公開的中文情感語意分析套件：CSentiPackage，套件中包含多個可以用於中文情感語意分析研究所需要的各式工具，例如中文意見、構詞詞典、中文意見樹庫、意見挖掘計分工具，及深度社群立場分析模型等。本文將詳細介紹各個工具的內容。欲取得CSentiPackage套件及其使用方法，可從網址http://www.lunweiku.com/ 之Lab Homepage分頁進入申請下載。

Sentiment analysis determines the polarities and strength of the sentiment‐bearing expressions, and it has been an important and attractive research area. In the past decade, resources and tools have been developed for sentiment analysis in order to provide subsequent vital applications, such as product reviews, reputation management, call center robots, automatic public survey, etc. However, most of these resources are for the English language. Being the key to the understanding of business and government issues, sentiment analysis resources and tools are required for other major languages, e.g., Chinese. To over come this obstacle, we introduce CSentiPackage, where resources for retrieving sentiment from texts in the Chinese language, are provided. The related sentiment analysis technologies and datasets are described to give the readers the opportunities to use resources and tools to process Chinese sentiment texts from the very basic to the advanced, i.e., applying sentiment dictionaries, obtaining sentiment scores, and analyzing stance of social media posts using the deep learning model. The introduced resources and tools in this paper include NTUSD, ANTUSD, the Chinese Morphological Dataset, the Chinese Opinion Treebank, CopeOpi, and UTCNN. These resources are all available at http://academiasinicanlplab.github.io/ and they are free for the research purpose.