Sentiment classification for stock news

Author

Gao, Yang ; Zhou, Li ; Zhang, Yong ; Xing, Chunxiao ; Sun, Yigang ; Zhu, Xianzhong

Author_Institution

Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China

fYear

2010

fDate

1-3 Dec. 2010

Firstpage

99

Lastpage

104

Abstract

Web news articles play an important role in stock market. Sentiment classification of news articles can help the investors make investment decisions more efficiently. In this paper, we implemented an approach of Chinese new words detection by using N-gram model and applied the result for Chinese word segmentation and sentiment classification. Appraisal theory was introduced into sentiment analysis and Naive Bayes, K-nearest Neighbor and Support Vector Machine were used as classification algorithms. Our method was used for a Chinese stock news data set. The best accuracy reaches 82.9% in all experiments. Additionally, we developed a prototype system to demonstrate our work.

Keywords

Bayes methods; classification; natural language processing; stock markets; support vector machines; text analysis; Chinese new word detection; Chinese word segmentation; N-gram model; Web news article; appraisal theory; k-nearest neighbor; naive Bayes method; sentiment classification; stock market; stock news; support vector machine; Chinese new word detection; N-gram model; Sentiment classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Pervasive Computing and Applications (ICPCA), 2010 5th International Conference on

Conference_Location

Maribor

Print_ISBN

978-1-4244-9144-5

Type

conf

DOI

10.1109/ICPCA.2010.5704082

Filename

5704082