http://www.springerlink.com/content/l722138386t42nn4/
Good News or Bad News? Let the Market Decide
Moshe Koppel, Itai Shtrimberg
書籍シリーズ The Information Retrieval Series ISSN 1387-5264 巻 Volume 20 書籍 Computing Attitude and Affect in Text: Theory and Applications 出版社 Springer Netherlands DOI 10.1007/1-4020-4102-0 著作権 2006 ISBN 978-1-4020-4026-9 (Print) 978-1-4020-4102-0 (Online) DOI 10.1007/1-4020-4102-0_22 ページ 297-301
A simple and novel method for generating labeled examples for sentiment analysis is introduced: news stories about publicly traded companies are labeled positive or negative according to price changes of the company stock. It is shown that there are many lexical markers for bad news but none for good news. Overall, learned models based on lexical features can distinguish good news from bad news with accuracy of about 70%. Unfortunately, this result does not yield profits since it works only when stories are labeled according to cotemporaneous price changes but does not work when they are labeled according to subsequent price changes.
Keywords sentiment analysis - financial analysis - automated labelling