RESEARCH AND DEVELOPMENT IN INTELLIGENT SYSTEMS XXV 307-320 2009年 [査読有り]
We propose a method of assigning polarity to causal information extracted from Japanese financial articles concerning business performance of companies. Our method assigns polarity (positive or negative) according to business performance to causal...
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E91D(4) 986-989 2008年4月 [査読有り]
We propose a method of informative DOM* subtree identification from a Web page in an unfamiliar Web site. Our method uses layout data of DOM nodes generated by a generic Web browser. The results show that our method outperforms a baseline method, ...
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E91D(4) 959-968 2008年4月 [査読有り]
We propose a method of extracting cause information from Japanese financial articles concerning business performance. Our method acquires cause information, e.g. (zidousya no uriage ga koutyou: Sales of cars were good)". Cause information is usefu...
ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PROCEEDINGS 5012 977-984 2008年 [査読有り]
This paper proposes a method to automatically extract basis expressions that indicate economic trends from newspaper articles by using a statistical method. We also propose a method to classify them into positive expressions that indicate upbeat, ...
he 6th International Workshop on Web Services and Social Media In conjunction with The 20th International Conference on Network-Based Information Systems 2017年8月