Affiliations: Department of Information and Communication Engineering, University of Tokyo, 7-3-1 Hongo, Bunkyu-ku, Tokyo 113-8656, Japan | Digital Contents and Media Sciences Research Division, National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda Ku, Tokyo 101-8430, Japan
Abstract: News is an interesting application domain for “emotion sensing”, since readers often have a personal attitude or subjective opinion regarding certain events or entities reported about. Hence the ability to determine user-centric emotion on a given topic or entity is of critical interest. This paper describes a system called Emotion Sensitive News Agent (ESNA). By employing several RSS news feeds chosen by the user, ESNA has been developed as a news aggregator to fetch news, and to categorize the themes of the collected news into eight emotional affinities, thereby taking into consideration of the user's preference profile. A user study has been conducted, which indicates that the system is conceived as intelligent and interesting as an affective interface. ESNA exemplifies a recent research agenda that aims at recognizing affective information conveyed through texts. Different approaches have already been employed to “sense” emotion from text. The novelty of the approach mentioned here is threefold: affective information conveyed through text is analyzed (1) by using a rule based approach to assign a numerical valence (i.e., a positive or negative value to indicate positive or negative sentiment of the input) instead of a machine learning approach, (2) by considering the cognitive and appraisal structure of emotions, and (3) by taking into account user preferences.
Keywords: Emotion and news, affect sensing from text, news categorization, user modeling, emotion modeling
