Abstract
This paper describes an emoticon recommendation system based on the emotional statements of users and their past selections of emoticons. Emoticons play an effective role to express user's feeling in online text-based communication. In these days, emoticons have grown its variety of patterns to almost 60,000 in Japan. However, it is difficult for users to select an appropriate emoticon from a large number of emoticons. The emoticon recommendation system aims to assist users to find a suitable emoticons in the database and easily insert them into the system. The system is comprised of an affect analysis system and an original database, a table of emoticon organized according to the gradation of 10 distinctive emoticons which was created by conducting a questionnaire. The confirmation of the effectiveness of this proposed system was conducted through an evaluation experience.
