User study on AffectIM, an avatar-based Instant Messaging system employing rule-based affect sensing from text

  • Authors:

  • Alena Neviarouskaya;Helmut Prendinger;Mitsuru Ishizuka

  • Affiliations:

  • University of Tokyo, Department of Information and Communication Engineering, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan;National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan;University of Tokyo, Department of Information and Communication Engineering, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

  • Venue:
  • International Journal of Human-Computer Studies
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Social interaction among people is an essential part of every society, and a strong foundation for the development and self-actualization of a person. Even in virtual environments we tend to interact in a social way. Our research addresses the tasks of recognition, interpretation, and visualization of affect communicated through text messaging. In order to facilitate sensitive and expressive interaction in computer-mediated communication, we previously introduced a novel syntactical rule-based approach to affect recognition from text. The evaluation of the developed Affect Analysis Model showed promising results regarding its capability to accurately recognize affective information in text from an existing corpus of informal online conversations. To enrich the user's experience in online communication, to make it enjoyable, exciting, and fun, we implemented a web-based Instant Messaging (IM) application, AffectIM, and endowed it with emotional intelligence by integrating the developed Affect Analysis Model. This paper describes the findings of a twenty-person study conducted with our AffectIM system. The results of the study indicate that our IM system with automatic emotion recognition function can achieve a level of affective intelligence (system is successful at conveying the user's feelings, avatar expression is appropriate) that is comparable to ''gold standard'', where users select the label of the conveyed emotion manually.