A ringtone recommendation agent based on a Bayesian model of user emotion

This paper presents a ringtone recommendation agent system which utilizes user's emotion to recommend an appropriate ringtone and the suitable volume level of a mobile phone. The system uses a Bayesian Network (BN) to infer user's emotion and the volume level at the current situation. After inferring user's emotion, a ringtone is selected from the pool of various kinds of genres of ringtones. Also, the volume level can be controlled according to the inferred volume level. User's feedback on the inferred values can be used to retrain the BN to provide the user with a personalized service. Experimental results showed that the proposed system is quite convenient and very useful.

[1]  Jun Ozawa,et al.  Cellular phone ringing tone recommendation system based on collaborative filtering method , 2003, Proceedings 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation. Computational Intelligence in Robotics and Automation for the New Millennium (Cat. No.03EX694).

[2]  Albrecht Schmidt,et al.  Advanced Interaction in Context , 1999, HUC.

[3]  Eric Horvitz,et al.  Bayesphone: Precomputation of Context-Sensitive Policies for Inquiry and Action in Mobile Devices , 2005, User Modeling.

[4]  Andreas Krause,et al.  SenSay: a context-aware mobile phone , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[5]  Rosalind W. Picard.  Affective Computing , 1997 .

[6]  Jin Song Dong,et al.  Semantic Space: an infrastructure for smart spaces , 2004, IEEE Pervasive Computing.

[7]  J. B. Brooke,et al.  SUS: A 'Quick and Dirty' Usability Scale , 1996 .

[8]  Daniel Zelterman,et al.  Bayesian Artificial Intelligence , 2005, Technometrics.