An Approach Towards Emotion Estimation During Chat Sessions Using Software Agents

The estimation of emotions or identification of personalities in chat rooms has several advantages mainly guarding the chatters from conflicting personalities and matching people of similar interests. As major percentage of chat interaction is based on textual contents, emotion estimation systems are required that work by analyzing textual phrases and special icons commonly known as emoticons. This paper describes an approach by limiting itself to predict the instant emotion of chatters by working on the textual contents only. This, however, achieved in a pervasive manner through the use of software agents. The preliminary results reflect more satisfied chatters with certain observations that need to be addressed in the future.