Human Computer Interface for communication is a very powerful and most current area of research because the human world is getting more and more digitize and one wants the digital systems to behave like a human being. This requires the digital systems to imitate the human behavior accurately. Emotion is one aspect of human behavior which plays an important role in human feeling and decision making thus influencing the way people interact in the society. In human computer interaction, the computer interfaces need to recognize the emotion of the end users in order to exhibit a truly intelligent behavior. Human express the emotion in the form their facial expression, through their speech, and by writing text. The automatic identification of emotions in texts is important for applications such as: opinion mining and market analysis, affective computing, natural language interfaces, and e-learning environments, including educational games. This paper is mainly focused on to conveying the emotion expressed by a text documents. In simple way I can say that main aim of this study is to classify the emotion expressed by the text, based on pre-defined list of emotion i. e. Anger, Joy, Sad, Fear, Disgust, and Surprise. In order to collect the emotion evoking word, this study paper is mainly enlightened on ISEAR dataset, WPARD and Word-Net Affect dataset. A lot of attention is paid to the normalization of text and expand the knowledge base of emotion word. Uses of Vector Space Model for Information retrieval and classification.

Information Retrieval Vector Space Classification.