TEXTUAL EMOTION RECOGNITION FOR ENHANCING SOCIAL PRESENCE IN ONLINE COMMUNICATIONS

Abstract

This paper presents an emotion recognition model that assesses the affective content from textual messages. Thefocus is on emotion recognition from online non verbal textual symbols of vocalics (e.g., the use of capitals and useof punctuation “!” and “!!s!” or “?” and “???”, length of response, etc), and those of chronemics (e.g. time torespond to an email or to a discussion posting, the length of the response, etc) that are used in text. The modelemploys a supervised machine learning approach to recognize six basic emotions (anger, disgust, fear, happiness,sadness and surprise) using an emotion-annotated training set composed of online chat messages exchanged byuniversity students. Naive Bayes algorithm is used to classify messages to the mentioned emotional classes basedon a variety of features. The model also takes into consideration the evolving language particularly the languageused in online chat where people tend to use an informal style of writing. Observations from informal experimentscomparing a chat system integrated with the emotion estimation model with a conventional chat system suggestthat an online interface that conveys emotional information helps online users to interact with each other moreefficiently thus providing an enhanced social presence.