Feeler: Emotion classification of text using vector space model

Abstract

Over the last quarter-century, there is increasing body of research on understanding the human emotions. In this study, automatic classification of anger, disgust, fear, joy and sad emotions in text have been studied on the ISEAR (International Survey on Emotion Antecedents and Reactions) dataset. For the classification we have used Vector Space Model with a total of 801 news headlines provided by "Affective Task" in SemEval 2007 workshop which focuses on classification of emotions and valences in text. We have compared our results with ConceptNet and powerful text based classifiers including Naive Bayes and Support Vector Machines. Our experiments showed that VSM classification gives better performance than ConceptNet, Naive Bayes and SVM based classifiers for emotion detection in sentences. We achieved an overall F-measure value of 32.22% and kappa value of 0.18 for five class emotional text classification on SemEval dataset which is better than Navie Bayes (28.52%), SVM (28.6%). We have tested and discussed the results of classification using cross-validation technique for emotion classification and sentiment analyses on both the ISEAR and SemEval datasets. In addition to the classification experiments we have developed an emotion enabled video player which automatically detects the emotion from subtitle text of video and displays corresponding emoticon.