A probabilistic framework for short text classification
Mubashir Ali, Shehzad Khalid, Mazhar Iqbal Rana, Fizza Azhar · 2018
The development of World Wide Web has made it difficult for a user to understand textual data coming from diverse sources. Automatic classification of short text i.e. tweets classification, news headlines classification etc. is one of the severe problem for user to get the right information related to his/her interest. In order to cope with the problem of short text classification, in this paper, we have proposed a probabilistic framework for short text classification. Proposed classification model is composed of three major modules i.e. pre-processing of unstructured text, learning of probabilistic model and the classification of unseen data by using learned model. This framework is trained and tested by using news headlines dataset containing six different news categories i.e. politics, sports, business, weather, showbiz and terrorist. During the experimental evaluation 92.41%classification accuracy is achieved by using bigram as feature which demonstrates the effectiveness of proposed short text classification approach.