Question identification and classification on an academic question answering site

Abstract

Online communities such as wikis, blogs, forums, scientific communities and other social networking services have enabled new levels of interactions and interconnections among individuals, documents and data and have become places for people to seek and share expertise. In this paper, we propose a systematic approach to identification and classification of questions. The questions were first identified using semantic occurrence of Part of Speech (POS) tag in English Language, after which they were classified based on maximum probability value of Naïve Bayes classification. The model was validated and evaluated with experiments on some crawled web pages from ResearchGate.