Intelligent Topical Sentiment Analysis for the Classification of E-Learners and Their Topics of Interest

摘要: Every day, huge numbers of instant tweets (messages) are published on Twitter as it is one the massive social media for e-learners interactions. The options regarding various interesting topics to be studied discussed among learners and teachers through capture ideal sources in Twitter. common sentiment behavior towards these received number messages about them. In this paper, rather than using opinion polarity each message relevant topic, authors focus sentence level classification upon unsupervised algorithm named bigram item response theory (BIRT). It differs from traditional document algorithm. investigation illustrated paper threefold which listed follows: (1) lexicon based tweet messages; (2) cooccurrence relationship naive Bayesian; (3) (BIRT) topics. has been proposed that a model constructed topical inference. performance improved remarkably when compared with other supervised algorithms. experiment conducted real life dataset containing different set