Abstract
Every day, huge numbers of instant tweets (messages) are published on Twitter as it is one of the massive social media for e-learners interactions. The options regarding various interesting topics to be studied are discussed among the learners and teachers through the capture of ideal sources in Twitter. The common sentiment behavior towards these topics is received through the massive number of instant messages about them. In this paper, rather than using the opinion polarity of each message relevant to the topic, authors focus on sentence level opinion classification upon using the unsupervised algorithm named bigram item response theory (BIRT). It differs from the traditional classification and document level classification algorithm. The investigation illustrated in this paper is of threefold which are listed as follows: (1) lexicon based sentiment polarity of tweet messages; (2) the bigram cooccurrence relationship using naïve Bayesian; (3) the bigram item response theory (BIRT) on various topics. It has been proposed that a model using item response theory is constructed for topical classification inference. The performance has been improved remarkably using this bigram item response theory when compared with other supervised algorithms. The experiment has been conducted on a real life dataset containing different set of tweets and topics.
Highlights
Social network analysis (SNA) can be considered as a global methodological approach to measure, visualize, and predict the interaction with one another in their field of study.The learning relationship between the students from their similar cultural background and their topic of interest can be analyzed
(2) The various online data mining techniques like classification, clustering information retrieval, question answering system, and query expansion are being used for social network analysis to the e-learning environment
It has been observed that the emotional intelligence (EI) of the teacher has a significant impact on teaching satisfaction [3]
Summary
Social network analysis (SNA) can be considered as a global methodological approach to measure, visualize, and predict the interaction with one another in their field of study. (2) The various online data mining techniques like classification, clustering information retrieval, question answering system, and query expansion are being used for social network analysis to the e-learning environment. The emotional intelligence helps the teacher and student to predict their performance. The novel algorithm called bigram topical item response theory (BIRT) for sentiment classification is achieved by an objective function which builds the model for the representation and predicts the document sentiment. In this paper rather than using the opinion polarities of each message relevant to the topic, the sentence level opinion classification based on BIRT is discussed. Unlike the fixed set of responses, dynamic response theory in terms of multiple factors on varied topics by different sets of interactions between the user communities offers the novelty of sentiment analysis. The likelihood of the responses and item level analysis can be formulated through the IRT model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
