Removing Flaming Problems from Social Networking Sites using Semi-Supervised Learning Approach
Vishakha Mal, A. J. Agrawal · 2016
Natural Language Processing (N.L.P.) is a field of Computer Science concerned with the interactions between Computer and Human (Natural) Languages. Social Networking Sites (S.N.S.) are amongst the most effective communication tools now days. But it also gave rise to the problem of flaming which is difficult to deal with. A flaming incident is triggered by comments and actions of users in S.N.S. that ends up damaging reputation or causing negative impact on the target party. So, this review paper is based on dealing with flaming problems and hence prevention of damages caused due to them. In this paper we have presented a brief review about various classifiers and methods that can be used for classification of documents in to required classes namely Positive, Negative and Neutral, such as Sentiment Analysis, Discourse Analysis, Naïve Bayes Classifier[1][2], Maximum Entropy Classifier[3], Back Propagation Neural Networks[2], Topic Modeling[5], Semi-Supervised Learning[1] etc. N.L.P. techniques of Parsing, P.O.S. Tagging [4], and Tokenization etc have also been studied. The method of Semi-Supervised Learning including Maximum Entropy Classifier has been proposed to deal with the flaming problems.