A filtering of message in online social network using hybrid classifier

In emerging trend of society based on online social networking (OSN), it is useful for associative with social relationship. It is mainly used to share all moments via messages with their private and public sector. In this social network, most of the people used to send indecent text to others. So, non-essential text will be neglected from user to view desirable messages on their OSN walls. This paper explores the use of short text classifier includes latent semantic analysis for extracting meaningful text to present on their user wall by preventing useless messages. The proposed algorithm concerns hybrid combination of text classifiers such as support vector machine SVM–ELM, SVM–NAÏVE, NAÏVE–ELM, and NAÏVE–artificial neuro-fuzzy inference systems. Comparative study of these techniques contributes which will gives higher prediction accuracy in evaluation process.