• Dr.S.Samundeeswari

Trust Relationship between users play a vital role in making decisions for social network users. Existing trust relations are often extremely sparse, therefore unknown trust relationship attacks increase attention in recent years. We propose a new technique from machine learning to predict Trust relationships in social network by using K-nearest neighbour Algorithm (KNN) and also we extend our work to classify the messages posted by these identified trusted users on Social Network sites as Interesting or not Interesting posts. The classification of messages to identify the usefulness is done by using two attributes Length of message in number of words and Posting frequency in terms of time difference between consecutive messages from the same sender. We use real-world dataset Epinions to evaluate their performance in trust Prediction.

Trust Relationship, Social Network, Interesting Posts, KNN, Classification.

"New Prediction Method for Correct Decision Using Authorized Group Members Results", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.371-373, April-2019, Available :http://www.jetir.org/papers/JETIRBF06073.pdf

"New Prediction Method for Correct Decision Using Authorized Group Members Results", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp371-373, April-2019, Available at : http://www.jetir.org/papers/JETIRBF06073.pdf