Personalized E-Learning on Social Web with Machine Learning

Abstract

Engaged User has been identified as a potential source of knowledge about personal interests, preferences, goals, and other attributes known from user models. As users are free to like the posts available on facebook such as photo and videos, status and links of their own interest, machine learning techniques are applied to analyze and predict that how many users engaged mostly with photos, videos, status and links. The main objective of this study is to analyze the Interest of engaged users on social web, Analyze and predict the engaged users on a particular post over the lifetime and analyzing and predicting facebook users personalized learning. In this work, we have proposed three machine learning algorithms to describe the users likes, shares and comments on posts of the facebook. In this article, we are proposing a new technology for classifying the users engaged in facebook based on Particle Swarm Optimization (PSO). The proposed machine learning algorithms shows that the performance of content-based engaged users is more reliable semantically for applied on personalized social web.