Abstract: Students unofficial discussion on social media network drop light into their educational observations reaction, feelings, and involvement about the learning process. Data from such uninstrumented environments can provide valuable knowledge to inform student learning. Analyzing such data, however, can be challenging. Data mining on student data is performed in this system. Social Networking Portal same as Facebook is developed in this Project. Classification of student posts into different categories such as Politics, Education, Entertainment, Sports etc. is made based on analysis of post messages in this College Network Portal. Interest of any student friend can be seen by user of this network from categories graph data. Adult images are blocked into College Social Network using adult detection based on Image Processing. Student posts, comments are analyzed to classify into Crime, Riots, and Worst or Vulgar categories. Sentiment analysis is done on user posts and comments using NLP (Natural Language Processing) algorithm to detect user sentiments. Staff can enter student’s marks, behaviour into database through this network. A Report of Student based on Social Network activities will be automatically generated and shown to Admin and Staff of College. If Student exceeds limit of vulgar activities it will be seen by admin and right action would be taken. 

Keywords: Data Mining, NLP (Natural Language Processing), Skin Detection, Image Processing.