Positive and Negative Link Prediction Algorithm Based on Sentiment Analysis in Large Social Networks

摘要

Signed network analysis being one of the greatest disruptive innovations within the last decade has assembled a vast amount of attention of the citizenry. The positions of the users of the signed networks are used by several societies in the world to see the mentality of the users, the current movement of the grocery store and many more things. But even so, in that location is a latent potential of social nets. Ace of the facial expressions that, we were able to determine was about seeing the relationship between the users (i.e., especially, the negative (i.e., ?Ve) link in social networks) on the signed network using the stakes that the users work and the reaction of the other users towards it. The anticipation of a negative link (i.e., ?Ve) can be applied in the information security field, to observe the aberrations in the largest social networks and further discover the malicious nodes in the larger social network; say, if two nodes are doing things together even though in that respect is no intercourse between them. It can likewise be utilized in improving the recommendation system in social networks as if there is some probability between the two the nodes of being an enemy or disliking each other then we can slay them from each other’s recommendation list or could assign a lesser weight to them in a recommended technique. To accomplish all this relationship between the nodes we first need to determine whether the user is posting posts with positive emotion (like happy, excited, etc.) or negative emotion (like angry, sad, and so on), and then that we can further examine the learning ability of the user and utilize it to recommend the people who we have previously separated with the similar personality. For that we have applied the sentiment analysis in social networks, which splits up the users into five simple categories: Highly Positive (i.e., Highly +Ve), Positive (i.e., +Ve), Neutral, Negative (i.e., ?Ve) and Highly Negative (i.e., Highly ?Ve).