Header menu link for other important links
Algorithm for prediction of negative links using sentiment analysis in social networks
, P. Sharma
Published in Institute of Electrical and Electronics Engineers Inc.
Pages: 1570 - 1575
The social network being one of the most disruptive innovations of the last decade has gathered a huge amount of attention of the people. The posts of the users of the social media are used by many companies in the world to find the mentality of the users, the current trend of the market and many more things. But still, there is a latent potential in the social network. One of the aspect that we were able to discover was about finding the relationship between the users (i.e., especially, the negative link) on the social network using the posts that the users make and the reaction of the other users towards it. The prediction of the negative link can be applied in the cyber security field, to observe the aberrations in the network and further find the malicious nodes in the social network; say, if two nodes are doing things together even though there is no relation between them. It can also be used in improving the recommendation system in social media as if there is some probability between the two nodes of being the enemy or disliking each other then we can remove them from each other's recommendation list or could assign a lower weight to them in our recommendation algorithm. To achieve all this relationship between the nodes we first need to find whether the user is posting posts with positive emotion (like happy, excited, etc.) or negative emotion (like angry, sad, etc.) so that we can further analyze the mentality of the user and use it to recommend the people who we have previously classified with the similar personality. For that, we have used the sentiment analysis, which divides the users into five simple categories: Extremely +ve(i.e.,positive), +ve, Neutral, -ve (i.e.,negative) and Extremely -ve. This research paper explains the methodologies that we have used to achieve the prediction of negative links between the nodes in the social network. © 2017 IEEE.