A Framework to Rank Nodes in Social Media Graph Based on Sentiment-Related Parameters

Abstract

Social networks provide a platform for users to interact and engage in various activities. Information pertaining to social media can be shared, ideas can be put forward and opinions can be analysed. Sentiment analysis of user comments can be done to extract important information and to make informed decisions. This paper elucidates previous work done on sentiment analysis and different ranking techniques for utilisation in different applications. A methodology is proposed in this paper for ranking users based on parameters such as likes, shares and user comments. Two ranking techniques are proposed in the methodology. One technique is based on the cosine similarity and the other involves features such as user comments.