A Graph-Based Node Identification Model in Social Networks

Abstract

An enormous amount of data is being generated in many social networking sites. Among them, Twitter is the most data generated platform, which includes commercial data, business data, events, and polls. Various tasks can be done with the generated data. One among them is finding the trending keyword in the huge data. To obtain the trending keyword, we have to consider certain factors to improve the model performance, which includes centrality measure, term frequency, and the position of the nodes in the network. Therefore, we propose a graph-based keyword extraction approach referred to as Multi-Attribute Keyword Extraction (MAKE) which determines the significance of a keyword with the aid of collectively taking various influencing parameters. The proposed graph-based approach is more accurate in finding the importance of a node in the network including the above-mentioned factors.