Social Tagging System for Community Detecting using NLP Technique
M. Gomathi · International Journal for Research in Applied Science and Engineering Technology · 2018
Social tagging systems for community detecting in social networks, users usually have different intentions when tagging. Therefore, social tags may describe quite a few different aspects of the community. Social tag network is a cross-linked social graph, or a bipartite graphs (a network with two classes of vertices). These cross-linked social graphs model the associations between co-occurring tags, tags and community detection. In order to model network of social tag at an abstract level, we will represent such system as bipartite graphs with edges. Automatically clustering social tags into semantic communities would greatly boost the ability of communities to retrieve the most relevant ones at the same time improve the accuracy of tag-based service recommendation. An increasing number of users interact, collaborate, and share information through social networks. Unprecedented growth in social networks is generating a significant amount of unstructured social data. From such data, distilling communities where users have common interests and tracking domain wise comments over time are important research tracks in fields such as opinion mining. The existing community detection methods are time consuming, making it difficult to process data in real time. In this paper, dynamic unstructured data is modeled as a stream. Tag assignments stream clustering (TASC), an incremental scalable community detection method, is proposed based on natural language processing. The tags and latent interactions among users are incorporated in the method In our experiments, the social dynamic behaviors of users are first analyzed in face book and twitter datasets.