Bara’a Talaat Ahmed Seyala
Community Detection in Facebook Using Visual Approach and Clustering
The previous decade has seen the growth of interested with networks and participatory social media that have brought users jointly in many originative ways. Many of users play, categorize, work and socialize online, showing new forms of cooperation, communication, and cleverness that were hard to imagine just a while ago. Social media refers to the interaction between people who create, share information and ideas in communities and virtual networks. Social media also helps reform business models, influence views and sentiments, and opens many possibilities for studying human interaction and mass conduct on an unprecedented level. This research employs visual representation of data and cluster algorithms for discovering patterns in the Facebook network to learn some of the behaviors practiced by community members. The results can be used to find out users directions in order to suggest appropriate advertisements for it, and cluster algorithms can be used to collect suspicious and inappropriate communication pages to take the necessary measures to prevent them from appearing to sensitive groups in the community, and the results can also be used to direct Facebook users, especially young groups, to organize their times and control the times they spend on social media.
Facebook, visual representation, K-Means, Density-Based Spatial Clustering of Applications with Noise (DBSCAN).