Analysis of User Vitality Prediction, Ranking and Providing Ads in Social Networking Services Based on Users Profile

Computer Engineering

Social networking services have been predominant at numerous online networks, for example, Twitter.com and Weibo.com, where a huge number of users continue cooperating with one another consistently. One interesting and important issue in the long range social networking services is to in a convenient manner. A precise ranking list of user vitality could benefit many parties in social network services such as the ads providers and site administrators. Despite the fact that it is exceptionally encouraging to acquire an vitality-based ranking list of users, there are numerous specialized difficulties because of the huge scale and dynamics of social networking data. In proposed system, there is a unique point of view to accomplish this objective, which is quantifying user vitality by analyzing the dynamic interactions among users on social networks and their profiles. The facility to build the social relations or social networks among users for instance, activities, share interest and physical connections is carried out by social networking services. Through such service, users could stay connected with each other and be informed of friends behaviors such as posting at a platform, and consequently be influenced by each other. Hence proposed system is a novel strategy to learn the latent profiles of social users rank them and recommend ads. To evaluate the performance of proposed algorithms collected two dynamic social network data sets. The experimental results with both data sets clearly demonstrate the advantage of proposed ranking and prediction methods.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.