Abstract
The volume of information generated by a huge number of social networks users is increasing every day. Social networks analysis has gained intensive attention in the data mining research community to identify circles of users depending on the characteristics in the individual profiles or the structure of the network. In this paper, we propose the boosting principle to find the circles of social networks. Constrained k-means clustering method is used as a weak learner with the boosting framework. This method generates a constrained clustering represented by a kernel matrix according to the priorities of the pair-wise constraints. The experimental results show that the proposed algorithm using boosting principle for social network analysis improves the performance of the clustering and outperforms the state-of-the-art.
Highlights
Due to the evolution in computer science and Internet, social network is considered a positive change in our society where a huge number of people communicate with each other, exchange information, ideas, news, etc. [1]
Social network analysis has gained intensive attention in the data mining research community to identify the groups of the individuals depending on the characteristics in the individual profiles or the structure of the network
The boosting approach is used to improve the performance of modified COP K-means (MC-KM) algorithm [17]
Summary
Due to the evolution in computer science and Internet, social network (virtual society) is considered a positive change in our society where a huge number of people communicate with each other, exchange information, ideas, news, etc. [1]. Social networks clustering which is named unsupervised learning, is improved by side information that are called constrained data clustering (semi-supervised clustering) that uses the pre-given knowledge (ground-truth) about the data pairs for enhancing the clustering accuracy. COP-K means method [19] is used for pair-wise constrained clustering It is based on the k-means algorithm and it is quick and easy to implement but it generates unsteady clustering results depending on the data assignment order. The framework of boosting for data clustering is able to enhance the performance of the clustering method using the pair-wise constraints. We employ the boosting principle by learning constraints priorities for social networks circles discovery. It uses two types of data to perform social networks clustering; profile information given by users and the topological structure of the network.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
