2019/01/19 by Mohsen Shahriari, Shahriari, Mohsen, Ralf Klamma +3
Computer Science · Physics and Astronomy · #Complex Network Analysis Techniques #FOS: Computer and information sciences #Online Learning and Analytics #Social and Information Networks (cs.SI) #Software Engineering Research
paper · pdf · doi:10.48550/arxiv.1901.06608
openalex publication_date 2019/01/19 · openalex created_date 2022/07/30 · openalex updated_date 2026/07/28
Many real-world networks can be modeled by networks of interacting agents.\nAnalysis of these interactions can reveal fundamental properties from these\nnetworks. Estimating the amount of collaboration in a network corresponding to\nconnections in a learning environment can reveal to what extent learners share\ntheir experience and knowledge with other learners. Alternatively, analyzing\nthe network of interactions in an open source software project can manifest\nindicators showing the efficiency of collaborations. One central problem in\nsuch domains is the low cooperativity values of networks due to the low\ncooperativity values of their respective communities. So administrators should\nnot only understand and predict the cooperativity of networks but also they\nneed to evaluate their respective community structures. To approach this issue,\nin this paper, we address two domains of open source software projects and\nlearning forums. As such, we calculate the amount of cooperativity in the\ncorresponding networks and communities of these domains by applying several\ncommunity detection algorithms. Moreover, we investigated the community\nproperties and identified the significant properties for estimating the network\nand community cooperativity. Correspondingly, we identified to what extent\nvarious community detection algorithms affect the identification of significant\nproperties and prediction of cooperativity. We also fabricated binary and\nregression prediction models using the community properties. Our results and\nconstructed models can be used to infer cooperativity of community structures\nfrom their respective properties. When predicting high defective structures in\nnetworks, administrators can look for useful drives to increase the\ncollaborations.\n