在线社交网络个体影响力算法测试与性能评估

Performance analysis and testing of personal influence algorithm in online social networks

社交影响力是驱动信息传播的关键因素,基于在线社交网络数据,可以对社交影响力进行建模和分析。针对一种经典的个体影响力计算方法,介绍了该算法的2种并行化实现,并在真实大规模在线社交网络数据集上进行了性能测试。结果表明,借助现有的大数据处理框架,显著提高了个体影响力计算方法在海量数据集中的计算效率,同时也给该类算法的研究和优化提供了实证依据。

Social influence is the key factor to drive information propagation in online social networks and can be modeled and analyzed with social networking data.As a kind of classical personal influence algorithm,two parallel implementation versions of a PageRank based method were introduced.Furthermore,extensive experiments were conducted on a large-scale real dataset to test the performance of these parallel methods in a distributed environment.The results demonstrate that the computational efficiency of the personal influence algorithm can be improved significantly in massive data sets by virtue of existing big data processing framework,and provide an empirical reference for the future research and optimization of the algorithm as well.