Gupta Sumit Kumar, Singh Dhirendra Pratap
Department of Computer Science, MANIT, Bhopal, India.
Arab J Sci Eng. 2023;48(2):1829-1843. doi: 10.1007/s13369-022-07020-z. Epub 2022 Jul 19.
The social media podium offers a communal perspective platform for web marketing, advertisement, political campaign, etc. It structures like-minded end-users over the explicit group as a community. Community structure over social media is the collaborative group of globally spread users having similar interests regarding a communal topic, product or any other axis. In recent years, researchers have widely used clustering techniques of data mining to structure communities over social media. Still, due to a lack of network and implicit communal information, researchers cannot bind mutually robust and modular community structures. The collaborative features of social media are inherent with implicit and explicit end-users. The explicit nature of both active and passive users is easily extracted from the graphical structure of social media. On the other hand, the degree of information inclusion of implicit features depends upon end-users participation. The Implicit features of frequently active users are diversely available, while integrating passive and silent users' implicit features over the community is tedious. This work proposed a social theory based influence maximization (STIM) framework for community detection over social media. It combines user-generated content with profile information, extracts passive social media users through influence maximization, and provides the user space for influencing inactive users. The STIM framework clusters identical nodes over the maximum influencing node axis based on their graphical parameters such as node degree, node similarity, node reachability, modularity, and node density. This framework also provides the structural, relational and mathematical concept for the functional grouping of like-minded people as a community over social media through social theory. Finally, an evaluation has been carried out over six real-time datasets. It analyses that convolution neural network over STIM structure more dense and modular communities via influence maximization. STIM acquired around 93% modularity and 94% Normalized Mutual Information (NMI), resulting in approximately 2.23% and 5.69% improvements in modularity and NMI, respectively, over the best-acquired result of the benchmark approach.
社交媒体平台为网络营销、广告、政治活动等提供了一个公共视角平台。它将志同道合的终端用户构建为一个明确群体之上的社区。社交媒体上的社区结构是全球范围内对某个公共话题、产品或其他任何方面有相似兴趣的用户的协作群体。近年来，研究人员广泛使用数据挖掘中的聚类技术来构建社交媒体上的社区。然而，由于缺乏网络和隐含的公共信息，研究人员无法构建相互稳健且模块化的社区结构。社交媒体的协作特性与显性和隐性终端用户固有相关。活跃和被动用户的显性特征很容易从社交媒体的图形结构中提取出来。另一方面，隐含特征的信息包含程度取决于终端用户的参与度。频繁活跃用户的隐含特征多种多样，而在社区中整合被动和沉默用户的隐含特征则很繁琐。这项工作提出了一种基于社会理论的影响最大化（STIM）框架，用于社交媒体上的社区检测。它将用户生成的内容与个人资料信息相结合，通过影响最大化提取被动社交媒体用户，并为影响不活跃用户提供用户空间。STIM框架基于节点度、节点相似度、节点可达性、模块度和节点密度等图形参数，在最大影响节点轴上对相同节点进行聚类。该框架还通过社会理论为将志同道合的人作为社交媒体上的一个社区进行功能分组提供了结构、关系和数学概念。最后，对六个实时数据集进行了评估。分析表明，卷积神经网络通过影响最大化在STIM结构上形成了更密集和模块化的社区。STIM获得了约93%的模块度和94%的归一化互信息（NMI），与基准方法的最佳结果相比，模块度和NMI分别提高了约2.23%和5.69%。
