Target-Aware Holistic Influence Maximization in Spatial Social Networks
Target-Aware Holistic Influence Maximization in Spatial Social Networks
复制标题
空间社交网络中目标感知的整体影响力最大化
DOI：
10.1109/tkde.2020.3003047
复制
发表时间：
2022-04-01
影响因子：
8.9
通讯作者：
Yu, Jeffrey Xu
中科院分区：
文献类型：
--
作者：
Cai, Taotao;Li, Jianxin;Yu, Jeffrey Xu
影响力最大化最近在社交网络平台上安排在线活动或广告方面受到了极大的关注。然而，大多数研究只关注用户通过网络互动的影响，而忽略了他们的物理互动，这也是衡量影响力传播的关键。此外，有针对性的运动或广告没有得到足够的重视。为了解决这些问题，我们首先设计了一个新的整体影响力扩散模型，考虑到网络和物理用户的互动，在一个有效和实用的方式。基于新的扩散模型，我们制定了一个新的问题的整体影响最大化，表示为HIM查询，有针对性的广告在空间社交网络。HIM查询问题的目标是寻找一个整体影响力能够覆盖网络中所有目标用户的最小用户集，属于集合覆盖问题。由于HIM查询问题是NP难的，我们开发了一个贪婪的基线算法，然后对该算法进行改进，以减少计算成本。为了处理大型网络，我们还设计了一个空间社会索引来维护用户的社会，空间和文本信息，以及开发一个基于索引的高效解决方案。最后，我们使用一个合成数据集和三个真实世界的数据集进行了广泛的实验，以验证所提出的整体影响力扩散模型和我们开发的算法的效率和有效性。
Influence maximization has recently received significant attention for scheduling online campaigns or advertisements on social network platforms. However, most studies only focus on user influence via cyber interactions while ignoring their physical interactions which are also essential to gauge influence propagation. Additionally, targeted campaigns or advertisements have not received sufficient attention. To address these issues, we first devise a novel holistic influence diffusion model that takes into account both cyber and physical user interactions in an effective and practical way. Based on the new diffusion model, we formulate a new problem of holistic influence maximization, denoted as HIM query, for targeted advertisements in a spatial social network. The HIM query problem aims to find a minimum set of users whose holistic influence can cover all target users in the network, which belongs to a set covering problem. Since the HIM query problem is NP-hard, we develop a greedy baseline algorithm and then improve on this algorithm to reduce the computational cost. To deal with large networks, we also design a spatial-social index to maintain the social, spatial and textual information of users, as well as developing an index-based efficient solution. Finally, we conduct extensive experiments using one synthetic and three real-world datasets to validate the efficiency and effectiveness of the proposed holistic influence diffusion model and our developed algorithms.