ABSTRACT
The emergence of filter bubbles leads to various harms. To mitigate filter bubbles, some recent works select the seeds for different viewpoints to minimize the formation of bubbles under the influence propagation model. Different from these works where the diffusion networks remain unchanged, in this paper, we conduct the first attempt to mitigate filter bubbles via edge insertion. Besides, to be more generalized, we focus on mitigating filter bubbles for the given target node set since the audiences can be different for different scenarios. Specifically, we propose the concept of openness score for each target node, which serves as a metric to assess the likelihood of this node being influenced by multiple viewpoints simultaneously. Given a directed graph G, two seed sets, a positive integer k and a target node set, we aim to find k edges incident to the given seeds such that the total openness score is maximized. We prove the NP-hardness of problem studied. A baseline method is first presented by extending the greedy framework. To handle large graphs efficiently, we develop a sampling-based strategy. A data-dependent approximation method is developed with theoretical guarantees. Experiments over real social networks are conducted to demonstrate the advantages of proposed techniques.
Supplemental Material
- Prithu Banerjee, Wei Chen, and Laks V. S. Lakshmanan. 2023. Mitigating Filter Bubbles Under a Competitive Diffusion Model. In SIGMOD.Google Scholar
- Christian Borgs, Michael Brautbar, Jennifer T. Chayes, and Brendan Lucier. 2014. Maximizing Social Influence in Nearly Optimal Time. In SIAM.Google Scholar
- Vineet Chaoji, Sayan Ranu, Rajeev Rastogi, and Rushi Bhatt. 2012. Recommendations to boost content spread in social networks. In WWW.Google Scholar
- Chen Chen, Qiuyu Zhu, Renjie Sun, Xiaoyang Wang, and Yanping Wu. 2023. Edge Manipulation Approaches for K-Core Minimization: Metrics and Analytics. In TKDE.Google Scholar
- Uriel Feige. 1998. A Threshold of ln n for Approximating Set Cover. In JACM.Google Scholar
- Kiran Garimella, Aristides Gionis, Nikos Parotsidis, and Nikolaj Tatti. 2017. Balancing information exposure in social networks. In NeurIPS.Google Scholar
- David Kempe, Jon M. Kleinberg, and É va Tardos. 2003. Maximizing the spread of influence through a social network. In KDD.Google Scholar
- Wei Lu, Wei Chen, and Laks V. S. Lakshmanan. 2015. From Competition to Complementarity: Comparative Influence Diffusion and Maximization. In VLDB.Google Scholar
- Antonis Matakos, cC igdem Aslay, Esther Galbrun, and Aristides Gionis. 2022. Maximizing the Diversity of Exposure in a Social Network. In TKDE.Google Scholar
- C Thi Nguyen. 2020. Echo chambers and epistemic bubbles. In Episteme.Google Scholar
- Anne Shelley. 2012. Book review of Eli Pariser's The filter bubble: What the Internet is hiding from you. In First Monday.Google Scholar
- Jing Tang, Xueyan Tang, Xiaokui Xiao, and Junsong Yuan. 2018. Online Processing Algorithms for Influence Maximization. In SIGMOD.Google Scholar
- Sijing Tu, cC igdem Aslay, and Aristides Gionis. 2020. Co-exposure Maximization in Online Social Networks. In NeurIPS.Google Scholar
- Xiaoyang Wang, Ying Zhang, Wenjie Zhang, and Xuemin Lin. 2016. Efficient distance-aware influence maximization in geo-social networks. In TKDE.Google Scholar
- Fangsong Xiang, Jinghao Wang, Yanping Wu, Xiaoyang Wang, Chen Chen, and Ying Zhang. 2024. Rumor blocking with pertinence set in large graphs. In WWWJ.Google Scholar
- Liwang Zhu, Qi Bao, and Zhongzhi Zhang. 2021. Minimizing Polarization and Disagreement in Social Networks via Link Recommendation. In NeurIPS.Google Scholar
- Weijie Zhu, Chen Chen, Xiaoyang Wang, and Xuemin Lin. 2018. K-core minimization: An edge manipulation approach. In CIKM.Google Scholar
- Yuqing Zhu, Jing Tang, Xueyan Tang, Sibo Wang, and Andrew Lim. 2023. 2-hop Sampling: Efficient and Effective Influence Estimation. In TKDE. ioGoogle Scholar
Index Terms
- Targeted Filter Bubbles Mitigating via Edges Insertion
Recommendations
Mitigating Filter Bubbles Under a Competitive Diffusion Model
PACMMODWhile social networks greatly facilitate information dissemination, they are well known to have contributed to the phenomena of filter bubbles and echo chambers. This in turn can lead to societal polarization and erosion of trust in public institutions. ...
Bubble Trouble: Strategies Against Filter Bubbles in Online Social Networks
Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management. Healthcare ApplicationsAbstractIn the recent past, some electoral decisions have gone against the pre-election expectations, what led to greater emphasis on social networking in the creation of filter bubbles. In this article, we examine whether Facebook usage motives, ...
Comments