NTT Paper Accepted for Publication in IEEE Transactions on Network Science and Engineering, a Competitive International Journal in Network Science and Engineering

A paper from NTT has been accepted for publication in IEEE Transactions on Network Science and Engineering (TNSE), a leading international journal in the field of network science and engineering. The accepted paper is as follows.

■ Minimizing Misinformation Spread Through Targeted Prebunking in Social Networks

Satoshi Furutani (NTT Social Informatics Laboratories); Toshiki Shibahara (NTT Social Informatics Laboratories); Mitsuaki Akiyama (NTT Social Informatics Laboratories); Masaki Aida (Tokyo Metropolitan University)

As a preventive measure against misinformation on social media, “prebunking” interventions have attracted growing attention. Prebunking aims to make users more resistant to misinformation by “inoculating” them with its characteristics and typical manipulation techniques before they encounter it. In this study, we considered a setting in which prebunking interventions can be provided to only a limited number of users, and formulated the question of “which users should be targeted to most effectively suppress the spread of misinformation across the social network” as a combinatorial optimization problem. To enable efficient target selection even in large-scale networks, we further proposed a method that efficiently approximates the gain from an intervention by considering only the paths with the highest influence propagation probabilities for each intervention candidate. Numerical experiments using multiple real-world network datasets demonstrated that the proposed method can effectively suppress the spread of misinformation while remaining applicable to large-scale networks. This work provides a foundational technology for allocating limited intervention resources effectively to suppress misinformation across an entire network by selecting intervention targets while taking into account not only individual users but also the propagation of information to surrounding users.

Journal: IEEE Transactions on Network Science and Engineering (IF: 7.3)
DOI: 10.1109/TNSE.2026.3719287
URL: https://doi.org/10.1109/TNSE.2026.3719287