Designed to Spread: A Generative Approach to Enhance Information Diffusion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (2) · 944-952
DOI: 10.1609/aaai.v40i2.37063 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ziqing Qian und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Social media has fundamentally transformed how people access information and form social connections, with content expression playing a critical role in driving information diffusion. While prior research has focused largely on network structures and tipping point identification, it provides limited tools for automatically generating content tailored for virality within a specific audience. To fill this gap, we propose the novel task of Diffusion-Oriented Content Generation (DOCG) and introduce an information enhancement algorithm for generating content optimized for diffusion. Our method includes an influence indicator that enables content-level diffusion assessment without requiring access to network topology, and an information editor that employs reinforcement learning to explore interpretable editing strategies. The editor leverages generative models to produce semantically faithful, audience-aware textual or visual content. Experiments on real-world social media datasets and user study demonstrate that our approach significantly improves diffusion effectiveness while preserving the core semantics of the original content.
Zitieren
APA
Qian, Z., Lei, J., Dang, S., & Cao, N. (2026). Designed to Spread: A Generative Approach to Enhance Information Diffusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 944-952. https://doi.org/10.1609/aaai.v40i2.37063
Vancouver
Qian Z, Lei J, Dang S, Cao N. Designed to Spread: A Generative Approach to Enhance Information Diffusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(2):944-952. doi:10.1609/aaai.v40i2.37063
BibTeX
@article{Qian2026,
author = {Qian, Ziqing and Lei, Jiaying and Dang, Shengqi and Cao, Nan},
title = {Designed to Spread: A Generative Approach to Enhance Information Diffusion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {2},
pages = {944--952},
doi = {10.1609/aaai.v40i2.37063}
}
EUVIMED