[2/5] We structure computational persuasion around three key perspectives:
π€ AI as Persuader: Generating persuasive content.
π― AI as Persuadee: Vulnerability to persuasive influence.
βοΈ AI as Persuasion Judge: Detecting persuasive tactics and ethical concerns.
[3/5] We introduce a taxonomy for computational persuasion research, highlight critical challenges, and map out future directions for safe, fair, and effective persuasive AI systems.
Beyza Bozdag
[4/5] We'll also be maintaining a GitHub repository for computational persuasion research. Datasets, code, and resources will be included! Contributions and collaborations are warmly welcomed! π
Check it out: github.com/beyzabozdag/...
Thrilled to announce our new survey that explores the exciting possibilities and troubling risks of computational persuasion in the era of LLMs π€π¬
πArxiv: arxiv.org/pdf/2505.07775
π» GitHub: github.com/beyzabozdag/...
[5/5] Persuasion research is still playing catch-up, promising great advancements!β¨
Thank you to my amazing co-authors! @shuhaib.bsky.social @xiaocheng-yang.bsky.social @HyeonjeongHa @ziruicheng.bsky.social @EsinDurmus @JiaxuanYou @HengJi @gokhantur.bsky.social @dilekh.bsky.social