Social Media Feed Elicitation
Lindsay Popowski, Xiyuan Wu, Xuyang Zhu, Tiziano Piccardi, Michael S. Bernstein
摘要
Social media users have repeatedly advocated for control over the currently opaque operations of feed algorithms. Large language models (LLMs) now offer the promise of custom-defined feeds—but users often fail to foresee the gaps and edge cases in how they define their custom feed. We introduce feed elicitation interviews, an interactive method that guides users through identifying these gaps and articulating their preferences to better author custom social media feeds. We deploy this approach in a online study to create custom Bluesky feeds and find that participants significantly prefer the feeds produced from their elicited preferences to those produced by users manually describing their feeds. Through feed elicitation interviews, we advance users’ ability to control their social media experience, empowering them to describe and implement their desired feeds.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper15
- Bridging the Gulf of Envisioning: Cognitive Challenges in Prompt Based Interactions with LLMsHariharan Subramonyam, Roy Pea, Christopher Lawrence Pondoc, Maneesh Agrawala 等CHI 2024 · 被引用 137 次
- "I See Me Here": Mental Health Content, Community, and Algorithmic Curation on TikTokAshlee Milton, Leah Ajmani, Michael Ann DeVito, Stevie ChancellorCHI 2023 · 被引用 115 次
- Designing Word Filter Tools for Creator-led Comment ModerationShagun Jhaver, Quan Ze Chen, Detlef Knauss, Amy X. ZhangCHI 2022 · 被引用 70 次
- "I'm not sure what difference is between their content and mine, other than the person itself": A Study of Fairness Perception of Content Moderation on YouTubeRenkai Ma, Yubo KouCSCW 2022 · 被引用 42 次
- Leveraging Structured Trusted-Peer Assessments to Combat MisinformationFarnaz Jahanbakhsh, Amy X. Zhang, David R. KargerCSCW 2022 · 被引用 41 次
相关 Paper
- Bonsai: Intentional and Personalized Social Media FeedsOmar El Malki, Marianne Aubin Le Quéré, Andrés Monroy-Hernández, Manoel Horta RibeiroCHI 2026 · 被引用 4 次
- Beyond Explicit and Implicit: How Users Provide Feedback to Shape Personalized Recommendation ContentWenqi Li, Jui-Ching Kuo, Manyu Sheng, Pengyi Zhang 等CHI 2025 · 被引用 14 次
- End User Authoring of Personalized Content Classifiers: Comparing Example Labeling, Rule Writing, and LLM PromptingLeijie Wang, Kathryn Yurechko, Pranati Dani, Quan Ze Chen 等CHI 2025 · 被引用 7 次
- Multi-LLM Persona Generation for Virtual Focus Groups in Software Engineering: A Controlled, Multi-domain Study of Emotional Requirements ElicitationGuangrui Fan, Dandan Liu, Lihu Pan, Rui Zhang 等FSE 2026
- Canvil: Designerly Adaptation for LLM-Powered User ExperiencesK. J. Kevin Feng, Q. Vera Liao, Ziang Xiao, Jennifer Wortman Vaughan 等CHI 2025 · 被引用 14 次
