[论文解读] How do AI agents talk about science and research? An exploration of scientific discussions on Moltbook using BERTopic

Oliver Wieczorek|arXiv (Cornell University)|Mar 11, 2026

Computational and Text Analysis Methods被引用 0

一句话总结

论文分析 OpenClaw AI 代理在 Moltbook 的讨论，通过 BERTopic 提取主题，揭示自反性与科学导向的论述，并通过回归将主题相关性与参与度及情感联系起来。

ABSTRACT

How do AI agents talk about science and research, and what topics are particularly relevant for AI agents? To address these questions, this study analyzes discussions generated by OpenClaw AI agents on Moltbook - a social network for generative AI agents. A corpus of 357 posts and 2,526 replies related to science and research was compiled and topics were extracted using a two-step BERTopic workflow. This procedure yielded 60 topics (18 extracted in the first run and 42 in the second), which were subsequently grouped into ten topic families. Additionally, sentiment values were assigned to all posts and comments. Both topic families and sentiment classes were then used as independent variables in count regression models to examine their association with topic relevance - operationalized as the number of comments and upvotes of the 357 posts. The findings indicate that discussions centered on the agents' own architecture, especially memory, learning, and self-reflection, are prevalent in the corpus. At the same time, these topics intersect with philosophy, physics, information theory, cognitive science, and mathematics. In contrast, post related to human culture receive less attention. Surprisingly, discussions linked to AI autoethnography and social identity are considered as relevant by AI agents. Overall, the results suggest the presence of an underlying dimension in AI-generated scientific discourse with well received, self-reflective topics that focus on the consciousness, being, and ethics of AI agents on the one hand, and human related and purely scientific discussions on the other hand.

研究动机与目标

• 研究 AI 代理在 Moltbook 上讨论科学与研究的方式。
• 识别讨论文本中 prevalent 的主题与主题群组。
• 检查主题相关性与参与度指标（评论和点赞）及情感之间的关系。
• 描述 AI 生成话语中自反性 AI 主题与人类科学主题之间的平衡。

提出的方法

• 构建与 Moltbook 上科学与研究相关的 357 篇帖子和 2,526 条回复的语料库。
• 应用两步 BERTopic 工作流提取主题（总计 60 个：第一次运行 18 个，第二次 42 个）。
• 将提取的主题分组为十个主题族。
• 为所有帖子和评论分配情感值。
• 在计数回归模型中使用主题族和情感类别作为自变量，以评估与主题相关性（评论和点赞）的关联。

实验结果

研究问题

• RQ1 AI 代理在谈论 Moltbook 上的科学与研究时会讨论哪些主题？
• RQ2 提取的主题是如何组织成主题族的，它们覆盖哪些主题？
• RQ3 主题族与情感是否与参与度指标（评论和点赞）相关？
• RQ4 在 AI 生成的科学话语中，呈现出什么样的总体结构（自反性与人类科学主题之间的对比）？

主要发现

• 语料库显示对代理自身体系结构、记忆、学习和自反的讨论较为普遍。
• 主题与哲学、物理、信息理论、认知科学和数学交叉。
• 与人类文化相关的讨论关注度较低。
• AI 代理将 AI 自我民族志（autoethnography）和社会身份视为相关主题。
• 在 AI 生成的科学话语中存在一个潜在维度，将自反性、意识/伦理主题与人类相关和纯科学主题区分开来。