发表机构
School of Business, Technical University of Applied Sciences Augsburg; Data Science und Autonome Systeme Technologietransferzentrum (TTZ)（奥格斯堡应用技术大学商学院; 数据科学与自主系统技术转移中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出计算框架，从协作VR游戏带时间戳对话检测团队过程阶段，经评估其可识别连贯阶段结构，为分析协作活动提供透明可迁移方法。
AI 中文摘要
协作虚拟现实（VR）环境使团队沟通在展开过程中可被观测，但传统的文本分析常总结整个试验或将其划分为固定时间窗口，这类方法可能掩盖团队沟通与协调随时间的变化。本文提出一种计算框架，用于从协作VR游戏中带时间戳的对话检测和解释动态团队过程阶段。该框架采用后期分块生成上下文感知的文本表示，将其聚合为时间分块，并应用带惩罚的高斯核变点检测识别团队沟通中的语义转变。边界检测后，词频-逆文档频率（TF-IDF）、非负矩阵分解（NMF）和代表性文本片段为阶段解释提供结构化证据。本地部署的大语言模型（LLM）利用上下文学习生成初始解释，随后由人类审核。将独立记录的交互日志与检测到的阶段对齐，以检查对应的任务-行动模式。评估对比了表示、池化策略、分割方法、参数设置、经审核的阶段解释以及阶段对齐的交互概况。结果表明，该框架能识别连贯且可解释的阶段结构，同时保留对底层文本证据的可追溯性；文本衍生的阶段与交互行为的对应关系进一步支持其在分析协作活动中的相关性。因此，该框架为从跨协作任务设置的带时间戳文本中研究团队合作的时间变化提供了一种透明且可迁移的方法。
英文摘要
Collaborative virtual reality (VR) environments make team communication observable as it unfolds, but conventional transcript analyses often summarize entire trials or divide them into fixed temporal windows. Such approaches can obscure changes in team communication and coordination over time. This article presents a computational framework for detecting and interpreting dynamic team-process phases from timestamped dialogue in a collaborative VR game. The framework uses late chunking to generate context-aware transcript representations, aggregates them into temporal chunks, and applies penalized Gaussian-kernel change-point detection to identify semantic transitions in team communication. After boundary detection, term frequency--inverse document frequency (TF-IDF), non-negative matrix factorization (NMF), and representative transcript segments provide structured evidence for phase interpretation. A locally deployed large language model (LLM) uses in-context learning to generate initial interpretations that are subsequently reviewed by humans. Independently recorded interaction logs are then aligned with the detected phases to examine corresponding task-action patterns. The evaluation compares representations, pooling strategies, segmentation methods, parameter settings, reviewed phase interpretations, and phase-aligned interaction profiles. The results show that the framework identifies coherent and interpretable phase structures while preserving traceability to the underlying transcript evidence. The correspondence between transcript-derived phases and interaction behavior further supports their relevance for analyzing collaborative activity. The framework therefore offers a transparent and transferable approach for studying temporal changes in teamwork from timestamped transcripts across collaborative task settings.
