用生成式模型识别青少年危机对话中的动态关键词，突破固定分类局限。
Keyphrase Generative Representation of Youth Crisis Conversations Beyond Static Taxonomies
- 设计约束型大模型生成对话特定关键词，替代固定标签
- 新分类体系准确率达0.96，81%关键词准确反映内容
- 可发现移民、照护负担等文化相关议题，适合心理干预系统
危机响应人员每年需快速评估数以万计的青少年短信对话，以识别心理健康问题并提供支持。然而，青少年困境表达日益使用动态且情境相关的语言，难以纳入固定标签体系。本研究分析了703,975条2018-2023年去标识化的Kids Help Phone对话，将原有19类议题分类扩展为39类分层结构。提出关键短语生成表示（KGR），一种约束型大语言模型，用于生成简洁、对话特定的关键短语。在129条对话和387份专家标注中评估显示，新分类体系达成专家共识可靠性（准确率0.96），专家评审认为81%的关键词准确反映内容，74%提升表达清晰度。KGR揭示了原固定分类中缺失的身份关联主题，如移民问题与照护者负担，并支撑主题检索流程，使准确率从0.25提升至0.70（+0.45），优于人工分析。该方法标志着向混合、可解释的生成式表征转变，推动危机响应超越静态分类，捕捉青年困境的新兴与文化根植模式。
原文摘要 · Abstract (English)
Crisis Responders (CRs) rapidly assess thousands of youth SMS conversations each year to identify mental health concerns and guide support. Yet youth distress is increasingly expressed through evolving and context-specific language that often does not fit fixed-label taxonomies. This work analyzed 703,975 de-identified Kids Help Phone conversations (2018-2023) and expanded KHP's 19-label issue taxonomy into a 39-label hierarchical schema. We then introduce Keyphrase Generative Representation (KGR), a constrained LLM generating concise, conversation-specific keyphrases, evaluated across 129 conversations and 387 expert annotations. The expanded taxonomy achieved expert consensus reliability, with an accuracy of 0.96, and expert review found that 81% of keyphrases accurately reflected content and 74% improved clarity. KGR surfaced identity-linked themes absent from the fixed taxonomy, including immigration problems and caregiver burden, and supported a topic-retrieval workflow that increased accuracy from 0.25 to 0.70 (+0.45) over the manual analyst process. KGR marks a shift toward hybrid, interpretable generative representations that extend crisis response beyond static taxonomies to surface emerging and culturally grounded patterns of youth distress.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。