基于大语言模型的情感个人信息学的范围界定:综述、反思与未来方向
Scoping the Landscape of Large Language Model-based Affective Personal Informatics: Review, Reflection, Future Direction
AI总结:
本文针对基于大语言模型的情感个人信息学,分析45篇相关论文,指出现有系统的缺陷,提出构建端到端多模态、低负担、高包容性系统的未来方向。
摘要:
情感个人信息学(PI)涉及对个人数据进行捕获、跟踪、分析与反思,以支持情绪自我觉察与心理健康。近期大语言模型(LLM)的进展正在重塑情感个人信息学,但目前仍缺乏针对基于LLM的情感个人信息学系统的全面综述。为填补这一空白,我们系统分析了2020年1月至2026年6月发表在四大计算机与健康数据库的45篇论文,考察其宏观趋势、系统分类与研究方法。我们的综合分析显示,该领域存在对多阶段、以文本为中心的流程的过度依赖、以主动的屏幕交互为主,以及实证评估中严重偏向年轻大学校园群体的人口统计学偏差。基于这些发现,我们批判性反思了现有架构与方法学的缺陷,并勾勒出构建端到端多模态、低负担、高包容性情感个人信息学系统的可行未来方向。
英文摘要:
Affective personal informatics (PI) involves capturing, tracking, analyzing, and reflecting on personal data to support emotional self-awareness and mental well-being. Recent advances in large language models (LLMs) are reshaping affective PI, yet a comprehensive survey of LLM-based affective PI systems is lacking. To bridge this gap, we systematically analyzed 45 papers published between January 2020 and June 2026 across four major computing and health databases, examining their macro trends, system taxonomies, and research methodologies. Our synthesis reveals an overreliance on multi-stage, text-centric pipelines, a predominance of active, screen-bound interactions, and a severe demographic skew toward young, university-campus-based cohorts in empirical evaluations. Based on these findings, we critically reflect on prevailing architectural and methodological shortcomings and outline actionable future directions for building end-to-end multimodal, low-burden, and inclusive affective PI systems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。