首个跨年期自然工作场景员工情绪数据集，支持长期追踪与团队关系分析。
WELD: The First Naturalistic Long-Period Small-Team Workplace Emotion Dataset for Ubiquitous Affective Computing
- 采集30个月自然工作环境下的面部表情概率向量，被动无侵入式监测
- 发现情绪波动中19.3%属个体差异，29.8%受月度季节性影响，揭示预测上限
- 揭露通用情绪识别模型对亚洲中性脸误判严重，助力公平性审计
情感计算在实验室环境已发展成熟，但此前尚无数据集同时满足：(i) 持续数月至数年、(ii) 自然工作场景、(iii) 稳定小团队结构、(iv) 可通过机构审查的全被动感知协议。我们提出WELD，首个满足四者的数据集。包含中国某软件公司49名员工在30.1个月（2021年11月–2024年5月）内采集的733,780个帧级七分类面部表情概率向量，是目前最长的自然场景情绪语料库，也是唯一支持同一批被试进行个体纵向与团队关系分析的多年度数据集。数据按四级访问权限开放，仅聚合概率可公开下载。通过复现三个已有现象（周末愉悦度提升+43.1%；每日13:00情绪低谷；上海2022年封控效应d=-0.40）验证其有效性，并报告四项新发现：(1) 方差分解显示日均情绪方差中19.3%来自个体差异，29.8%来自月度季节性，为未来预测模型设定了量化上限；(2) 隐马尔可夫分解揭示六种情绪状态，负向状态持续时间显著更长（16–18天对比3天）；(3) 去除一人预测离职的AUC=0.79，但Cox一致性指数仅为0.52，暴露仅报告AUC会因缺乏生存分析基线导致误导；(4) 发现通用情绪识别模型对亚洲中性脸错误高估愤怒概率（0.194对比西方先验~0.05），使WELD成为情绪识别公平性审计的重要资源。该数据集的复杂系统分析详见配套预印本（arXiv:2510.16046）。
原文摘要 · Abstract (English)
Affective computing has matured rapidly in laboratory settings, yet no prior dataset combines (i) months-to-years of duration, (ii) a naturalistic workplace context, (iii) a stable small-team social structure, and (iv) a fully passive sensing protocol that survives institutional review. We introduce WELD, the first dataset to satisfy all four. WELD comprises 733,780 per-frame seven-class facial-expression probability vectors from 49 employees of a Chinese software company over 30.1 months (Nov 2021 - May 2024) -- the longest naturalistic in-the-wild emotion corpus and the only multi-year corpus supporting both within-individual longitudinal and within-team relational analyses on the same subjects. Data are released under a four-tier access model with only aggregated probabilities publicly downloadable. We validate the corpus by replicating three established phenomena (+43.1% weekend valence boost; 13:00-trough diurnal cycle; Shanghai 2022 lockdown effect d=-0.40), and report four novel findings: (1) variance decomposition attributes 19.3% of daily-valence variance to between-person differences and 29.8% to month seasonality -- a quantitative ceiling for future predictive models; (2) Hidden Markov decomposition reveals six emotional regimes with asymmetric negative-state dwell times (16-18 d vs 3 d); (3) leave-one-person-out turnover prediction reaches AUC=0.79 yet a Cox concordance index of only 0.52, exposing a metric-trap when AUC is reported without survival-aware baselines; (4) the corpus reveals systematic over-prediction of "angry" by an off-the-shelf FER model on neutral Asian faces (0.194 vs ~0.05 Western priors), making WELD valuable for FER fairness audits. A complex-systems analysis of the corpus appears as a companion preprint (arXiv:2510.16046).
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。