Understanding what leads to emotions during large-scale crises is important as it can provide groundings for expressed emotions and subsequently improve the understanding of ongoing disasters. Recent approaches trained supervised models to both detect emotions and explain emotion triggers (events and appraisals) via abstractive summarization. However, obtaining timely and qualitative abstractive summaries is expensive and extremely time-consuming, requiring highly-trained expert annotators. In time-sensitive, high-stake contexts, this can block necessary responses. We instead pursue unsupervised systems that extract triggers from text. First, we introduce CovidET-EXT, augmenting (Zhan et al. 2022)'s abstractive dataset (in the context of the COVID-19 crisis) with extractive triggers. Second, we develop new unsupervised learning models that can jointly detect emotions and summarize their triggers. Our best approach, entitled Emotion-Aware Pagerank, incorporates emotion information from external sources combined with a language understanding module, and outperforms strong baselines. We release our data and code at https://github.com/tsosea2/CovidET-EXT.

翻译：理解大规模危机期间情绪产生的原因至关重要，因为它能为表达的情绪提供依据，进而提升对持续灾难的理解。近期方法通过抽象式摘要训练监督模型来同时检测情绪并解释情绪触发点（事件与评估）。然而，获取及时且高质量的抽象式摘要成本高昂且极为耗时，需要经过高度训练的专业标注员。在时间敏感、高风险的情境下，这会阻碍必要的响应。我们转而研究从文本中提取触发点的无监督系统。首先，我们引入CovidET-EXT，通过添加抽取式触发点来扩充（Zhan等，2022）在COVID-19危机情境下的抽象式数据集。其次，我们开发了能够联合检测情绪并总结其触发点的全新无监督学习模型。我们最佳方法——命名为情绪感知PageRank——融合了来自外部源的情绪信息与语言理解模块，并优于强基线模型。我们在https://github.com/tsosea2/CovidET-EXT 公开了数据和代码。