@inproceedings{lv-etal-2025-tracking,
    title = "Tracking Life{'}s Ups and Downs: Mining Life Events from Social Media Posts for Mental Health Analysis",
    author = "Lv, Minghao  and
      Chen, Siyuan  and
      Jin, Haoan  and
      Yuan, Minghao  and
      Ju, Qianqian  and
      Peng, Yujia  and
      Zhu, Kenny Q.  and
      Wu, Mengyue",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.345/",
    pages = "6950--6965",
    ISBN = "979-8-89176-251-0",
    abstract = "Social media platforms possess considerable potential in the realm of exploring mental health. Previous research has indicated that major life events can greatly impact individuals' mental health. However, due to the complexity and ambiguity nature of life events, shedding its light on social media data is quite challenging. In this paper, we are dedicated to uncovering life events mentioned in posts on social media. We hereby provide a carefully-annotated social media event dataset, PsyEvent, which encompasses 12 major life event categories that are likely to occur in everyday life. This dataset is human-annotated under iterative procedure and boasts a high level of quality. Furthermore, by applying the life events extracted from posts to downstream tasks such as early risk detection of depression and suicide risk prediction, we have observed a considerable improvement in performance. This suggests that extracting life events from social media can be beneficial for the analysis of individuals' mental health."
}