Overview of the CLPsych 2022 Shared Task: Capturing Moments of Change in Longitudinal User Posts
Overview of the CLPsych 2022 Shared Task on identifying 'moments of change' in individuals' longitudinal social-media posts. The task defined two change types, abrupt Switches and gradual Escalations in mood, and included a secondary suicide-risk assessment subtask, using temporally sensitive evaluation metrics designed for per-timeline prediction.
Publisher
Association for Computational Linguistics (CLPsych 2022 Workshop)
Published
1 Jul 2022
Added
today
Key Findings
- Defines 'moments of change' in longitudinal text as abrupt Switches and gradual Escalations in mood
- Includes a secondary suicide-risk assessment subtask building on the earlier CLPsych 2019 task
- Introduces temporally sensitive evaluation metrics for per-timeline mood-change prediction
Methodology Notes
Peer-reviewed shared-task overview, 8th CLPsych Workshop (NAACL 2022). Published July 2022; exact day not stated, so the day is set to 01. Substrate is social-media timelines, not chatbot conversation.
Sources
ACL Anthology (primary)
Archived snapshot (Wayback Machine) — preserved against link rot
Authors
Adam Tsakalidis, Jenny Chim, Iman Munire Bilal, Ayah Zirikly, Dana Atzil-Slonim, Federico Nanni, Philip Resnik, Manas Gaur, Kaushik Roy, Becky Inkster, Jeff Leintz, Maria Liakata
Tags
Cite This
APA
Adam Tsakalidis et al. (2022). Overview of the CLPsych 2022 Shared Task: Capturing Moments of Change in Longitudinal User Posts. Association for Computational Linguistics (CLPsych 2022 Workshop). https://aclanthology.org/2022.clpsych-1.16/