Shared-Task 1: Empathy Detection and Emotion Classification
We foresee a fourth run of this shared task using a new, unpublished extension of the dataset already used last year. This task is focused on modeling empathetic and emotional reactions to news articles. This task is both multi-level and multi-modal: data is available at the person, essay, dialog, and dialog-turn levels and includes formal (news articles) and informal text (essays and dialogs), self-report data (e.g., personality and distress), and third-party annotations (empathy and emotion). This year’s task adds conversations between humans and LLM-based virtual agents which occur immediately after reading and reacting to the news articles. It also introduces partner empathy perception for both human-human and human-agent conversations. Participants will be encouraged to explore the multi-level and multi-modal nature of this data.
Shared-task 1 can be found on codalab.
Shared-Task 2: Explainability of Cross-lingual Emotion Detection
The is the first shared task on explainability of cross-lingual emotion detection. With recent developments of large, opaque, black box systems behind APIs, it is becoming harder and harder to understand the rationales behind decisions made by these models for subjective tasks. To look further into one such direction, we aim to better understand the decision making of emotion detection systems and assess if they are capable of understanding the triggers of emotion in social media data. For more information, please visit EXALT.
Shared-task 2 can be found on codalab