AFourP at SemEval-2026 Task 2: Predicting Variation in Emotional Valence and Arousal over Time from Ecological Essays

Shrika Thota, Lakshmi Priya Swaminatha Rao, Shivaanee Sk, Thirumurugan Ra, Vishal Muralidharan, Dhannya Santhakumari Madhavan


Abstract
We describe our submission to SemEval-2026 Task 2 (Subtask 1), which asks systems to predict continuous Valence and Arousal scores from ecological diary texts. We fine-tune RoBERTa-base with a single linear regression head, treating each essay independently. Our system scores rcomposite of .679 (Valence) and .466 (Arousal) on the official test set, placing 4th on the Subtask 1 leaderboard.
Anthology ID:
2026.semeval-1.217
Volume:
Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
Month:
July
Year:
2026
Address:
San Diego, California, USA
Editors:
Ekaterina Kochmar, Debanjan Ghosh, Kai North, Mamoru Komachi
Venues:
SemEval | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1695–1700
Language:
URL:
https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.217/
DOI:
Bibkey:
Cite (ACL):
Shrika Thota, Lakshmi Priya Swaminatha Rao, Shivaanee Sk, Thirumurugan Ra, Vishal Muralidharan, and Dhannya Santhakumari Madhavan. 2026. AFourP at SemEval-2026 Task 2: Predicting Variation in Emotional Valence and Arousal over Time from Ecological Essays. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1695–1700, San Diego, California, USA. Association for Computational Linguistics.
Cite (Informal):
AFourP at SemEval-2026 Task 2: Predicting Variation in Emotional Valence and Arousal over Time from Ecological Essays (Thota et al., SemEval 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.217.pdf