@inproceedings{lolli-etal-2026-es4mll,
    title = "{ES}4{MLL} at {S}em{E}val-2026 Task 2: Set Attention Aggregation and Recurrent Temporal Modeling for Longitudinal Affect Prediction",
    author = "Lolli, Andrea  and
      Lunazzi, Chiara  and
      Coppola, Riccardo  and
      Giobergia, Flavio",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.102/",
    pages = "720--726",
    ISBN = "979-8-89176-414-9",
    abstract = "Longitudinal modelling of affect from text requires capturing both linguistic content and temporal emotional dynamics. SemEval-2026 Task 2 introduces a dataset of essays and feeling words annotated with self-reported valence and arousal scores. In this work, we propose a neural architecture that combines pretrained Transformer encoders with temporal sequence modelling to predict continuous valence and arousal over user-specific timelines. Individual texts are encoded using a Transformer-based language model and aggregated through attention-based pooling before being processed by recurrent layers to capture longitudinal dependencies. To adapt pretrained representations under limited data conditions, we explore parameter-efficient fine-tuning strategies. We make the code available at https://github.com/AndreaLolli2912/SemEval2026-EmoVA."
}