@inproceedings{tee-2026-khaleesiyali,
    title = "Khaleesiyali at {S}em{E}val-2026 Task 2: Lexicon-Augmented {R}o{BERT}a for Valence{--}Arousal Regression on Ecological Essays",
    author = "Tee, Eleale",
    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-1.75/",
    pages = "522--527",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents a lexicon-augmentedRoBERTa system for the SemEval-2026 Task2 valence{--}arousal regression challenge. Themodel integrates deep contextual embeddingswith a 6-dimensional feature vector derivedfrom the NRC VAD lexicon, achieving a hightoken coverage rate of 72.05{\%}. Under officialuser-aware evaluation, the system reached acompetitive average composite correlation of0.547, significantly outperforming the ridgeregressionbaseline. The system demonstratedparticular robustness in valence (r = 0.656)and achieved strong generalization to unseenusers (rarousal = 0.519). These findings indicatethat lightweight lexicon-based statisticsprovide valuable complementary cues for longitudinalemotion modeling in modern transformerarchitectures."
}