@inproceedings{wang-etal-2025-qmul,
    title = "{QMUL} at {S}em{E}val-2025 Task 11: Explicit Emotion Detection with {E}mo{L}ex, Feature Engineering, and Threshold-Optimized Multi-Label Classification",
    author = "Wang, Angeline  and
      Gupta, Aditya  and
      Roman, Iran  and
      Zubiaga, Arkaitz",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.128/",
    pages = "959--964",
    ISBN = "979-8-89176-273-2",
    abstract = "SemEval 2025 Task 11 Track A explores the detection of multiple emotions in text samples. Our best model combined BERT (fine-tuned on an emotion dataset) predictions and engineered features with EmoLex words appended. Together, these were used as input to train a multi-layer perceptron. This achieved a final test set Macro F1 score of 0.56. Compared to only using BERT predictions, our system improves performance by 43.6{\%}."
}