@inproceedings{radulescu-2026-fnlp412,
    title = "{FNLP}412@{EEUCA} 2026: Understanding Toxic Behavioral Intent in Gaming Chat Logs using Transfer Learning and Synthetic Data Augmentation",
    author = "Radulescu, Mihai Radu",
    editor = {H{\"u}rriyeto{\u{g}}lu, Ali  and
      Thapa, Surendrabikram  and
      Tanev, Hristo  and
      Adhikari, Surabhi},
    booktitle = "Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications ({EEUCA} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-naloma/2026.eeuca-1.10/",
    doi = "10.18653/v1/2026.eeuca-1.10",
    pages = "96--103",
    ISBN = "979-8-89176-402-6",
    abstract = "Our paper explores several machine learning methods for detecting toxic language in gaming-related chat utterances. We start with the GameTox dataset, perform some data preprocessing and augment the minority classes with LLM-generated synthetic data. We then set a baseline using a classic Logistic Regression model and continue to explore severalapproaches to surpassing it, by leveraging the leading multilingual transformer models (XLM-RoBERTa and DeBERTa-V3) to classify our test data. We achieve a top result of 0.6725 Macro-F1 (2nd place on shared task leaderboard) using a MDeBERTa-V3 model which we pretrained on the Jigsaw dataset for 1 epoch and then fine-tuned on our GameTox data for 5 epochs."
}