@article{pananookooln-etal-2023-comparing,
    title = "Comparing Selective Masking Methods for Depression Detection in Social Media",
    author = "Pananookooln, Chanapa  and
      Akaranee, Jakrapop  and
      Silpasuwanchai, Chaklam",
    journal = "Computational Linguistics",
    month = sep,
    year = "2023",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2023.cl-3.1",
    doi = "10.1162/coli_a_00479",
    pages = "525--553",
    abstract = "Identifying those at risk for depression is a crucial issue and social media provides an excellent platform for examining the linguistic patterns of depressed individuals. A significant challenge in depression classification problems is ensuring that prediction models are not overly dependent on topic keywords (i.e., depression keywords) such that it fails to predict when such keywords are unavailable. One promising approach is masking{---}that is, by selectively masking various words and asking the model to predict the masked words, the model is forced to learn the inherent language patterns of depression. This study evaluates seven masking techniques. Moreover, predicting the masked words during the pre-training or fine-tuning phase was also examined. Last, six class imbalanced ratios were compared to determine the robustness of masked words selection methods. Key findings demonstrate that selective masking outperforms random masking in terms of F1-score. The most accurate and robust models are identified. Our research also indicates that reconstructing the masked words during the pre-training phase is more advantageous than during the fine-tuning phase. Further discussion and implications are discussed. This is the first study to comprehensively compare masked words selection methods, which has broad implications for the field of depression classification and general NLP. Our code can be found at: https://github.com/chanapapan/Depression-Detection.",
}