@inproceedings{gamoran-etal-2021-using,
    title = "Using Psychologically-Informed Priors for Suicide Prediction in the {CLP}sych 2021 Shared Task",
    author = "Gamoran, Avi  and
      Kaplan, Yonatan  and
      Simchon, Almog  and
      Gilead, Michael",
    editor = "Goharian, Nazli  and
      Resnik, Philip  and
      Yates, Andrew  and
      Ireland, Molly  and
      Niederhoffer, Kate  and
      Resnik, Rebecca",
    booktitle = "Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.clpsych-1.12/",
    doi = "10.18653/v1/2021.clpsych-1.12",
    pages = "103--109",
    abstract = "This paper describes our approach to the CLPsych 2021 Shared Task, in which we aimed to predict suicide attempts based on Twitter feed data. We addressed this challenge by emphasizing reliance on prior domain knowledge. We engineered novel theory-driven features, and integrated prior knowledge with empirical evidence in a principled manner using Bayesian modeling. While this theory-guided approach increases bias and lowers accuracy on the training set, it was successful in preventing over-fitting. The models provided reasonable classification accuracy on unseen test data (0.68{\ensuremath{<}}=AUC{\ensuremath{<}}= 0.84). Our approach may be particularly useful in prediction tasks trained on a relatively small data set."
}