@InProceedings{jamil-EtAl:2017:CLPsych,
  author    = {Jamil, Zunaira  and  Inkpen, Diana  and  Buddhitha, Prasadith  and  White, Kenton},
  title     = {Monitoring Tweets for Depression to Detect At-risk Users},
  booktitle = {Proceedings of the Fourth Workshop on Computational Linguistics and Clinical Psychology --- From Linguistic Signal to Clinical Reality},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, BC},
  publisher = {Association for Computational Linguistics},
  pages     = {32--40},
  abstract  = {We propose an automated system that can identify at-risk users from their
	public social media activity, more specifically, from Twitter. The data that we
	collected is from the \#BellLetsTalk campaign, which is a wide-reaching,
	multi-year program designed to break the silence around mental illness and
	support mental health across Canada. To achieve our goal, we trained a
	user-level classifier that can detect at-risk users that achieves a reasonable
	precision and recall. We also trained a tweet-level classifier that predicts if
	a tweet indicates depression. This task was much more difficult due to the
	imbalanced data. In the dataset that we labeled, we came across 5% depression
	tweets and 95% non-depression tweets. To handle this class imbalance, we used
	undersampling methods. The resulting classifier had high recall, but low
	precision. Therefore, we only use this classifier to compute the estimated
	percentage of depressed tweets and to add this value as a feature for the
	user-level classifier.},
  url       = {http://www.aclweb.org/anthology/W17-3104}
}