@InProceedings{bell-EtAl:2018:LOUHI,
  author    = {Bell, Dane  and  Laparra, Egoitz  and  Kousik, Aditya  and  Ishihara, Terron  and  Surdeanu, Mihai  and  Kobourov, Stephen},
  title     = {Detecting Diabetes Risk from Social Media Activity},
  booktitle = {Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis},
  month     = {October},
  year      = {2018},
  address   = {Brussels, Belgium},
  publisher = {Association for Computational Linguistics},
  pages     = {1--11},
  abstract  = {This work is the first to explore the detection of individuals' risk of type 2 diabetes mellitus (T2DM) directly from their social media (Twitter) activity. Our approach extends a deep learning architecture with several contributions: following previous observations that language use differs by gender, it captures and uses gender information through domain adaptation; it captures recency of posts under the hypothesis that more recent posts are more representative of an individual’s current risk status; and, lastly, it demonstrates that in this scenario where activity factors are sparsely represented in the data, a bag-of-word neural network model using custom dictionaries of food and activity words performs better than other neural sequence models. Our best model, which incorporates all these contributions, achieves a risk-detection F1 of 41.9, considerably higher than the baseline rate (36.9).},
  url       = {http://www.aclweb.org/anthology/W18-5601}
}