Will be updated soon with the code. Unfortunately, we are not permitted to release the datasets, but they will soon appear in a Codalab competition where people can try their models' performance. The model weights have been uploaded.

The relevant paper can be found here. Below you can find the .bib entry for the paper.

@InProceedings{W18-5910,
  author = 	"Xherija, Orest",
  title = 	"Classification of Medication-Related Tweets Using Stacked Bidirectional LSTMs with Context-Aware Attention",
  booktitle = 	"Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop and Shared Task",
  year = 	"2018",
  publisher = 	"Association for Computational Linguistics",
  pages = 	"38--42",
  location = 	"Brussels, Belgium",
  url = 	"http://aclweb.org/anthology/W18-5910"
}

Distinguish tweets that mention names of medications or dietary supplements from those that do not. The definitions of drugs and dietary supplements is taken from the FDA.

Distinguish tweets that mention personal medication intake, possible medication intake or no intake.

Distinguish tweets that contain mentions of adverse drug reaction those that do not.

Distinguish tweets that mention behavior related to influenza vaccination from those that do not. Data annotators labeled tweets to answer the binary question Does this message indicate that someone received, or intended to receive, a flu vaccine?