# Spanish ADR corpus and SpanishDrugEffectBD database

SpanishADR is the first corpus of Spanish user comments extracted from social media annotated with drugs and adverse events. User comments were collected from the www.forumclinic.org website. The annotation was carried out using the GATE tool. 

In addition, we have automatically built the first database, SpanishDrugEffectBD, with information about drugs, their drug indications as well as their adverse drug reactions in Spanish.


In any work that uses the corpus and/or the database, please acknowledge the authors, as follows:

Isabel Segura-Bedmar, Paloma Martínez, Ricardo Revert, Julián Moreno-Schneider, (2015). Exploring Spanish Health Social Media for detecting drug effects, BMC Medical Informatics and Decision Making, Volume 15, Supplement S2, in press.

Isabel Segura-Bedmar, Ricardo Revert, Paloma Martínez, (2014). Detecting drugs and adverse events from Spanish social media streams. In Proceedings of the 5th International Louhi Workshop on Health Document Text Mining and Information Analysis (Louhi 2014).

Isabel Segura-Bedmar, Santiago de la Peña, Paloma Martínez, (2014). Extracting drug indications and adverse drug reactions from Spanish health social media. In Proceedings of the 2014 Workshop on Biomedical Natural Language (BioNLP 2014).


## Contact Info:

This dataset has been created by Hulat Group at University Carlos III of Madrid. 
Contact address: isegura@inf.uc3m.es or isegurabe@gmail.com