A computer science and engineering team from the Carlos III Universidad in Madrid (UC3M) found a way to convert forum posts and social-media comments into adverse drug reaction reports.

The group used natural language processing to “translate social media descriptions of experiences with medicines into structured, codified data that can be used in comparative studies to identify patterns and trends,” In-Pharma Technologist reported Wednesday.

The prototype software analyzes big swaths of online data for mentions of drugs, illnesses and adverse effects, the news outlet wrote. The system also recognizes drugs by both their generic and branded names as well as their active ingredients.

A paper on the subject has been submitted for publication to the journal BMC Medical Informatics and Decision Making.