Analysis of Twitter data for postmarketing surveillance in pharmacovigilance

Julie Pain, Jessie Levacher, Adam Quinqunel, Anja Belz

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBNpeer-review


Postmarketing surveillance (PMS) has the vital aim to monitor effects of drugs af- ter release for use by the general pop- ulation, but suffers from under-reporting and limited coverage. Automatic meth- ods for detecting drug effect reports, es- pecially for social media, could vastly in- crease the scope of PMS. Very few auto- matic PMS methods are currently avail- able, in particular for the messy text types encountered on Twitter. In this paper we describe first results for developing PMS methods specifically for tweets. We de- scribe the corpus of 125,669 tweets we have created and annotated to train and test the tools. We find that generic tools per- form well for tweet-level language iden- tification and tweet-level sentiment anal- ysis (both 0.94 F1-Score). For detection of effect mentions we are able to achieve 0.87 F1-Score, while effect-level adverse- vs.-beneficial analysis proves harder with an F1-Score of 0.64. Among other things, our results indicate that MetaMap seman- tic types provide a very promising ba- sis for identifying drug effect mentions in tweets.
Original languageEnglish
Title of host publicationProceedings of the 2nd Workshop on Noisy User-generated Text
Place of PublicationOsaka, Japan
Number of pages8
Publication statusPublished - 1 Jan 2016
EventProceedings of the 2nd Workshop on Noisy User-generated Text - Osaka, Japan, 11 Dec 2016
Duration: 1 Jan 2016 → …


ConferenceProceedings of the 2nd Workshop on Noisy User-generated Text
Period1/01/16 → …

Bibliographical note

© Copyright of each paper stays with the respective authors (or their employers).

Fingerprint Dive into the research topics of 'Analysis of Twitter data for postmarketing surveillance in pharmacovigilance'. Together they form a unique fingerprint.

Cite this