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.
|Title of host publication||Proceedings of the 2nd Workshop on Noisy User-generated Text|
|Place of Publication||Osaka, Japan|
|Number of pages||8|
|Publication status||Published - 1 Jan 2016|
|Event||Proceedings of the 2nd Workshop on Noisy User-generated Text - Osaka, Japan, 11 Dec 2016|
Duration: 1 Jan 2016 → …
|Conference||Proceedings of the 2nd Workshop on Noisy User-generated Text|
|Period||1/01/16 → …|
Bibliographical note© Copyright of each paper stays with the respective authors (or their employers).
- School of Computing, Engineering & Maths - Professor of Computer Science
- Applied Data Analytics Research and Enterprise Group
- Centre for Digital Media Cultures