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 ISBN

Abstract

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
Pages94-101
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 → …

Conference

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

Fingerprint

Semantics

Bibliographical note

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

Cite this

Pain, J., Levacher, J., Quinqunel, A., & Belz, A. (2016). Analysis of Twitter data for postmarketing surveillance in pharmacovigilance. In Proceedings of the 2nd Workshop on Noisy User-generated Text (pp. 94-101). Osaka, Japan.
Pain, Julie ; Levacher, Jessie ; Quinqunel, Adam ; Belz, Anja. / Analysis of Twitter data for postmarketing surveillance in pharmacovigilance. Proceedings of the 2nd Workshop on Noisy User-generated Text. Osaka, Japan, 2016. pp. 94-101
@inproceedings{54e8e268b64b46e4b55fa48a85bdf5d1,
title = "Analysis of Twitter data for postmarketing surveillance in pharmacovigilance",
abstract = "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.",
author = "Julie Pain and Jessie Levacher and Adam Quinqunel and Anja Belz",
note = "{\circledC} Copyright of each paper stays with the respective authors (or their employers).",
year = "2016",
month = "1",
day = "1",
language = "English",
isbn = "9784879747075",
pages = "94--101",
booktitle = "Proceedings of the 2nd Workshop on Noisy User-generated Text",

}

Pain, J, Levacher, J, Quinqunel, A & Belz, A 2016, Analysis of Twitter data for postmarketing surveillance in pharmacovigilance. in Proceedings of the 2nd Workshop on Noisy User-generated Text. Osaka, Japan, pp. 94-101, Proceedings of the 2nd Workshop on Noisy User-generated Text, 1/01/16.

Analysis of Twitter data for postmarketing surveillance in pharmacovigilance. / Pain, Julie; Levacher, Jessie; Quinqunel, Adam; Belz, Anja.

Proceedings of the 2nd Workshop on Noisy User-generated Text. Osaka, Japan, 2016. p. 94-101.

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

TY - GEN

T1 - Analysis of Twitter data for postmarketing surveillance in pharmacovigilance

AU - Pain, Julie

AU - Levacher, Jessie

AU - Quinqunel, Adam

AU - Belz, Anja

N1 - © Copyright of each paper stays with the respective authors (or their employers).

PY - 2016/1/1

Y1 - 2016/1/1

N2 - 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.

AB - 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.

M3 - Conference contribution with ISSN or ISBN

SN - 9784879747075

SP - 94

EP - 101

BT - Proceedings of the 2nd Workshop on Noisy User-generated Text

CY - Osaka, Japan

ER -

Pain J, Levacher J, Quinqunel A, Belz A. Analysis of Twitter data for postmarketing surveillance in pharmacovigilance. In Proceedings of the 2nd Workshop on Noisy User-generated Text. Osaka, Japan. 2016. p. 94-101