Extended trigger terms for extracting Adverse Drug Reactions in social media texts

Rami Naim Mohammad Yousef, Sabrina Tiun, Nazlia Omar

Research output: Contribution to journalArticle

Abstract

Adverse Drug Reaction (ADR) is a disorder caused by taking medications. Studies have addressed extracting ADRs from social networks where users express their opinion regarding a specific medication. Extracting entities mainly depends on specific terms called trigger terms that may occur before or after ADRs. However, these terms should be extended, especially when examining multiple representation of N-gram. This study aims to propose an extension of trigger terms based on the multiple representation of N-gram. Two benchmark datasets are used in the experiments and three classifiers, namely, support vector machine, Naïve Bayes and linear regression, are trained on the proposed extension. Furthermore, two document representations have been utilized including Term Frequency Inverse Document Frequency (TFIDF) and Count Vector (CV). Results show that the proposed extended trigger terms outperform the baseline by achieving 88% and 69% of F1-scores for the first and second datasets, respectively. This finding implies the effectiveness of the proposed extended trigger terms in terms of detecting new ADRs.

Original languageEnglish
Pages (from-to)873-879
Number of pages7
JournalJournal of Computer Science
Volume15
Issue number6
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Linear regression
Support vector machines
Classifiers
Experiments

Keywords

  • Adverse Drug Reaction
  • Feature extraction
  • Linear regression
  • Support Vector Machine
  • Trigger terms

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Extended trigger terms for extracting Adverse Drug Reactions in social media texts. / Yousef, Rami Naim Mohammad; Tiun, Sabrina; Omar, Nazlia.

In: Journal of Computer Science, Vol. 15, No. 6, 01.01.2019, p. 873-879.

Research output: Contribution to journalArticle

@article{259843453e7941cca63eaa86f48e51fa,
title = "Extended trigger terms for extracting Adverse Drug Reactions in social media texts",
abstract = "Adverse Drug Reaction (ADR) is a disorder caused by taking medications. Studies have addressed extracting ADRs from social networks where users express their opinion regarding a specific medication. Extracting entities mainly depends on specific terms called trigger terms that may occur before or after ADRs. However, these terms should be extended, especially when examining multiple representation of N-gram. This study aims to propose an extension of trigger terms based on the multiple representation of N-gram. Two benchmark datasets are used in the experiments and three classifiers, namely, support vector machine, Na{\"i}ve Bayes and linear regression, are trained on the proposed extension. Furthermore, two document representations have been utilized including Term Frequency Inverse Document Frequency (TFIDF) and Count Vector (CV). Results show that the proposed extended trigger terms outperform the baseline by achieving 88{\%} and 69{\%} of F1-scores for the first and second datasets, respectively. This finding implies the effectiveness of the proposed extended trigger terms in terms of detecting new ADRs.",
keywords = "Adverse Drug Reaction, Feature extraction, Linear regression, Support Vector Machine, Trigger terms",
author = "Yousef, {Rami Naim Mohammad} and Sabrina Tiun and Nazlia Omar",
year = "2019",
month = "1",
day = "1",
doi = "10.3844/jcssp.2019.873.879",
language = "English",
volume = "15",
pages = "873--879",
journal = "Journal of Computer Science",
issn = "1549-3636",
publisher = "Science Publications",
number = "6",

}

TY - JOUR

T1 - Extended trigger terms for extracting Adverse Drug Reactions in social media texts

AU - Yousef, Rami Naim Mohammad

AU - Tiun, Sabrina

AU - Omar, Nazlia

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Adverse Drug Reaction (ADR) is a disorder caused by taking medications. Studies have addressed extracting ADRs from social networks where users express their opinion regarding a specific medication. Extracting entities mainly depends on specific terms called trigger terms that may occur before or after ADRs. However, these terms should be extended, especially when examining multiple representation of N-gram. This study aims to propose an extension of trigger terms based on the multiple representation of N-gram. Two benchmark datasets are used in the experiments and three classifiers, namely, support vector machine, Naïve Bayes and linear regression, are trained on the proposed extension. Furthermore, two document representations have been utilized including Term Frequency Inverse Document Frequency (TFIDF) and Count Vector (CV). Results show that the proposed extended trigger terms outperform the baseline by achieving 88% and 69% of F1-scores for the first and second datasets, respectively. This finding implies the effectiveness of the proposed extended trigger terms in terms of detecting new ADRs.

AB - Adverse Drug Reaction (ADR) is a disorder caused by taking medications. Studies have addressed extracting ADRs from social networks where users express their opinion regarding a specific medication. Extracting entities mainly depends on specific terms called trigger terms that may occur before or after ADRs. However, these terms should be extended, especially when examining multiple representation of N-gram. This study aims to propose an extension of trigger terms based on the multiple representation of N-gram. Two benchmark datasets are used in the experiments and three classifiers, namely, support vector machine, Naïve Bayes and linear regression, are trained on the proposed extension. Furthermore, two document representations have been utilized including Term Frequency Inverse Document Frequency (TFIDF) and Count Vector (CV). Results show that the proposed extended trigger terms outperform the baseline by achieving 88% and 69% of F1-scores for the first and second datasets, respectively. This finding implies the effectiveness of the proposed extended trigger terms in terms of detecting new ADRs.

KW - Adverse Drug Reaction

KW - Feature extraction

KW - Linear regression

KW - Support Vector Machine

KW - Trigger terms

UR - http://www.scopus.com/inward/record.url?scp=85071375310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071375310&partnerID=8YFLogxK

U2 - 10.3844/jcssp.2019.873.879

DO - 10.3844/jcssp.2019.873.879

M3 - Article

AN - SCOPUS:85071375310

VL - 15

SP - 873

EP - 879

JO - Journal of Computer Science

JF - Journal of Computer Science

SN - 1549-3636

IS - 6

ER -