Next Article in Journal
Computer-Aided Identification and Validation of Privacy Requirements
Next Article in Special Issue
Efficient Dynamic Integrity Verification for Big Data Supporting Users Revocability
Previous Article in Journal
The Potential of Three Computer-Based Communication Activities for Supporting Older Adult Independent Living
Previous Article in Special Issue
A Big Network Traffic Data Fusion Approach Based on Fisher and Deep Auto-Encoder
Open AccessArticle

Feature Engineering for Recognizing Adverse Drug Reactions from Twitter Posts

1
Department of Computer Science & Information Engineering, National Taitung University, Taitung 95092, Taiwan
2
Interdisciplinary Program of Green and Information Technology, National Taitung University, Taitung 95092, Taiwan
3
Graduate Institute of Biomedical Informatics, Taipei Medical University, Taipei 11031, Taiwan
4
School of Public Health and Community Medicine, UNSW Australia, Sydney, NSW 2052, Australia
5
Prince of Wales Clinical School, UNSW Australia, Sydney, NSW 2052, Australia
6
International Center for Health Information Technology, Taipei Medical University, Taipei 11031, Taiwan
*
Authors to whom correspondence should be addressed.
Academic Editors: Yong Yu and Yu Wang
Information 2016, 7(2), 27; https://doi.org/10.3390/info7020027
Received: 30 March 2016 / Revised: 17 May 2016 / Accepted: 18 May 2016 / Published: 25 May 2016
(This article belongs to the Special Issue Recent Advances of Big Data Technology)
Social media platforms are emerging digital communication channels that provide an easy way for common people to share their health and medication experiences online. With more people discussing their health information online publicly, social media platforms present a rich source of information for exploring adverse drug reactions (ADRs). ADRs are major public health problems that result in deaths and hospitalizations of millions of people. Unfortunately, not all ADRs are identified before a drug is made available in the market. In this study, an ADR event monitoring system is developed which can recognize ADR mentions from a tweet and classify its assertion. We explored several entity recognition features, feature conjunctions, and feature selection and analyzed their characteristics and impacts on the recognition of ADRs, which have never been studied previously. The results demonstrate that the entity recognition performance for ADR can achieve an F-score of 0.562 on the PSB Social Media Mining shared task dataset, which outperforms the partial-matching-based method by 0.122. After feature selection, the F-score can be further improved by 0.026. This novel technique of text mining utilizing shared online social media data will open an array of opportunities for researchers to explore various health related issues. View Full-Text
Keywords: adverse drug reactions; named entity recognition; word embedding; social media; natural language processing adverse drug reactions; named entity recognition; word embedding; social media; natural language processing
Show Figures

Figure 1

MDPI and ACS Style

Dai, H.-J.; Touray, M.; Jonnagaddala, J.; Syed-Abdul, S. Feature Engineering for Recognizing Adverse Drug Reactions from Twitter Posts. Information 2016, 7, 27.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop