An ensemble method for extracting adverse drug events from social media

作者：

Highlights：

• We propose a relation extraction system to distinguish between adverse drug events (ADEs) and non-ADEs on social media.

• We develop a feature-based method, investigate the effectiveness of feature selection, and analyze the contributions of different features.

• We investigate whether kernel-based methods can effectively extract ADEs from social media.

• We propose several classifier ensembles to further enhance ADE extraction capabilities.

摘要

•We propose a relation extraction system to distinguish between adverse drug events (ADEs) and non-ADEs on social media.•We develop a feature-based method, investigate the effectiveness of feature selection, and analyze the contributions of different features.•We investigate whether kernel-based methods can effectively extract ADEs from social media.•We propose several classifier ensembles to further enhance ADE extraction capabilities.

论文关键词：Relation extraction,Feature-based approach,Feature selection,Kernel-based approaches,Social media,Adverse drug event extraction

论文评审过程：Received 7 October 2015, Revised 20 May 2016, Accepted 27 May 2016, Available online 6 June 2016, Version of Record 18 June 2016.

论文官网地址：https://doi.org/10.1016/j.artmed.2016.05.004