An Ensemble Method for Binary Classification of Adverse Drug Reactions from Social Media
نویسندگان
چکیده
This paper describes the system we developed for PSB 2016 social media mining shared task on binary classification of adverse drug reactions (ADRs). The task focuses on automatic classification of ADR assertive user posts. We propose a weighted average ensemble of four classifiers: (1) a concept-matching classifier based on ADR lexicon; (2) a maximum entropy (ME) classifier with word-level n-gram features and TFIDF weighting scheme; (3) a ME classifier based on word-level n-grams using naive Bayes (NB) log-count ratios as feature values; and (4) a ME classifier with word embedding features. Our system is ranked 2nd with ADR class F-score of 41.82%.
منابع مشابه
Detecting Signals in Noisy Data - Can Ensemble Classifiers Help Identify Adverse Drug Reaction in Tweets?
In this paper, we describe our system for detecting adverse reactions from tweets, a task organized as part of Pacific Symposium of Biocomputing Social Media Mining Shared Task. The shared task primarily involves a binary classification of the tweets, whether they contain description of adverse drug reaction or not. We propose an ensemble machine learning classifier to tackle the unbalanced dis...
متن کاملBinary Classification of Twitter Posts for Adverse Drug Reactions
Nowadays, social media is often being used by users to create public messages or posts that are related to their health. With the increasing number of social media usage, a trend has been observed of users creating posts related to adverse drug reactions. Mining social media data for these information can be used for pharmacological post-marketing surveillance and monitoring. We developed a bin...
متن کاملA High-Performance Model based on Ensembles for Twitter Sentiment Classification
Background and Objectives: Twitter Sentiment Classification is one of the most popular fields in information retrieval and text mining. Millions of people of the world intensity use social networks like Twitter. It supports users to publish tweets to tell what they are thinking about topics. There are numerous web sites built on the Internet presenting Twitter. The user can enter a sentiment ta...
متن کاملSocial Media Mining Shared Task Workshop
Social media has evolved into a crucial resource for obtaining large volumes of real-time information. The promise of social media has been realized by the public health domain, and recent research has addressed some important challenges in that domain by utilizing social media data. Tasks such as monitoring flu trends, viral disease outbreaks, medication abuse, and adverse drug reactions are s...
متن کاملMedication Errors Associated With Adverse Drug Reactions in Iran (2015-2017): A P-Method Approach
Medication errors are the second most common cause of adverse patient safety incidents and the single most common preventable cause of adverse events in medical practice. Given the high human fatalities and financial burden of medication errors for healthcare systems worldwide, reducing their occurrence is a global priority. Therefore, appropriate policies to reduce medication errors, using nat...
متن کامل