An ensemble deep learning model for drug abuse detection in sparse twitter-sphere

Document Type

Conference Proceeding

Publication Date

8-21-2019

Abstract

As the problem of drug abuse intensifies in the U.S., many studies that primarily utilize social media data, such as postings on Twitter, to study drug abuse-related activities use machine learning as a powerful tool for text classification and filtering. However, given the wide range of topics of Twitter users, tweets related to drug abuse are rare in most of the datasets. This imbalanced data remains a major issue in building effective tweet classifiers, and is especially obvious for studies that include abuse-related slang terms. In this study, we approach this problem by designing an ensemble deep learning model that leverages both word-level and character-level features to classify abuse-related tweets. Experiments are reported on a Twitter dataset, where we can configure the percentages of the two classes (abuse vs. non abuse) to simulate the data imbalance with different amplitudes. Results show that our ensemble deep learning models exhibit better performance than ensembles of traditional machine learning models, especially on heavily imbalanced datasets.

Identifier

85071471488 (Scopus)

ISBN

[9781643680026]

Publication Title

Studies in Health Technology and Informatics

External Full Text Location

https://doi.org/10.3233/SHTI190204

e-ISSN

18798365

ISSN

09269630

PubMed ID

31437906

First Page

163

Last Page

167

Volume

264

Grant

CNS-1624503

Fund Ref

National Science Foundation

This document is currently not available here.

Share

COinS