Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.
Who will be affected?
Readers: No access to all 28 journals. We recommend accessing our articles via PubMed Central
Authors: No access to the submission form or your user account.
Reviewers: No access to your user account. Please download manuscripts you are reviewing for offline reading before Wednesday, July 01, 2020 at 7:00 PM.
Editors: No access to your user account to assign reviewers or make decisions.
Copyeditors: No access to user account. Please download manuscripts you are copyediting before Wednesday, July 01, 2020 at 7:00 PM.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Automated Classification of Lay Health Articles Using Natural Language Processing: A Case Study on Pregnancy Health and Postpartum Depression
Braja Gopal Patra;
Zhaoyi Sun;
Zilin Cheng;
Praneet Kasi Reddy Jagadeesh Kumar;
Abdullah Altammami;
Yiyang Liu;
Rochelle Joly;
Caroline Jedlicka;
Diana Delgado;
Jyotishman Pathak;
Yifan Peng;
Yiye Zhang
ABSTRACT
Background:
Creating credible and engaging health communication materials is knowledge- and labor-intensive.
Objective:
We propose a low-cost alternative by classifying lay health articles by relevance and topic using natural language processing (NLP).
Methods:
With postpartum depression as a case study, we conducted a manual review of online lay articles to classify articles on their relevance to pregnancy and topics. To scale the classification process on relevance and topics, we built models using Bidirectional Encoder Representations from Transformers (BERT), Generative Pre-trained Transformer model (ChatGPT), and Random Forest.
Results:
The gold standard corpus included 392 articles. A BERT-based model performed best (F1= 0.974) in an end-to-end classification of relevance and topics. In a two-step approach, given articles already classified as related to pregnancy, ChatGPT was best (F1 = 0.972) in classifying topics.
Conclusions:
With NLP, we may repurpose lay reading materials as low-cost and easily accessible health education and communication sources.
Citation
Please cite as:
Patra BG, Sun Z, Cheng Z, Reddy Jagadeesh Kumar PK, Altammami A, Liu Y, Joly R, Jedlicka C, Delgado D, Pathak J, Peng Y, Zhang Y
Automated Classification of Lay Health Articles Using Natural Language Processing: A Case Study on Pregnancy Health and Postpartum Depression