Details
| Originalsprache | Englisch |
|---|---|
| Aufsatznummer | e34492 |
| Seitenumfang | 13 |
| Fachzeitschrift | JMIR Medical Informatics |
| Jahrgang | 10 |
| Ausgabenummer | 2 |
| Publikationsstatus | Veröffentlicht - 1 Feb. 2022 |
Abstract
Background: Eating disorders affect an increasing number of people. Social networks provide information that can help. Objective: We aimed to find machine learning models capable of efficiently categorizing tweets about eating disorders domain. Methods: We collected tweets related to eating disorders, for 3 consecutive months. After preprocessing, a subset of 2000 tweets was labeled: (1) messages written by people suffering from eating disorders or not, (2) messages promoting suffering from eating disorders or not, (3) informative messages or not, and (4) scientific or nonscientific messages. Traditional machine learning and deep learning models were used to classify tweets. We evaluated accuracy, F1 score, and computational time for each model. Results: A total of 1,058,957 tweets related to eating disorders were collected. were obtained in the 4 categorizations, with The bidirectional encoder representations from transformer-based models had the best score among the machine learning and deep learning techniques applied to the 4 categorization tasks (F1 scores 71.1%-86.4%). Conclusions: Bidirectional encoder representations from transformer-based models have better performance, although their computational cost is significantly higher than those of traditional techniques, in classifying eating disorder-related tweets.
ASJC Scopus Sachgebiete
- Medizin (insg.)
- Gesundheitsinformatik
- Gesundheitsberufe (insg.)
- Gesundheits-Informationsmanagement
Ziele für nachhaltige Entwicklung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: JMIR Medical Informatics, Jahrgang 10, Nr. 2, e34492, 01.02.2022.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Traditional Machine Learning Models and Bidirectional Encoder Representations From Transformer (BERT)-Based Automatic Classification of Tweets About Eating Disorders
T2 - Algorithm Development and Validation Study
AU - Benítez-Andrades, Jose Alberto
AU - Alija-Perez, Jose Manuel
AU - Vidal, Maria Esther
AU - Pastor-Vargas, Rafael
AU - García-Ordas, María Teresa
PY - 2022/2/1
Y1 - 2022/2/1
N2 - Background: Eating disorders affect an increasing number of people. Social networks provide information that can help. Objective: We aimed to find machine learning models capable of efficiently categorizing tweets about eating disorders domain. Methods: We collected tweets related to eating disorders, for 3 consecutive months. After preprocessing, a subset of 2000 tweets was labeled: (1) messages written by people suffering from eating disorders or not, (2) messages promoting suffering from eating disorders or not, (3) informative messages or not, and (4) scientific or nonscientific messages. Traditional machine learning and deep learning models were used to classify tweets. We evaluated accuracy, F1 score, and computational time for each model. Results: A total of 1,058,957 tweets related to eating disorders were collected. were obtained in the 4 categorizations, with The bidirectional encoder representations from transformer-based models had the best score among the machine learning and deep learning techniques applied to the 4 categorization tasks (F1 scores 71.1%-86.4%). Conclusions: Bidirectional encoder representations from transformer-based models have better performance, although their computational cost is significantly higher than those of traditional techniques, in classifying eating disorder-related tweets.
AB - Background: Eating disorders affect an increasing number of people. Social networks provide information that can help. Objective: We aimed to find machine learning models capable of efficiently categorizing tweets about eating disorders domain. Methods: We collected tweets related to eating disorders, for 3 consecutive months. After preprocessing, a subset of 2000 tweets was labeled: (1) messages written by people suffering from eating disorders or not, (2) messages promoting suffering from eating disorders or not, (3) informative messages or not, and (4) scientific or nonscientific messages. Traditional machine learning and deep learning models were used to classify tweets. We evaluated accuracy, F1 score, and computational time for each model. Results: A total of 1,058,957 tweets related to eating disorders were collected. were obtained in the 4 categorizations, with The bidirectional encoder representations from transformer-based models had the best score among the machine learning and deep learning techniques applied to the 4 categorization tasks (F1 scores 71.1%-86.4%). Conclusions: Bidirectional encoder representations from transformer-based models have better performance, although their computational cost is significantly higher than those of traditional techniques, in classifying eating disorder-related tweets.
KW - BERT
KW - bidirectional encoder representations from transformer
KW - classification
KW - data
KW - deep learning
KW - diet
KW - disorder
KW - eating disorder
KW - machine learning
KW - mental health
KW - model
KW - natural language processing
KW - NLP
KW - nutrition
KW - performance
KW - social media
KW - Twitter
KW - weight
UR - http://www.scopus.com/inward/record.url?scp=85126462382&partnerID=8YFLogxK
U2 - 10.2196/34492
DO - 10.2196/34492
M3 - Article
AN - SCOPUS:85126462382
VL - 10
JO - JMIR Medical Informatics
JF - JMIR Medical Informatics
IS - 2
M1 - e34492
ER -