Abstract
BackgroundEating disorders affect an increasing number of people. Social networks provide information that can help.ObjectiveWe aimed to find machine learning models capable of efficiently categorizing tweets about eating disorders domain.MethodsWe 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.ResultsA 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%).ConclusionsBidirectional 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.
Highlights
BackgroundPhysical appearance is an essential element for people in this society
Our main objectives were to achieve accurate text classification in performing these 4 tasks, to compare the efficiency of text classification models using traditional machine learning techniques and those using novel techniques, such as pretrained bidirectional encoder representations from transformer (BERT)–based models, to determine which approach has the best combination of performance and computational cost and would be useful for future research
Accuracy for all bidirectional encoder representations from transformer–based models, except ALBERT and FlauBERT, exceeded 80%; applying bidirectional long short-term memory resulted in an accuracy of 78.7%
Summary
BackgroundPhysical appearance is an essential element for people in this society. many studies corroborate that moderate physical activity and proper nutrition help to maintain a healthy body [1] and mind [2], a large part of society continues to place more importance on physical appearance than on health. Trends have promoted a curvy physique [3,4] despite it being unhealthy, and most people associate having a slim body with being happy to have a slim body. These associations between physical appearance and happiness are the causes of illnesses such as eating disorders. Conclusions: Bidirectional encoder representations from transformer–based models have better performance, their computational cost is significantly higher than those of traditional techniques, in classifying eating disorder–related tweets
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
