Eating disorders (EDs) are among the most pressing issues in public health, affecting individuals across various age and social groups. With the rapid growth of digitalization and the widespread use of social media, there emerges a promising opportunity to detect signs of EDs through the analysis of user-generated textual content. This study presents a comprehensive approach that combines natural language processing (NLP) techniques, Word2Vec vectorization, and a neural network architecture for binary text classification. The model aims to identify whether a post is related to disordered eating behavior. Additionally, the study incorporates social network analysis to examine the structure of interactions among users who publish related content. Experimental results demonstrate high precision (0.87), recall (0.84), and overall performance, confirming the model’s practical applicability. The network analysis revealed clusters of users with ED-related content, suggesting the presence of a "social contagion" effect – here dysfunctional behavioral patterns may spread through online social connections. These findings highlight the potential of NLP and graph-based modeling in the early detection, monitoring, and prevention of eating disorders by leveraging digital traces left in online environments.
1. Movsisyan K.R. The Influence of Social Networks on the Formation and Development of Eating Disorders. Severo-Kavkazskii psikhologicheskii vestnik. 2022;20(1):15–28. (In Russ.).
2. Lerman K., Karnati A., Zhou Sh., et al. Radicalized by Thinness: Using a Model of Radicalization to Understand Pro-Anorexia Communities on Twitter. arXiv. URL: https://doi.org/10.48550/arXiv.2305.11316 [Accessed 4th April 2025].
3. Ramírez-Cifuentes D., Freire A., Baeza-Yates R., et al. Characterization of Anorexia Nervosa on Social Media: Textual, Visual, Relational, Behavioral, and Demographical Analysis. Journal of Medical Internet Research. 2021;23(7). https://doi.org/10.2196/25925
4. Frieiro Padín P., González-Rodríguez R., Verde-Diego C., Vázquez-Pérez R. Social Media and Eating Disorder Psychopathology: A Systematic Review. Cyberpsychology: Journal of Psychosocial Research on Cyberspace. 2021;15(3). https://doi.org/10.5817/CP2021-3-6
5. Wang T., Brede M., Ianni A., Mentzakis E. Detecting and Characterizing Eating-Disorder Communities on Social Media. In: WSDM '17: Proceedings of the 10th ACM International Conference on Web Search and Data Mining, 06–10 February 2017, Cambridge, United Kingdom. New York: Association for Computing Machinery; 2017. P. 91–100. https://doi.org/10.1145/3018661.3018706
6. Dane A., Bhatia K. The Social Media Diet: A Scoping Review to Investigate the Association Between Social Media, Body Image and Eating Disorders Amongst Young People. PLOS Global Public Health. 2023;3(3). https://doi.org/10.1371/journal.pgph.0001091
7. Tukayev R.D. Trigger Mechanisms of Biological and Psychological Stress and the Diathesis Stress Models in Psychiatry. Social and Clinical Psychiatry. 2012;22(2):69–77. (In Russ.).
8. Solnyshkina M.I., McNamara D.S., Zamaletdinov R.R. Natural Language Processing and Discourse Complexity Studies. Russian Journal of Linguistics. 2022;26(2):317–341. (In Russ.). https://doi.org/10.22363/2687-0088-30171
9. Petrov A., Ivanova G., Slavutskaya E. Neuro Net Training as Instrument of System Analysis of Multidimensional Psychodyagnostic Data. Vestnik Chuvashskogo Universiteta. 2018;(1):162–168. (In Russ.).
10. Slavutskaya E., Abrukov V., Slavutskii L. Neural Network Systems Analysis of the Split-Level Psychological Characteristics. Vestnik Chuvashskogo Universiteta. 2016;(1):164–173. (In Russ.).
Solokhov Timur Damirovich
ORCID |
Financial University under the Government of the Russian Federation
Moscow, Russian Federation
