Predicting Different Health and Lifestyle Behaviors of Social Media Users


Smirnoff I. Stankevich M.


The rise of social media platforms and a growing interest in applying machine learning methods to ever increasing amounts of data creates an opportunity to use data from social media to predict lifestyle choices and behaviors. In this study, we examine the possibility of using machine learning methods to classify users of the Russian-speaking social networking service VK based on different health related activities and habits. Participants of this study took a survey that had questions about different health-related behaviors and activities and the intensity with which users follow them. We describe the process of gathering, processing, and using this data to train a set of machine learning classifiers, and we evaluate the performance of these models in our experimental results. The features that were best able to classify most of the behaviors were collected from user subscription data. The best results were achieved on the questions about limiting the alcohol use and limiting the laptop and smartphone use (0.73 and 0.74 ROC AUC) with features generated from user profile and subscription data.

External links

DOI: 10.1007/978-3-030-86855-0_5

Read at Google Books:

Microsoft Academic:


Semantic Scholar:

Reference link

Khalil K., Stankevich M., Smirnov I., Danina M. (2021) Predicting Different Health and Lifestyle Behaviors of Social Media Users. In: Kovalev S.M., Kuznetsov S.O., Panov A.I. (eds) Artificial Intelligence. RCAI 2021. Lecture Notes in Computer Science, vol 12948. Springer, Cham. Pages 57-66