Exploring online public survey lifestyle datasets with statistical analysis, machine learning and semantic ontology - Open access paper

Sep 17, 2026

Uploaded by Ezra

Lifestyle diseases significantly shape global health burdens, with lifestyle factors playing a key role in depression, intensified by the COVID-19 pandemic. This study investigated lifestyle and demographic correlates of depression symptoms among Indians during the pandemic, using an online public survey from Kolkata. Data from 1,834 participants were collected anonymously over three months and analyzed with PCA and ANOVA for feature selection, K-means clustering, and an SVM classifier achieving 96% accuracy. LIME provided local explanations and an OWL ontology supported semantic reasoning.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Overview

Data collection and survey design

Statistical and machine-learning analysis

Semantic representation with OWL ontology

[www. nature.com/scientificreports](www. nature.com/scientificreports) OPEN Exploring online public survey lifestyle datasets with statistical analysis, machine learning and semantic ontology Ayan Chatterjee1,2,3􀀍, Michael A. Riegler3, Miriam Sinkerud Johnson4, Jishnu Das5, Nibedita Pahari6, Raghavendra Ramachandra7, Bikramaditya Ghosh8,11, Arpan Saha9 & Ram Bajpai10 Lifestyle diseases significantly contribute to the global health burden, with lifestyle factors playing a crucial role in the development of depression. The COVID-19 pandemic has intensified many determinants of depression. This study aimed to identify lifestyle and demographic factors associated with depression symptoms among Indians during the pandemic, focusing on a sample from Kolkata, India. An online public survey was conducted, gathering data from 1,834 participants (with 1,767 retained post-cleaning) over three months via social media and email. The survey consisted of 44 questions and was distributed anonymously to ensure privacy. Data were analyzed using statistical methods and machine learning, with principal component analysis (PCA) and analysis of variance (ANOVA) employed for feature selection. K-means clustering divided the pre-processed dataset into five clusters, and a support vector machine (SVM) with a linear kernel achieved 96% accuracy in a multi-class classification problem. The Local Interpretable Model-agnostic Explanations (LIME) algorithm provided local explanations forthe SVM model predictions. Additionally, an OWL (web ontology language) ontology facilitated the semantic representation and reasoning of the survey data. The study highlighted a pipeline for collecting, analyzing, and representing data from online public surveys during the pandemic. The identified factors were correlated with depressive symptoms, illustrating the significant influence of lifestyle and demographic variables on mental health. The online survey method proved advantageous for data collection, visualization, and cost-effectiveness while maintaining anonymity and reducing bias. Challenges included reaching the target population, addressing language barriers, ensuring digital literacy, and mitigating dishonest responses and sampling errors. In conclusion, lifestyle and demographic factors significantly impact depression during the COVID-19 pandemic. The study’s methodology offers valuable insights into addressing mental health challenges through scalable online surveys, aiding in the understanding and mitigation of depression risk factors. Keywords Survey, Datasets, COVID-19, Depression, Machine learning, Semantics, LIME Abbreviations ML Machine learning PCA Principal component analysis 1Department of Information and Communication Technologies, University of Agder, 4879 Grimstad, Norway. 2Department of Holistic Systems, Simula Metropolitan Center for Digital Engineering, 0167 Oslo, Norway. 3Department of Digital Technology, STIFTELSEN NILU, 2007 Kjeller, Norway. 4Department of Behavioral Sciences, Oslo Metropolitan University, 0176 Oslo, Norway. 5Department of Information Systems, University of Agder, 4630 Kristiansand, Norway. 6Department of Software Development, Maulana Abul Kalam Azad University of Technology, Kolkata 700064, India. 7Department of Information Security and Communication Technology, Norwegian University of Science and Technology, 2815 Gjøvik, Norway. 8Department of Finance, Symbiosis Institute of Business Management, Symbiosis International (Deemed University), Bengaluru 560100, India. 9Department of Pharmaceutical Chemistry, Bharat Pharmaceutical Technology, Tripura 799130, India. 10School of Medicine, Keele University, Keele, Newcastle ST5 5BG, UK. 11Department of Finance, Harper Adams University, Shropshire TF10 8NB, UK. 􀀍 email: [ayan@nilu.no](ayan@nilu.no); [ayan1.c2@gmail.com](ayan1.c2@gmail.com) [www. nature.com/scientificreports/](www. nature.com/scientificreports/) OWL ANOVAKNN SVC NBStaRIRQ SPARQL WWW

FAQs

What was the study’s goal regarding depression during the COVID-19 pandemic?

To identify lifestyle and demographic factors associated with depression symptoms among Indians during the pandemic, using a Kolkata-based sample.

How was the dataset collected and prepared?

An online public survey gathered data from 1,834 participants over three months via social media and email, with 1,767 retained after cleaning and anonymity preserved.

Which models and methods were used for analysis and prediction?

Principal component analysis and analysis of variance supported feature selection; K-means clustering created five clusters; an SVM with a linear kernel reached 96% multi-class classification accuracy, with LIME providing local explanations.

How did the study use semantic technology in its pipeline?

An OWL (Web Ontology Language) ontology enabled semantic representation and reasoning over the survey data, supporting the overall pipeline for collecting, analyzing, and representing online survey information.

Sep 17, 2026

Uploaded by Ezra