Textbox 4.

Limitations of this study.

a. Sampling Bias – The study’s reliance on an online survey may introduce sampling bias, as it excludes individuals without internet access or digital literacy. This could lead to underrepresentation of certain demographic groups, potentially skewing the results. b. Self-Reporting Bias – The data collected through self-reported measures may be subject to bias, as participants may provide inaccurate or incomplete information due to social desirability or recall biases. This could affect the reliability and validity of the findings. c. Limited Generalizability – Conducting the study in Kolkata, India, may limit the generalizability of the findings to other regions or populations with different socio-cultural contexts. The study’s focus on a specific geographic area may restrict the applicability of the results to broader populations. d. Data Quality and Noise – Despite efforts to clean the dataset by removing missing data and outliers, the presence of residual noise or errors may still impact the validity of the results. Without robust measures to address data quality issues, the accuracy of the findings may be compromised. e. Lack of Longitudinal Data - The study’s cross-sectional design and reliance on data collected at a single point in time limit its ability to capture the dynamic nature of depressive symptoms over time, hindering a comprehensive understanding of the longitudinal impact of lifestyle and demographic factors on mental health outcomes. f. Language and Digital Literacy Barriers - The use of online surveys conducted in English may exclude individuals who are not proficient in the language or lack digital literacy skills, potentially leading to underrepresentation of certain demographic groups and limiting the inclusivity and diversity of the sample. g. Methodological Constraints – While the study employs advanced statistical and machine learning techniques, such as PCA and SVC, other relevant methods or approaches may not have been considered. The omission of alternative methodologies could limit the comprehensiveness of the analysis and interpretation of the results. h. Ontology Development – While the use of an OWL Ontology facilitates semantic representation of the dataset, challenges in ontology development, such as ontology alignment, scalability, and maintenance, may affect the utility and usability of the semantic model.