Identifying Smiling Depression vai Sentiment Score

The dataset comprises self-reported responses from undergraduate students across various colleges and universities in South India, primarily from the states of Telangana, Andhra Pradesh, and Tamil Nadu. Participants are aged between 18 and 22 years and are enrolled in technical (e.g., B.Tech) and traditional undergraduate programs (e.g., B.A., B.Sc., B.Com.). The data captures a diverse mix of students from urban, semi-urban, and rural backgrounds, providing a broad perspective on student experiences.

Each entry includes basic demographic information such as age, gender, place of living, educational qualification, and the name of the institution. The core of the dataset consists of responses to a series of statements designed to probe behaviors and attitudes associated with "smiling depression"—a phenomenon where individuals conceal depressive symptoms behind a façade of happiness. Statements address themes such as hiding negative emotions, reluctance to discuss problems, the use of humour to mask distress, and the perceived need to appear happy or in control around others.

For each statement, students indicate the frequency or degree to which it applies to them, using scales such as "Always," "Often," "Sometimes," "Rarely," and "Never," or levels of agreement from "Strongly Agree" to "Strongly Disagree." These qualitative responses are numerically encoded for analysis.

Additionally, the dataset includes sentiment scoring outputs, where each response is assigned a sentiment value (e.g., -2 for strongly negative, 0 for neutral, +2 for strongly positive). An average sentiment score is calculated for each participant, offering a quantitative measure of their overall emotional expression related to smiling depression behaviors. This scoring allows for the identification of students who may be at risk, despite outward appearances of well-being.

The data is anonymised to protect participant privacy, with personal identifiers removed. The comprehensive structure and sentiment scoring make the dataset suitable for sentiment analysis, enabling researchers to detect patterns and prevalence of smiling depression among undergraduate students and to explore correlations with demographic factors.