Daily Smartphone Sensing Features and Self-Reported Sadness Scores

Averaged daily smartphone sensing features and self-reported mental health outcomes by participant, used for correlation analysis in a research paper. The data includes features like acceleration magnitude, GPS variance, and phone unlock duration, paired with mean and standard deviation of daily sadness scores on a 0-3 scale. The dataset was authored by Wu, Congyu and last updated on March 18, —2024.

Use Cases

• Correlating physical activity patterns (via acceleration magnitude RMSSD) with self-reported sadness.
• Analyzing mobility patterns (via GPS coordinate variance) in relation to mental health outcomes.
• Investigating the relationship between smartphone engagement (via unlocked duration) and emotional states.
• Modeling the stability of daily sadness (via its standard deviation) against behavioral sensing features.

Strengths

• Data is aggregated and averaged by participant, likely simplifying analysis.
• Includes a specific count ('num.entries') of days where both sensing and self-report data are available.
• Features are derived from established algorithms, such as the temporal coordinate clustering for place entropy.

Limitations

• Row count, column details, and file formats are unknown, which may limit suitability assessment.
• Description metadata is limited; actual data quality and completeness require manual inspection after download.
• Data may reflect temporal and participant bias inherent to the specific study and dataverse source.

Provenance

Source

Texas Data Repository Harvested Dataverse

Collection Method

Smartphone sensing and daily end-of-day self-reports from participants.

Time Range

null

Freshness

Last updated 2024-03-18 08:34:10; freshness should be verified.

Geography

null