Table 4 User metadata and overall activity features
From: Predicting subjective well-being in a high-risk sample of Russian mental health app users
Feature name | Description | Number |
|---|---|---|
Age | – | 1 |
Gender | – | 1 |
NVkFriends | No of friends in VKontakte | 1 |
AllAlters | No of alters (accounts that a user has a message history with) in the last 12 months | 1 |
Subscriptions | No of VKontakte page subscriptions | 1 |
Mess_ 1 | Total number of messages written in the last 30 days | 1 |
MessChars_ 1 | Total size (in characters) of messages written in the last 30 days | 1 |
growth-2to-1weighted | Weighted difference between total size of messages written in the months −1 and −2 | 1 |
altersdiff | Weighted difference between numbers of alters in the months −1 and −2 | 1 |
AppUsage1Week | Number of active app usage instances in the period of app data sharing time (one week) | 1 |
AllAppTime1Week | Total time of phone app usage in the period of app data sharing time (in seconds) | 1 |
RatioAppTime1Week | Ratio of phone app usage time in the week of app data sharing time | 1 |
AppUsage 0–3, 3–6, 6–9, 9–12, 12–15, 15–18, 18–21, 21–24 | Time of phone app usage in 3-hour time periods – each out of the 8 features represents a 3-hour time period | 8 |
AppUsage 0–3, 3–6, 6–9, 9–12, 12–15, 15–18, 18–21, 21–24 Ratio | Time of phone app usage in 3-hour time periods normalized by total app usage time – each out of the 8 features represents a 3-hour time period | 8 |
Alters −1–−12 | Numbers of alters in every month (30 days) before the DigitalFreud install time, for months between −1 and −12 | 12 |
Total | 40 | |