Table 7 SWLS value prediction results
From: Predicting subjective well-being in a high-risk sample of Russian mental health app users
Features | Best model | Results | ||
|---|---|---|---|---|
MAE | Pearson R | R-2 | ||
Mean baseline | 0.1853 | – | – | |
Median baseline | 0.185 | – | – | |
Words | ElasticNet | 0.1744 | 0.3402 | 0.1022 |
RuLIWC | DecisionTree | 0.182 | 0.2168 | 0.0142 |
AppCats | ElasticNet | 0.1762 | 0.2737 | 0.0172 |
Behavior | DecisionTree | 0.1785 | 0.191 | 0.0195 |
Clusters | RandomForest | 0.1814 | 0.1709 | 0.026 |
Clusters + AppCats + Behavior + Words | ElasticNet | 0.1698 | 0.4024 | 0.1045 |
Clusters + AppCats + RuLIWC + Behavior + Words | ElasticNet | 0.1681 | 0.3776 | 0.1164 |