Table 4. Spearman correlation and bootstrapped confidence intervals of predicted scores with manually assigned scores per model and schema.

The result of the best model per schema is shown in bold font.

Schema	Model Outcome
	kNN-C	kNN-R	SVM	SVR	per-schema RNNs	multi-label RNN
Attachment	0.55 [0.51,0.60]	0.63 [0.59,0.65]	0.65 [0.61,0.68]	0.68 [0.65,0.70]	0.73 [0.70,0.76]	0.67 [0.66,0.72]
Competence	0.69 [0.64,0.73]	0.66 [0.63,0.69]	0.68 [0.65,0.72]	0.64 [0.61,0.67]	0.76 [0.72,0.79]	0.66 [0.64,0.69]
Global self-evaluation	0.40 [0.33,0.46]	0.41 [0.36,0.46]	0.36 [0.31,0.40]	0.49 [0.45,0.52]	0.58 [0.54,0.63]	0.49 [0.45,0.53]
Health	0.74 [0.65,0.81]	0.53 [0.44,0.60]	0.73 [0.65,0.81]	0.35 [0.31,0.40]	0.75 [0.65,0.82]	0.35 [0.31,0.39]
Power and Control	0.11 [0.02,0.18]	0.23 [0.17,0.27]	nan [0.00,1.00]	0.31 [0.26,0.35]	0.28 [0.20,0.35]	0.31 [0.27,0.34]
Meta-cognition	nan [0.00,1.00]	0.10 [0.01,0.20]	nan [0.00,1.00]	0.11 [0.06,0.16]	-0.01 [0.00,-0.01]	0.11 [0.06,0.14]
Other people	0.28 [0.00,1.00]	0.24 [0.17,0.31]	nan [0.00,1.00]	0.19 [0.14,0.24]	0.22 [0.07,0.33]	0.16 [0.10,0.20]
Hopelessness	0.48 [0.44,0.55]	0.51 [0.47,0.56]	0.49 [0.43,0.53]	0.54 [0.51,0.57]	0.63 [0.56,0.68]	0.53 [0.50,0.56]
Other’s views on self	0.45 [0.41,0.51]	0.46 [0.42,0.50]	0.48 [0.43,0.53]	0.52 [0.48,0.55]	0.58 [0.52,0.63]	0.50 [0.47,0.54]

The abbreviation nan that resulted for some schemas and some models stands for not a number and is caused by the absence of variance in the prediction (see text for details).