Hybrid Recommender System for Mental Illness Detection in Social Media Using Deep Learning Techniques

Table 2

Precision for RFD – PSO feature selection - with systolic tree frequent pattern mining + CF.

Top-N recommended items	RFD feature selection-without frequent pattern mining	RFD feature selection-without frequent pattern mining + CF	RFD feature selection-with systolic tree frequent pattern mining	RFD feature selection-with systolic tree frequent pattern mining + CF	RFD - PSO feature selection-without frequent pattern mining	RFD - PSO feature selection-without frequent pattern mining + CF	RFD - PSO feature selection-with systolic tree frequent pattern mining	RFD - PSO feature selection-with systolic tree frequent pattern mining + CF
N = 2	0.82	0.84	0.88	0.89	0.85	0.89	0.93	0.94
N = 4	0.8	0.81	0.83	0.85	0.84	0.85	0.87	0.89
N = 6	0.77	0.8	0.79	0.81	0.81	0.84	0.83	0.85
N = 8	0.75	0.76	0.76	0.78	0.78	0.79	0.8	0.81
N = 10	0.7	0.72	0.73	0.75	0.73	0.76	0.76	0.79
N = 12	0.69	0.7	0.69	0.71	0.73	0.73	0.73	0.75
N = 14	0.67	0.66	0.66	0.68	0.71	0.69	0.7	0.71
N = 16	0.63	0.64	0.64	0.66	0.66	0.67	0.67	0.69
N = 18	0.6	0.61	0.61	0.62	0.63	0.64	0.64	0.66