PLANNING OF PERSONALIZED PSYCHOLOGICAL INTERVENTION IN VICTIMS OF THE ARMED CONFLICT IN COLOMBIA THROUGH ARTIFICIAL INTELLIGENCE

Millan De Lange, Constant Anthony; Molinares Brito, Carmen Margarita; Dasuki Garcia, Karim Hussein; Baena Valencia, Stefany

doi:10.1590/0101-7438.2023.043.00279900

Acessibilidade / Reportar erro

Brasil

Español English

sumário « anterior atual seguinte »

Sumário

ARTICLES • Pesqui. Oper. 44 • 2024 • https://doi.org/10.1590/0101-7438.2023.043.00279900 copy

PLANNING OF PERSONALIZED PSYCHOLOGICAL INTERVENTION IN VICTIMS OF THE ARMED CONFLICT IN COLOMBIA THROUGH ARTIFICIAL INTELLIGENCE

Authorship SCIMAGO INSTITUTIONS RANKINGS

ABSTRACT

This paper describes the psychometric validation procedure for the creation of an Artificial Intelligence (AI) engine based on the theory of precision psychology and expert system-type machine learning algorithms. The focus is on individual coping strategies and the factor of reconciliation in victims of armed conflict in Colombia. A non-experimental methodology with a cross-sectional design was used, with a total of 363 participants. The results highlight that elements related to economic factors, individual condition, and political concerns in the victims explain the conditions required to generate a reconciliation process in the context of reintegrating into civilian life. It is concluded that the use of artificial intelligence enhances the process of psychological care by providing precision in the etiological information of the illness and the data, which enables discrimination between the health status, symptoms, and disease of the victims.

Keywords:
psychological intervention; simulator; armed conflict; victims; artificial intelligence

	(1)	(2)	(3)	(4)	(5)	(6)	(7)	(8)	(9)	(10)
Reconciliation Pearson Correlation	,041	,109	,130	,090	,166	,043	,060	-,008	,114	,061
Sig. (two-tailed)	,432	,037	,013	,086	,002	,413	,256	,877	,029	,250
N	363	363	363	363	363	363	363	363	363	363

Model Nº	χ²/gl GFI	0	7	9	15	0
Factors N°	ECVI		ML	ULS	ML	ULS
Factors N°	NCP	2,21	2.195	2.241	2.274	2.222
Estimation method	RMSR	13.655	9.431	8.309	13.572	7.698
	RMSEA	0.00	0.00	0.00	0.00	0.00
	RMSEA	6.19	4.30	3.71	5.97	3.46
gl	p value	0,65	0,73	0,75	0,65	0,92
gl	p value	18,9	13,21	11,75	18,8	11,3
χ ²		11.448	7.236	6.068	11.298	5.746
χ ²		0,085	0.075	0.067	0.085	0.061
χ ² p value		0,08	0,067	0,061	0,082	0,06

Model Nº	Factors Nº	Estimation method	Incremental Fit Indices				Parsimony Fit Indices
Model Nº	Factors Nº	Estimation method	AGFI	NNFI O TLI	NFI	NFI	PNFI	PGFI
5	3	ML	0.63	0.83	0.83	0.8	0.77	0.61
7	6	ML	0.71	0.87	0.87	0.84	0.81	0.66
9	9	ULS	0.73	0.89	0.89	0.86	0.82	0.7
15	3	ML	0.63	0.83	0.84	0.8	0.78	0.61
19	9	ULS	0.73	0.89	0.89	0.86	0.82	0.7
33	11	ULS	0.74	0.89	0.9	0.86	0.82	0.7

(Z-Score)	(F) 1	(F) 2	(F) 3	(F) 4	(F) 5	(F) 6	(F) 7
Total	405	405	405	405	405	405	405
Minimum	-3.98	-2.50	-2.11	-4.22	-2.31	-3.13	-2.53
Mean	0.00	0.00	-0.00	-0.00	-0.00	-0.00	-0.00
Median	0.16	0.16	0.04	0.20	-0.02	0.09	-0.00
Mode	0.32	0.97	-1.87	0.50	2.53	0.53	0.42
Maximum	1.35	1.70	2.22	1.72	2.58	2.42	2.62
Deviation	0.88	0.91	0.95	0.90	0.83	0.86	0.89
Skewness	-1.42	-0.54	-0.08	-1.27	0.37	-0.73	0.08
Kurtosis	2.49	-0.66	-0.71	2.36	0.45	1.74	0.39
Skewness Error	-11.66	-4.41	-0.66	-10.40	3.02	-6.02	0.67
Kurtosis Error	10.25	-2.71	-2.92	9.70	1.84	7.15	1.59
N	NN	NN	NN	NN	NN	NN	NN

Model N°	GFI	923	23	7	17
Factors N°	ECVI NCP	3413.78	ML	5 ULS	ML
		0.00	0.090	0.110	0.110
		0.00	0.082	0.110	0.110
Estimation method gl	χ ² RMSR	370 9	1588,7	5345,27	5727
	RMSEA
	RMSEA
χ ²	p value	9	0	0	0
χ ² p value		2490,8	1,64	5,72	7,21
χ ² /gl		0,092	9,52	13,73	14,68
χ ² /gl		0,082	2650,6	4410,27	4718

Model Nº	Factors Nº	Estimation method	Incremental Fit Indices				Parsimony Fit Indices
Model Nº	Factors Nº	Estimation method	AGFI	NNFI o TLI	CFI	NFI	PNFI	PGFI
10	7	ULS	0.69	0.84	0.85	0.8	0.74	0.65
23	7	ML	0.85	1.07	1	1	0.94	0.78
7	5	ULS	0.81	1.05	1	1	0.94	0.75
17	5	ML	0.80	1.05	1	1	0.95	0.74

Model	R	R squared	Adjusted R squared	Standard error of estimation	Durbin-Watson
1	,785ª	,617	,603	6,29726	1,770

	Density %	Almost none	(1)	(2)	(3)	(4)	(5)	(6)
Minimum	0	0	0	0	0	0	0	0
Average	0,68	0,02	0,64	0,22	0,54	0,19	0,38	0,04
Standard deviation	0,23	0,10	0,29	0,23	0,30	0,17	0,30	0,07
Maximum	1	1	1	1	1	1	1	1
Skewness	-0,30	5,76	-0,30	1,51	1,05	1,37	0,59	2,61
Kurtosis	-0,66	35,40	-1,03	1,95	-1,18	2,23	-0,71	10,60

	Almost none	(1)	(2)	(3)	(4)	(5)	(6)	Standardized Predicted Value
Reconciliation, Pearson correlation	-070	-,065	-,016	,011	-,002	-.085	,002	,138
Sig. (bilateral)	,183	,214	,828	,828	,965	,106	,973	,008
N	363	363	363	363	363	363	363	363

	Model	Sum of squares	gl	Root mean square	F	Sig.
1	Regression	22320,571	12	1860,048	46,905	,000^b
	Residual	13879,407	350	39,655
	Total	36199,978	362

Type of intervention	Reconciliation	Multiple Regression	Discriminant Analysis	Logistic Regression	Final Model
Not required or Prevention	3 Above expectations	27,55%	54,00%	64,00%-66,00%	66,00%
2 (Promotion)	2 Within expectations	45,73%	88,55%		80,72%
3 (Recovery)	1 Below expectations	26,72%	47,42%	60,82%-62,89%	62,89%
					71,90%

Sociedade Brasileira de Pesquisa Operacional Rua Mayrink Veiga, 32 - sala 601 - Centro, 20090-050 Rio de Janeiro RJ - Brasil, Tel.: +55 21 2263-0499, Fax: +55 21 2263-0501 - Rio de Janeiro - RJ - Brazil
E-mail: sobrapo@sobrapo.org.br

Acompanhe os números deste periódico no seu leitor de RSS

[1] *Corresponding author