2020
Gonçalves, C.; Ferreira, D.; Neto, C.; Abelha, A.; Machado, J.
Prediction of mental illness associated with unemployment using data mining Proceedings Article
Em: E.M., Yasar A. Shakshuki (Ed.): pp. 556-561, Elsevier B.V., 2020, ISSN: 18770509, (cited By 7; Conference of 11th International Conference on Emerging Ubiquitous Systems and Pervasive Networks, EUSPN 2020 ; Conference Date: 2 November 2020 Through 5 November 2020; Conference Code:166555).
Resumo | Links | BibTeX | Etiquetas: CRISP-DM; Cross industry; Evaluation metrics; Mental illness, Data mining, Diseases; Employment; Forecasting
@inproceedings{Gonçalves2020556,
title = {Prediction of mental illness associated with unemployment using data mining},
author = {C. Gonçalves and D. Ferreira and C. Neto and A. Abelha and J. Machado},
editor = {Yasar A. Shakshuki E.M.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099879347&doi=10.1016%2fj.procs.2020.10.078&partnerID=40&md5=077569e0b99ba95909110a8699069c1e},
doi = {10.1016/j.procs.2020.10.078},
issn = {18770509},
year = {2020},
date = {2020-01-01},
journal = {Procedia Computer Science},
volume = {177},
pages = {556-561},
publisher = {Elsevier B.V.},
abstract = {Mental illness is a concern these days, affecting people worldwide and across all kinds of ages. This article aims to predict mental illness and discover its association with unemployment as well as other possible causes behind the illness. In order to accomplish this goal, a Data Mining (DM) process was performed using the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology and the RapidMiner Studio software. In the end, the results obtained were considered promising since all the evaluation metrics, namely accuracy, sensitivity, and specificity, obtained values above 90%. The study also allowed, in the end, to identify the factors associated with the prediction of mental illness. © 2020 The Authors. Published by Elsevier B.V.},
note = {cited By 7; Conference of 11th International Conference on Emerging Ubiquitous Systems and Pervasive Networks, EUSPN 2020 ; Conference Date: 2 November 2020 Through 5 November 2020; Conference Code:166555},
keywords = {CRISP-DM; Cross industry; Evaluation metrics; Mental illness, Data mining, Diseases; Employment; Forecasting},
pubstate = {published},
tppubtype = {inproceedings}
}
Mental illness is a concern these days, affecting people worldwide and across all kinds of ages. This article aims to predict mental illness and discover its association with unemployment as well as other possible causes behind the illness. In order to accomplish this goal, a Data Mining (DM) process was performed using the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology and the RapidMiner Studio software. In the end, the results obtained were considered promising since all the evaluation metrics, namely accuracy, sensitivity, and specificity, obtained values above 90%. The study also allowed, in the end, to identify the factors associated with the prediction of mental illness. © 2020 The Authors. Published by Elsevier B.V.