The prediction of health information quality perception using machine learning and deep learning techniques

Baqraf, Yousef; Keikhosrokiani, Pantea (2023-09-29)
 
Avaa tiedosto
Lataukset: 

URL:
https://doi.org/10.1109/ICoICT58202.2023.10262623

Baqraf, Yousef
Keikhosrokiani, Pantea
IEEE
29.09.2023

Y. Baqraf and P. Keikhosrokiani, "The Prediction of Health Information Quality Perception Using Machine Learning and Deep Learning Techniques," 2023 11th International Conference on Information and Communication Technology (ICoICT), Melaka, Malaysia, 2023, pp. 104-109, doi: 10.1109/ICoICT58202.2023.10262623.

https://rightsstatements.org/vocab/InC/1.0/
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
doi:https://doi.org/10.1109/icoict58202.2023.10262623
Näytä kaikki kuvailutiedot
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202312013477
Tiivistelmä
Abstract

With the substantial rise in the number of people seeking health information online, manually evaluating their perceptions of the quality of health information has become increasingly difficult. These perceptions can impact the acceptance or rejection of the information. To address this issue, the study has employed deep learning and machine learning models to automatically identify consumer perceptions of health information. Furthermore, the study used a survey to collect data from 253 individuals to train the models, measuring the perception of 18 dimensions related to health information quality. This will help health information providers to provide personalized health information that aligns with individual preferences. The RandomForest and neural network model are found to have achieved the best performance among all the algorithms with an Accuracy of over 90% in all the quality dimensions. In sum, our findings show that automating the identification of consumer perception is feasible, which is an essential step toward providing online health information that matches consumer perception and increases the willingness to use it.
Kokoelmat