TY - GEN
T1 - Assessing Depression Health Information Using Machine Learning
AU - Jebadurai, Jebaveerasingh
AU - Lebina, W. Maria
AU - Shwetha, V.
N1 - Funding Information:
The authors acknowledge the computational facilities provided by Karunya Institute of Technology and Sciences through the CISCO Center of Excellence for Advanced Networking in the Department of Computer Science and Engineering.
Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Evaluating health information using machine learning is a must, especially with the tremendous growth of internet resources. Increased usage of technology may result in a less working lifestyle. Furthermore, continual stress on an individual might increase the likelihood of psychosis. Peer pressure, heart attacks, despair, and a variety of other effects are examples of these ailments. Health information should be accurate in most cases People browse the internet before seeing a doctor. Our main idea is the process of evaluating depression treatment guidelines without automation High-precision medical professional intervention. In our idea we used Naive Bayes classifier with high text classification accuracy. In front When using a naive Bayes classifier, treatment guidelines are cleaned up by Stop With words derived from NLTK to avoid meaningless words. Words-in-a-Bag By constructing a recurrence matrix, the technique is utilized to calculate the number of words. The final product is available as a web application.
AB - Evaluating health information using machine learning is a must, especially with the tremendous growth of internet resources. Increased usage of technology may result in a less working lifestyle. Furthermore, continual stress on an individual might increase the likelihood of psychosis. Peer pressure, heart attacks, despair, and a variety of other effects are examples of these ailments. Health information should be accurate in most cases People browse the internet before seeing a doctor. Our main idea is the process of evaluating depression treatment guidelines without automation High-precision medical professional intervention. In our idea we used Naive Bayes classifier with high text classification accuracy. In front When using a naive Bayes classifier, treatment guidelines are cleaned up by Stop With words derived from NLTK to avoid meaningless words. Words-in-a-Bag By constructing a recurrence matrix, the technique is utilized to calculate the number of words. The final product is available as a web application.
UR - http://www.scopus.com/inward/record.url?scp=85152585611&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85152585611&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-28475-5_5
DO - 10.1007/978-3-031-28475-5_5
M3 - Conference contribution
AN - SCOPUS:85152585611
SN - 9783031284748
T3 - Communications in Computer and Information Science
SP - 45
EP - 53
BT - Internet of Things - 3rd International Conference, ICIoT 2022, Revised Selected Papers
A2 - Venkataraman, Revathi
A2 - Uthra, Annie
A2 - Minu, R.I.
A2 - Sugumaran, Vijayan
A2 - Chelliah, Pethuru Raj
PB - Springer Science and Business Media Deutschland GmbH
T2 - 3rd International Conference on Internet of Things, ICIoT 2022
Y2 - 5 April 2022 through 7 April 2022
ER -