Open AccessAnalysis of the effect of the lecturer satisfaction with the Naive Bayes Data Mining technique on institutional performance
Author(s) -
Siti Aisyah,
Preddy Marpaung,
Wiwin Aprinai,
Komda Saharja,
I Made Yuda Suryawan,
Bekti Tufiq Ari Nugroho,
Amin Nurbaedi,
Hasrul Azwar Hasibuan,
Bernadetha Nadeak,
Ahmad Tohir
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1933/1/012034
Subject(s) - naive bayes classifier , accountability , reliability (semiconductor) , bayes' theorem , compassion , recall , computer science , psychology , data mining , applied psychology , statistics , artificial intelligence , mathematics , bayesian probability , political science , cognitive psychology , power (physics) , physics , quantum mechanics , support vector machine , law
The study aimed to analyze the effect on institutional performance of lecturer satisfaction with data extraction techniques. The solution is the technique of Naive Bayes, where data is obtained through interviews and questionnaires conducted in one of the private institutions in the north-sumatra of Medan. The evaluation criteria are readiness, compassion, reliability and accountability. The tests indicate that the level of accuracy is 85.48% with 81.08% precision, and 93.75% recall value. The Naïve Bayes method can also be recommended to predict the degree of satisfaction of the lecturer with institutional performance based on the results of tests using fast miner software.