The selection of thesis titles by students is an important thing to do as part of the graduation requirements in completing undergraduate studies. In general, the difficulty or complexity of the thesis can be reflected through the title of the thesis that is appointed. This can indicate that the more difficult a thesis title, the longer it will take to complete the thesis research. This study utilizes the data mining method using machine learning, namely linear regression, in predicting how long it will take to complete a thesis title. The data used is obtained from the words or text in the thesis title as a feature or independent variable and the completion time in days as the dependent variable to predict the time required for students starting from a thesis proposal seminar to a comprehensive seminar or thesis final session. The regression model produces an evaluation value of the coefficient of determination of 0.999, which is close to the maximum value equal to 1.
Copyrights © 2025