Yılmaz, CansenCaglayan,C.Computer Engineering2024-07-052024-07-0520191978-172813992-010.1109/UBMYK48245.2019.89655192-s2.0-85079221372https://doi.org/10.1109/UBMYK48245.2019.8965519https://hdl.handle.net/20.500.14411/3921In this study, teaching machine learning algorithms by using a software tool or with the code based methods were compared according to level of interest for the subject and perception of self-knowledge of the first time learners. Eleven participants were first year students from computer, software and information systems engineering departments who completed the C programming language course at the university. Participants were divided into two groups. Both groups were given basic theoretical knowledge about machine learning and one of the easiest algorithms to implement k-Nearest Neighbors (kNN) algorithm at the same level. The kNN algorithm, was explained to a group with the C programming language code implementation, and the other group with using a software tool Orange3 which has designed for implementing machine learning algorithms easily. Two questionnaires were applied to both groups. One was applied to measure their level of knowledge of programming and basic knowledge of machine learning. Other one was applied to measure their thoughts about knowledge and level of interest in the subject after the lecture. The aim of this study is to investigate whether we can improve the level of interest of students about machine learning by using code based or tool based environment for the first time learners and find the best teaching environment for them at the beginning. © 2019 IEEE.eninfo:eu-repo/semantics/closedAccessartificial intelligence educationk-Nearest Neighbors algorithmmachine learning educationteaching algorithmConference Object