Educational data mining has become an effective tool for exploring the hidden relationships in educational data and predicting students' academic achievements. This study proposes a new model based on machine learning algorithms to predict the final exam grades of undergraduate students, taking their midterm exam grades as the source data. The performances of the random forests, nearest neighbour, support vector machines, logistic regression, Naïve Bayes, and k-nearest neighbour algorithms, which are among the machine learning algorithms, were calculated and compared to predict the final exam grades of the students. The dataset consisted of the academic achievement grades of 1854 students who took the Turkish Language-I course in a state University in Turkey during the fall semester of 2019–2020. The results show that the proposed model achieved a classification accuracy of 70–75%. The predictions were made using only three types of parameters; midterm exam grades, Department data and Faculty data. Such data-driven studies are very important in terms of establishing a learning analysis framework in higher education and contributing to the decision-making processes. Finally, this study presents a contribution to the early prediction of students at high risk of failure and determines the most effective machine learning methods.

No abstract

No abstract

In the relevant literature, it is often debated whether learning programming requires high-level thinking skills, the lack of which consequently results in the failure of students in programming. The complex nature of programming and individual differences, including study approaches, thinking styles, and the focus of supervision, all have an effect on students' achievement in programming. How students learn programming and the relationships between their study approaches and their achievement in programming have not yet been adequately illuminated. In this regard, the present study aims to investigate the effect of the study approach used on students' attitudes toward programming and on their academic achievement within an online problem-based learning environment. In this study, a single-factor, pretest posttest single group and semiempirical method was utilized. The study was conducted on 41 students from a public university in Turkey. To implement problem-based learning activities, a teaching environment was created with the Moodle platform, allowing for group work and discussions. Seven status of the problems were prepared exclusively for the 12-week application period so that students could make suggestions about how to solve them. In the data collection phase, the Study Approach Scale, the Attitude Towards Programming Scale, and the Academic Achievement Test were

Learning programming requires high level of problem solving skills. Therefore, factors effective on students’ success in programming have been one of the debated subjects in the literature. Moreover, average success levels of students in programming languages course are usually at low level. The reason lying underneath failure of students could also be their readiness for programming and self-sufficiencies in addition to necessity of high level of thinking skill. In this respect, the purpose of the present research is to investigate attitudes of IT preservice teachers and CP students toward computer programming, their self-sufficiency perception toward programming, and the relationship among them. Data was collected from totally 274 participants including 165 IT preservice teachers and 114 CP students. Research results reveal that IT preservice teachers and CP students have medium level of attitude and self-sufficiency perception toward programming. Another research reports that IT preservice teachers have higher self-sufficiency perception regarding programming with respect to CP students. Additionally, no significant relationship was found between attitudes of students toward computer programming and their self-sufficiency perceptions regarding programming. ÖzetProgramlama öğrenimi üst düzey problem çözme becerileri gerektirmektedir. Bu yüzden öğrencilerin programlama başarılarını etkileyen faktörler literatürde tartışılan bir konu olmuştur. Ayrıca öğrencilerin programlama dilleri derslerinde başarı ortalaması genelde düşük düzeydedir. Öğrencilerin başarısız oluşunun altında yatan sebep programlama öğreniminin üst düzey düşünme becerisi gerektirmesinin yanında programlamaya yönelik hazırbulunuşlukları da olabilir. Bu bağlamda bu araştırmanın amacı BT öğretmen adaylarının ve BP öğrencilerinin bilgisayar programlamaya yönelik tutumları, programlamaya ilişkin öz yeterlik algıları ve bunlar arasındaki ilişkiyi incelemek olarak belirlenmiştir. Veriler 165’i BT öğretmen adayı ve 114’ü BP öğrencisi olmak üzere toplam 274 katılımcıdan elde edilmiştir. Araştırma sonuçları BT öğretmen adaylarının ve BP öğrencilerinin orta düzeyde programlamaya yönelik tutuma ve öz yeterlik algısına sahip olduklarını göstermektedir. Cinsiyet, öğrencilerin tutum ve algılarında anlamlı bir farklılık oluşturmamıştır. Sınıf düzeyi BT öğretmen adaylarının tutum ve öz yeterlik algılarında farklılık oluşturmazken BP öğrencilerinin tutum ve algılarında anlamlı bir farklılık oluşturmuştur. Bir diğer araştırma sonucu ise BT öğretmen adaylarının BP öğrencilerinden daha yüksek düzeyde programlamaya ilişkin öz yeterlik algısına sahip olduğudur. Ayrıca öğrencilerin bilgisayar programlamaya yönelik tutumları ile programlamaya ilişkin öz yeterlik algıları arasında anlamlı bir ilişki bulunmamıştır.