Determinants of Turkish Language Achievement: An Ecological and Data Mining Analysis Using ABİDE Data

The purpose of this study is to identify the factors associated with students’ achievement on the Monitoring and Evaluation of Academic Skills (Akademik Becerilerin İzlenmesi ve Değerlendirilmesi; [ABİDE]) Turkish language assessment. The research was designed using quantitative methods, specifically descriptive and correlational survey models. The sample consisted of 513 8th-grade students enrolled in selected districts of Mersin, Türkiye. The dataset included 58 categorical variables and eight continuous index variables, and data analysis was conducted using R software and SPSS.The findings suggest that the Home Resources Index and the Perception of Problem-Solving Skills Index are the main significant predictors of Turkish language achievement. Although students with higher Turkish scores reported lower exposure to peer bullying, this variable did not emerge as a statistically significant predictor in the regression model (p= .087). Similarly, the Sense of Belonging to School Index showed no significant relationship with or predictive effect on Turkish language achievement. The findings suggest that home resources and students’ educational goals play a critical role in shaping academic achievement and should therefore be prioritized in educational policies. However, since the sample is limited to specific districts in Mersin, the generalizability of the results is restricted to similar socio-economic contexts.