Predicting Geospatial Thinking Ability for Secondary School Students Based on the Decision Tree Algorithm in Mainland China

Shumin Xie, Siying Zeng, Lu Liu, Huimin Wei, Yanhua Xu, Xiaoxu Lu

Abstract

Predicting secondary school students' geospatial thinking ability can provide targeted guidance for teachers. To date, few scholars have focused on predicting students’ geospatial thinking ability. In this paper, we address this gap by constructing a prediction model based on the decision tree algorithm, to predict the geospatial thinking ability of secondary school students. A total of 1029 secondary school students were surveyed using the Spatial Thinking Ability Test, the Students' Geography Learning Status Questionnaire, and the Middle Students Motivation Test. Our model indicates that geospatial thinking ability can be predicted by nine factors, in order of importance: academic achievement in geography, geography learning strategy, geography classroom environment, gender, learning initiative, learning goals, extra-curricular time spent learning geography, ego-enhancement drive, and interest in learning geography. The model accuracy is 81.25%. Specifically, our study is the first to predict geospatial thinking ability. It provides a tool for teachers that can help them identify and predict students' geospatial thinking ability, which is conducive to designing better teaching plans and making adjustments to the curriculum.

Keywords

Geospatial thinking ability, Decision tree, Prediction, Model, Teaching


DOI: http://dx.doi.org/10.15390/EB.2022.10367

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.