Automatic Classification of Computational Thinking Skills in Elementary School Math Questions

This research full paper presents the design of an automatic classifier for Computational Thinking skills in math questions, based on Machine Learning and Natural Language Processing techniques. We trained and evaluated our model using a dataset of real-world math questions. We obtained encouraging results that indicate the proposed approach may ease the process of assessing the level of alignment between matt questions and Computational Thinking skills, which may help improve the problem-solving ability in students of elementary school. These results stimulate the use of automated environments for the elaboration, classification, and resolution of math questions in conformity with Computational Thinking skills.