Cheating among elementary school children: A machine learning approach

Academic cheating is common, but little is known about its early emergence. It was examined among Chinese second to sixth graders (N = 2094; 53% boys, collected between 2018 and 2019) using a machine learning approach. Overall, 25.74% reported having cheated, which was predicted by the best machine learning algorithm (Random Forest) at a mean accuracy of 81.43%. Cheating was most strongly predicted by children's beliefs about the acceptability of cheating and the observed prevalence and frequency of peer cheating at school. These findings provide important insights about the early development of academic cheating, and how to promote academic integrity and limit cheating before it becomes entrenched. The present research demonstrates that machine learning can be effectively used to analyze developmental data.     

Assessing students' ability to trace matter in dynamic systems in cell biology

College-level biology courses contain many complex processes that are often taught and learned as detailed narratives. These processes can be better understood by perceiving them as dynamic systems that are governed by common fundamental principles. Conservation of matter is such a principle, and thus tracing matter is an essential step in learning to reason about biological processes. We present here multiple-choice questions that measure students' ability and inclination to trace matter through photosynthesis and cellular respiration. Data associated with each question come from students in a large undergraduate biology course that was undergoing a shift in instructional strategy toward making fundamental principles (such as tracing matter) a central theme. We also present findings from interviews with students in the course. Our data indicate that 1) many students are not using tracing matter as a tool to reason about biological processes, 2) students have particular difficulties tracing matter between systems and have a persistent tendency to interconvert matter and energy, and 3) instructional changes seem to be effective in promoting application of the tracing matter principle. Using these items as diagnostic tools allows instructors to be proactive in addressing students' misconceptions and ineffective reasoning.