One innovative assessment approach that has been increasingly implemented in many schools is student knowledge assessment using machine learning.

Alruwais and Zakariah (2023) discuss the implementation of machine learning for student knowledge assessment. Student knowledge assessment is the process of learning about a student’s knowledge and comprehension of a particular subject to help instructors and curriculum designers identify areas where students need additional support, evaluate the effectiveness of instruction, make important decisions such as on student placement and curriculum development, and monitor the quality of education. Schools implement periodic assessments to gain up-to-date information about what each student knows and can do so that teachers can target teaching to the learning needs of every child (schools.nyc.gov). Many public schools in New York City have been implementing computer-based periodic student knowledge assessments that make use of machine learning technologies including computer adaptive testing (CAT) where the test presents the student progressively harder or easier questions depending on whether they answer the previous question correctly (Cope & Kalantzis, 2016).

Machine learning in student knowledge assessment seems to be a very useful tool for increasing the validity and efficiency of these assessments and providing scores to educators in that they provide more accurately calibrated scores for students across a broader range of capacities and can reach an accurate score faster than manual grading for educators to refine which subject areas and content need improvement to guide future instruction. This also allows for equality to increase for students with disabilities and to identify which students may be falling behind compared to their peers since learning gaps between students will often vary, so the results of these tests will more accurately provide information to educators about which subject areas these students will need extra support.

References:

Alruwais, Nuha, and Mohammed Zakariah. 2023. "Evaluating Student Knowledge Assessment Using Machine Learning Techniques" Sustainability 15, no. 7: 6229. https://doi.org/10.3390/su15076229

Cope, B., & Kalantzis, M. (2016). Big Data Comes to School: Implications for Learning, Assessment, and Research. AERA Open, 2(2). https://doi.org/10.1177/2332858416641907

“Periodic Assessments.” schools.nyc.gov. Accessed February 11, 2024. https://www.schools.nyc.gov/learning/testing/periodic-assessments.