Abstract:

Low achievement rates in mathematics of undergraduates in Science and Engineering represent an issue of great concern for universities. Among the very varied causes, one is associated to the mismatch between the students' learning characteristics and the design of instructional materials and practice in online education settings (Turnbull, Chugh, & Luck, 2021).

The objective of this study is to provide an instructional design model based on microlearning for the construction of knowledge and improvement of cognitive skills in mathematical themes distinguished as difficult by low performance students through five domains:
(1) analysis of the learner,
(2) cognitive demands when determining learning outcomes and competencies,
(3) learning strategies and materials,
(4) formative assessment, and
(5) measurement and processing of data from three sources (assessment, satisfaction survey, and facial expression analysis).

To develop the proposal, it was analyzed roles of models used for instructional design to guide principles for analyzing, producing, and revising learning environments (Zhou, Bao, & He, 2023; Branch, Kopcha, 2014). Also, given the potential of Artificial Intelligence in math education as a promising and revolutionary technology to assist math learning environments (Mohamed et al., 2022), image processing techniques were used to obtain student frame sequences.

Data was gathered through video-recorded observations of lessons, and with video frames obtained per student, a facial expression database was generated, in the sense of associating facial expressions and emotions each student exhibits in a math class. That is, through the images, emotions emitted by students during different moments in the class are identified and monitored.

Implications of the proposed model are the improvement of the guidance quality by proposing more effective strategies for the acquisition of knowledge and the development of positive behaviors.

References:
[1] Turnbull, D., Chugh, R. & Luck, J. Transitioning to E-Learning during the COVID-19 pandemic: How have Higher Education Institutions responded to the challenge?. Educ Inf Technol 26, 6401–6419 (2021). https://doi.org/10.1007/s10639-021-10633
[2] Zhou, J., Bao, J. & He, R. Characteristics of Good Mathematics Teaching in China: Findings from Classroom Observations. Int J of Sci and Math Educ 21, 1177–1196 (2023). https://doi.org/10.1007/s10763-022-10291-5
[3] Branch, R.M., Kopcha, T.J. (2014). Instructional Design Models. In: Spector, J., Merrill, M., Elen, J., Bishop, M. (eds) Handbook of Research on Educational Communications and Technology. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-3185-5_7
[4] Mohamed, M. Z. b., Hidayat, R., Suhaizi, N. N. b., Sabri, N. b. M., Mahmud, M. K. H. b., & Baharuddin, S. N. b. (2022). Artificial intelligence in mathematics education: A systematic literature review. International Electronic Journal of Mathematics Education, 17(3), em0694. https://doi.org/10.29333/iejme/12132

Keywords:

Instructional model, math education, facial expression analysis, formative assessment.