Multimodal Conversational Learning to Improve Mathematics Learning in Low-Resource School Settings in Peru

Castillo-Ojeda A.V.; Gabriel-Corilloclla K.; Lazaro-Trinidad L.D.; Ticona L.G.P.; Raez S.S.V.; Rodriguez-Baca L.S. · International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2025 (2025) · DOI: 10.1109/iceccme64568.2025.11277754

Resumen

This study aimed to determine how a multimodal conversational agent improves mathematics learning among students at an educational institution located in Ate, contributing to SDG 12: Responsible Consumption and Production. This study was applied, with a quantitative approach, experimental design, and explanatory scope. The population was 110, and the study sample was 52 students from a public educational institution. The techniques used included observation data sheets, and the instrument used was the registration form. The findings showed that mathematics learning improved from an average of 4.88 to 7.47. The Wilcoxon test was also used to test hypotheses. The significance level obtained was less than 0.05, confirming that the multimodal conversational agent improved mathematics learning. It was concluded that the implementation of the conversational agent did significantly improve mathematical learning. The data obtained from the pretest and posttest showed significant progress, demonstrating that the chatbot efficiently assisted students, a fact that was beneficial for their performance.

Instituciones: Universidad César Vallejo