Inteligencia artificial para la mejora de la evaluación docente en una universidad privada peruana

• Autor: Díaz Rosemberg, Arturo Gustavo
• Formato: tesis de maestría
• Fecha de Publicación: 2024
• Institución: Pontificia Universidad Católica del Perú
• Repositorio: PUCP-Tesis
• Lenguaje: español
• OAI Identifier: oai:tesis.pucp.edu.pe:20.500.12404/30551
• Enlace del recurso: http://hdl.handle.net/20.500.12404/30551
• Nivel de acceso: acceso abierto
• Materia: Maestros universitarios--Perú--Evaluación; Tecnología educativa--Perú; Inteligencia artificial; Procesamiento de lenguaje natural (Computación); https://purl.org/pe-repo/ocde/ford#2.00.00

This work is carried out at a Peruvian university with multiple campuses, which currently has more than 72,000 students and 3,666 teachers. For this institution, having a considerable teaching staff and student body, it becomes a priority to have quantifiable information on students' perception of teachers' performance. To address this need, the analysis of student surveys is proposed, using sentiment analysis and classification of responses to an open-ended question, based on artificial intelligence. The objectives of this innovation proposal focus on optimizing the interpretation of teacher evaluation survey results using artificial intelligence. Specifically, it seeks to automate the analysis of open-ended survey questions using natural language processing and provide qualitative reference metrics with these results. Finally, using classification, it is proposed to train a model that can identify outstanding responses that help identify a particular problem with a course or a teacher. The proposed solution aims to be a tool that allows for quick action by university administrators and to consider the open-ended responses of surveys, which is often information that can go unnoticed, particularly in large institutions like this one.