When using machine-learning techniques to determine algorithms or ranking models that identify student satisfaction, algorithms are often trained and tested on a single data set, leading to bias in their performance metrics. This article aims to identify the best algorithm to classify the satisfaction of university students applying the K-fold cross-validation technique, comparing the error rates of the performance metrics before and after its application. The method used began with the collection of student opinions on the teaching performance of the social network Twitter during an academic semester. Then, sentiment analysis was used for data processing, through which it was possible to categorize the opinions of the students into “satisfied” or “dissatisfied.” The results showed that the algorithm with the lowest error rate in its performance metric was the support vector machine (SVM). In addition, it was identified that its classification probability reached an accuracy of 91.76%. It is concluded that SVM classification using K-fold cross-validation will contribute to determining which factors associated with the teacher’s didactic strategies should be improved in each class session, since traditional surveying techniques have shortcomings.

Satisfaction with teaching performance is an important measurement process in higher education institutions, for this reason, applying sentiment analysis to the opinions of university students through the support vector machine (SVM) Fine Gaussian supervised learning algorithm represents an important contribution to the academic literature. This article identifies the best classification algorithm according to performance parameters for predicting student satisfaction with teaching performance through sentiment analysis; the subsequent implementation of the research has the purpose of strengthening teaching practices, in addition to allowing continuous training of teaching for the benefit of student learning. This article has provided a compact predictive model, with literature review based on SVM and sentiment analysis techniques. Through the machine learning classification learner technique, it is identified that the SVM algorithm: Fine Gaussian SVM is the one with the best accuracy equal to 98.3%. Likewise, the performance metrics for the four classes of the model were identified, which have a sensitivity equal to 88.89%, a specificity of 98.04%, a precision of 99.21% and an accuracy of 98.85%.

Circular economy learning fosters competencies in sustainable resource management and environmental protection, which have been recognized by the OECD (Organization for Economic Cooperation and Development) to be essential for cross-curricular training and higher education. However, implementing gamification techniques through mobile applications remains challenging, as their effectiveness depends on students’ willingness to adopt them. This study evaluated acceptance of a gamified mobile application for circular economy learning among university students in Peru, analyzing the relationships between the constructs of the Technology Acceptance Model (TAM). A quantitative correlational case study involving 76 students was conducted. The results showed a moderate-to-high acceptance rate of 73.69%, with significant correlations identified between the TAM constructs. This study contributes to closing gaps in empirical evidence on the acceptance of technology for sustainability education in diverse contexts. Future studies should integrate generative artificial intelligence into gamified apps to deliver personalized feedback and employ learning analytics tools for progress tracking, supporting global efforts toward SGD 4 (Quality Education) and SDG 12 (Responsible Production and Consumption) for the transition to circular economies.

During the context of COVID-19, educational processes migrated to a strictly virtual scenario, so the quantity of information grew in such a way that techniques such as data mining or machine learning contributed to generating knowledge for decision-making. In this sense, it is relevant to define the state of the art of the contributions of data mining in the university environment, and from there, to see in perspective how these could be applied in scenarios of return to the face-to-face. In this sense, a systematic review of the literature is carried out, based on scientific evidence extracted from the Taylor & Francis, ERIC and Scopus databases. A qualitative content analysis approach and the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) statement were used to extract the findings published in scientific articles. The results were that educational data mining was applied to a greater extent in the field of “teaching”, and it was focused on the search for patterns and predictive models to improve student performance, reduce student dropout, improve the student’s quality of life, and teacher performance. In addition, as a resource for data extraction, university learning management systems (LMS) were used to a greater extent. It is concluded that tools such as data mining should be implemented as academic management policies, achieving a prospective on indicators linked to the improvement of student learning and performance.

La presente investigación tuvo como objetivo determinar la relación que existe entre las tecnologías educativas, habilidades sociales y la toma de decisiones en estudiantes universitarios de la facultad de Ingeniería Industrial de una universidad privada de Lima. Este estudio fue de tipo básica, diseño no experimental-transversal. La población estuvo constituida por 80 alumnos. Se utilizó la técnica de la encuesta y su instrumento el cuestionario, con preguntas tipo escala de likert. Los resultados permitieron determinar que existe una relación significativa entre las tecnologías educativas, habilidades sociales y la toma de decisiones, con una significancia menor a .05.

La presente investigación tuvo por objetivo determinar la calidad de citas y referencias de las tesis de Maestría en Educación de universidades peruanas. Se utilizó la técnica del análisis documental y como instrumento se recurrió a la “Guía de observación” propuesta por Martín y Lafuente (2017), compuesta por cinco indicadores de calidad para la revisión bibliográfica (exhaustividad, utilización crítica de la bibliografía, calidad, relevancia y revisión de investigaciones previas); y nueve para las referencias bibliográficas (actualización, cantidad de referencias, autocitación, idioma, tipología, soporte, referencias completas, exactitud y cumplimiento con una norma o estilo). El análisis se realizó a 562 referencias bibliográficas y 1209 citas extraídas de 14 tesis, digitalizadas y publicadas en el Repositorio Nacional Digital de Perú, durante el año 2017. Se evaluaron tanto los mecanismos de citado, como las referencias bibliográficas. Después del análisis estadístico descriptivo se pudo identificar que el nivel alcanzado para ambas variables fue “suficiente”.