Reflective writing is an important educational practice to train reflective thinking. Currently, researchers must manually analyze these writings, limiting practice and research because the analysis is time and resource consuming. This study evaluates whether machine learning can be used to automate this manual analysis. The study investigates eight categories that are often used in models to assess reflective writing, and the evaluation is based on 76 student essays (5080 sentences) that are largely from third- and second-year health, business, and engineering students. To test the automated analysis of reflection in writings, machine learning models were built based on a random sample of 80% of the sentences. These models were then tested on the remaining 20% of the sentences. Overall, the standardized evaluation shows that five out of eight categories can be detected automatically with substantial or almost perfect reliability, while the other three categories can be detected with moderate reliability (Cohen’s κ ranges between .53 and .85). The accuracies of the automated analysis were on average 10% lower than the accuracies of the manual analysis. These findings enable reflection analytics that is immediate and scalable.

By nature, learning is social. The interactions by which we learn from others inherently form a network of relationships among people, but also between people and resources. This paper gives an overview of the potential social network analysis (SNA) may have for social learning. It starts with an overview of the history of social learning and how SNA may be of value. The core of the paper outlines the state-of-art of SNA for technology-enhanced learning (TEL), by means of four possible types of SNA applications: visualisation, analysis, simulation, and interventions. In an outlook, future directions of SNA research for TEL are provided.

Despite their importance for educational practice, reflective writings are still manually analysed and assessed, posing a constraint on the use of this educational technique. Recently, research started to investigate automated approaches for analysing reflective writing. Foundational to many automated approaches is the knowledge of words that are important for the genre. This research presents keywords that are specific to several categories of a reflective writing model. These keywords have been derived from eight datasets, which contain several thousand instances using the log-likelihood method. Both performance measures, the accuracy and the Cohen's κ, for these keywords were estimated with ten-fold cross validation. The results reached an accuracy of 0.78 on average for all eight categories and a fair to good interrater reliability for most categories even though it did not make use of any sophisticated rule-based mechanisms or machine learning approaches. This research contributes to the development of automated reflective writing analytics that are based on data-driven empirical foundations.

La habilidad para participar y contribuir a los debates es importante para el aprendizaje informal y formal. Especialmente cuando se abordan temas altamente complejos, puede ser difícil apoyar a los alumnos que participan en una discusión grupal efectiva y mantenerse al tanto de toda la información generada colectivamente durante la discusión. La tecnología puede ayudar con el compromiso y razonamiento en debates tan grandes, por ejemplo, puede monitorear cuán saludable es un debate y proporcionar indicadores sobre la distribución de la participación. Un marco especial que pretende aprovechar la inteligencia de grupos de pequeños a muy grandes con el apoyo de herramientas de discurso y argumentación estructuradas es la Inteligencia Colectiva Controvertida (ICC). Las herramientas de CCI proporcionan una fuente rica de datos semánticos que, si se procesan de manera adecuada, pueden generar un sofisticado análisis del discurso en línea. Este estudio presenta un panel de visualización con varios análisis visuales que muestran aspectos importantes de los debates en línea que han sido facilitados por las herramientas de discusión de CCI. El tablero de instrumentos fue diseñado para mejorar la creación de sentidos y la participación en los debates en línea y se ha evaluado con dos estudios, un experimento de laboratorio y un estudio de campo, en el contexto de dos institutos de educación superior. Este artículo informa sobre los resultados de una evaluación de usabilidad del panel de visualización. Los hallazgos descriptivos sugieren que los participantes con poca experiencia en el uso de visualizaciones analíticas pudieron desempeñarse bien en determinadas tareas. Esto constituye un resultado prometedor para la aplicación de tales tecnologías de visualización, ya que las interfaces analíticas de aprendizaje centradas en el discurso pueden ayudar a apoyar el compromiso de los alumnos y su razonamiento en debates en línea complejos.

The wide availability of generative artificial intelligence (AI) for content production has resulted in a growing interest in the area of education, particularly for course content production purposes. This research has mapped out a set of curriculum production tasks and illustrated how generative AI can support three important tasks: the development of course outlines and content, the drafting of assessment instructions and the mapping of learning outcomes to benchmark statements. We evaluated the outputs of the generative AI with five experts: a course production expert, an academic expert, two Learning Design experts and an AI expert. The results indicate that generative AI enabled the generation of plausible content skeletons for content and first drafts of relevant content to aid the course production team’s brainstorming but also highlighted the importance of reviewing generated content. Our research indicates that generative AI can result in shifts in the delivery of these tasks.