Multimodal learning analytics (MMLA) has become a prominent approach for capturing the complexity of learning by integrating diverse data sources such as video, audio, physiological signals, and digital interactions. This comprehensive review synthesises findings from 177 peer-reviewed studies to examine the foundations, methodologies, tools, and applications of MMLA in education. It provides a detailed analysis of data collection modalities, feature extraction pipelines, modelling techniques—including machine learning, deep learning, and fusion strategies—and software frameworks used across various educational settings. Applications are categorised by pedagogical goals, including engagement monitoring, collaborative learning, simulation-based environments, and inclusive education. The review identifies key challenges, such as data synchronisation, model interpretability, ethical concerns, and scalability barriers. It concludes by outlining future research directions, with emphasis on real-world deployment, longitudinal studies, explainable artificial intelligence, emerging modalities, and cross-cultural validation. This work aims to consolidate current knowledge, address gaps in practice, and offer practical guidance for researchers and practitioners advancing multimodal approaches in education.

Internet and social media have revolutionised the way news is distributed and consumed. However, the constant flow of massive amounts of content has made it difficult to discern between truth and falsehood, especially in online platforms plagued with malicious actors who create and spread harmful stories. Debunking disinformation is costly, which has put artificial intelligence (AI) and, more specifically, machine learning (ML) in the spotlight as a solution to this problem. This work revises recent literature on AI and ML techniques to combat disinformation, ranging from automatic classification to feature extraction, as well as their role in creating realistic synthetic content. We conclude that ML advances have been mainly focused on automatic classification and scarcely adopted outside research labs due to their dependence on limited-scope datasets. Therefore, research efforts should be redirected towards developing AI-based systems that are reliable and trustworthy in supporting humans in early disinformation detection instead of fully automated solutions.

El presente artículo analiza las necesidades y desafíos de los verificadores de hechos en la Península Ibérica, en el marco del proyecto IBERIFIER. Este estudio se centra en la identificación y evaluación de herramientas tecnológicas basadas en inteligencia artificial (IA) utilizadas en la lucha contra la desinformación en España y Portugal. Se destacan los perfiles de los verificadores, las herramientas y flujos de trabajo actuales, así como las necesidades de formación específicas. Se incluyen observaciones preliminares de la dinámica laboral en cuatro redacciones de verificación en España, subrayando las diferencias organizativas y metodológicas entre las entidades. Además, se abordan las limitaciones y oportunidades que presenta la implementación de soluciones de IA en este ámbito. Los resultados muestran que, aunque existen diversas herramientas tecnológicas, la eficiencia y efectividad de estas dependen en gran medida de la integración del factor humano en el proceso de verificación. Finalmente, se proponen directrices y mejores prácticas para mejorar la verificación de hechos mediante el uso de tecnologías avanzadas, subrayando la importancia de la formación continua y la colaboración entre diferentes actores para enfrentar la desinformación de manera efectiva.

This article develops an automatic detection model based on natural learning by designing a useful tool for disinformation monitoring in Telegram that avoids the algorithmic bias of artificial intelligence. It is of relevance the monitoring of online platforms and messaging applications such as WhatsApp and Telegram because they have become tools for circumventing traditional verification controls, and, therefore, for conveying disinformation content. The goal of this work is to contribute with early warning mechanisms that allow early combatting of disinformation (prebunking), especially in media ecosystems prone to the dissemination of false content such as pre-election periods, wars or energy crises. The methodology used applies a systematic and structured approach that allows the design and development of the tool, as well as its subsequent evaluation and optimisation. The main result is the creation of an Artificial Intelligence model capable of detecting disinformation in Telegram, and which also allows the integration of these solutions in the information verification workflow through a friendly and easy-to-use interface, thus contributing to the field of fact-checking. The findings reveal lines of future research, including the adaptation of the tool for other platforms and the integration of new features.