The rapid expansion of online education has generated large volumes of learner interaction data, highlighting the need for intelligent systems capable of transforming this information into personalized guidance. Educational Recommender Systems (ERS) represent a key application of big data analytics and machine learning, offering adaptive learning pathways that respond to diverse student needs. For widespread adoption, these systems must align with pedagogical principles while ensuring transparency, interpretability, and seamless integration into Learning Management Systems (LMS). This paper introduces a comprehensive framework and implementation of an ERS designed for platforms such as Moodle. The system integrates big data processing pipelines to support scalability, real-time interaction, and multi-layered personalization, including data collection, preprocessing, recommendation generation, and retrieval. A detailed use case demonstrates its deployment in a real educational environment, underlining both technical feasibility and pedagogical value. Finally, the paper discusses challenges such as data sparsity, learner model complexity, and evaluation of effectiveness, offering directions for future research at the intersection of big data technologies and digital education. By bridging theoretical models with operational platforms, this work contributes to sustainable and data-driven personalization in online learning ecosystems.

Due to its inherent flexibility and adaptability, e-learning has become a versatile and effective educational option, with video-based learning (VBL) enabling asynchronous engagement. Despite the wealth of video resources, evaluating their effectiveness remains challenging. This study employs a comprehensive approach, analyzing student behavior and video metadata to assess educational videos’ efficacy. Metrics such as average playback speed, video and course completion rates, and video metadata were examined using the XuetangX dataset, MOOC- CubeX. Results indicate that viewing patterns are more influenced by students’ choices than by video content. Well-conceptualized videos increase viewing time, with 17 % of students engaging with videos over 30 min if they cover focused topics. While shorter videos generally have higher completion rates, many remain untouched. Playback speed analysis shows a preference for standard speed, with positive correlations between speed and both completion percentage and viewing time. Courses under 5 h are likely to be watched for less than an hour, reflecting brief viewing durations. Metadata analysis reveals that generic titles may deter engagement, underscoring the importance of precise tagging and content relevance for enhancing student interaction.