The global labor market is changing due to artificial intelligence (AI), causing job losses and new opportunities. One predicted consequence is the emergence of a discrepancy between the skills possessed by employers and employees and those offered by continuing education providers. AI-based systems, such as recommender systems (RS), could help bridge this gap. RS are commonly used in educational settings, though their application in continuing vocational education (CVE) remains limited. This study evaluates two deployed hybrid explainable RS versions for CVE courses provided by a German startup-one using knowledge graphs combined with collaborative filtering and the other employing a deep neural network. These RS generate recommendations from a database of 1,500 courses that six German CVE course providers deliver. The goals of this evaluation study are twofold: to evaluate the status quo of the RS and to explore potential improvements. We evaluated this RS by conducting 26 semi-structured interviews with neutral CVE course counselors in two settings. Group one worked with the RS on fictional cases, while group two used it for a month in real situations. Participants saw value in the RS but noted that the quality of explanations was insufficient. Both groups found the RS easy to use but suggested improvements, such as adding questions on preferred learning formats to enhance recommendations.

Learning analytics are utilized to support learners’ educational needs as well as to enhance their study success, for example, via the use of real-time prompts, motivational dashboards, and appropriate learning interventions, which have been shown to increase students’ academic performance as well as their course retention rates. Yet, the perspective of higher education teachers in utilizing analytics to help analyze, reflect on, and improve their teaching design prior to delivery as well as to monitor and measure how the students engaged with their learning processes has been less recognized. In this paper, we present the results of a systematic review conducted from higher education teachers’ perspective concerning how analytics can be deployed to adapt the curriculum to suit better students’ educational needs in order to increase their study success. Thirty-five key studies were identified showing that analytics have been successful in influencing positively study success via teachers’ academic curriculum intervention. Specifically, via analytics, higher education teachers could rapidly visualize common course pathways and identify any difficulties students experienced in real-time in order to increase their learning experiences and outcomes.

Personalized and adaptive learning environments (PALE) offer benefits for workplace learning because they can account for individual needs and constantly changing work requirements. Yet, the identification of reliable indicators for supporting trusted PALE remains a major challenge. This systematic review provides an overview of empirically investigated indicators of the learning context. Out of an initial set of 28,782 publications, a final sample of 273 key publications was identified, according to predefined inclusion criteria. The synthesis yielded 208 indicators of the learning context that were clustered into 26 dimensions. The findings show that the learning context has been associated with learning processes and outcomes in numerous included studies and should therefore be considered when designing PALE. Future research shall detect the most relevant indicators as well as design and evaluate specific learning interventions based on these indicators.

Technology-and analytics-enhanced self-assessments may provide multiple benefits for learners. However, data analytics approaches currently fail to make full use of educational technology and data for self-assessment. This research focuses on the implementation of an environment for self-assessment including a data-driven dashboard in the context of higher education and examines learners’ usage behaviors of N= 100 learners in three experimentally varied conditions. Findings indicate an intensive use of the self-assessments and data-driven dashboards throughout the semester. However, no differences in the interaction of learners with the different dashboard conditions were found. In conclusion, the design of data-driven dashboards for self-assessments requires valid information about learners, assessment processes, and the context of the assessment to better support the current needs of the learner and provide meaningful feedback to foster learning processes and outcomes.

Feedback has been identified as the most powerful moderator for supporting learning. Learning analytics haven been recognized for opportunities for providing timely and informative feedback to learners when they need it. This study seeks to investigate learners' perceptions and expected benefits of different forms of learning analytics feedback from different sources. In a quasi-experimental study including 230 students, four experimental groups were confronted with five learning scenarios receiving different learning analytics feedback. Findings indicate that perceived benefits from learning analytics feedback varies across different delivery sources and requires informative recommendations. Accordingly, designing and implementing feedback in learning analytics systems is more complex than just providing visualizations of behavioral data.

Vast amounts of educational data created by learners interacting with digital learning tools open up the opportunity to gain insights for improving education at a new level of evidence-based research into learning and teaching. This study is part of a research programme investigating the dynamics and impacts of learning engagement in a challenge-based online learning environment. Learning engagement is a multidimensional concept which includes an individual's ability to behaviourally, cognitively, emotionally, and motivationally engage in an on-going learning process. Challenge-based learning gives significant freedom to the learner to decide what and when to engage and interact with digital learning materials. In light of previous empirical findings, we expect that learning engagement is positively related to learning performance in a challenge-based online learning environment. This study was based on data from the Careers Challenge platform, including transaction data from 8,951 students. Findings indicate that learning engagement in challenge-based online learning environments is, as expected, positively related to learning performance. Implications point toward the need for personalised and adaptive learning environments to be developed in order to cater for the individual needs of learners in challenge-based online learning environments.