E-learning systems, which are used for teaching complex software, can facilitate learning if they provide an appropriate teaching approach that decreases learners’ cognitive load in addition to providing practical knowledge. We believe there is lack of cognitively guided educational recommendations on how to effectively and efficiently design such learning platforms. We thus provide an integrative review paper that overviews relevant literature to cognitive load theory to provide practical solutions and an empirically validated framework to decrease learners’ cognitive load and improve the learning of complex software through E-learning systems. The solutions (which contain practical examples) are proposed based on different concepts of cognitive load theory including using analogies, worked examples and infographics to facilitate schema acquisition; keeping learners’ concentration on the target tools by preventing split-attention and redundancy effects and applying the training wheel method; using interactive videos based on embodied cognition theory and finally considering the modality and transient information effects in designing E-learning systems. These solutions are related to adapting the learning platform to human cognitive structures and can lead to increased learning performance by preventing working memory from being overwhelmed, thus facilitating the formation of schemas and resulting in more efficient and reliable learning with less effort.

Learners’ emotional states might change during the learning process, and unpredictable variations of a person’s emotions raise the demand for regular assessment of feelings during learning. In this paper, an AI-based decision framework is proposed and implemented for e-learning systems that identify suitable micro-brake activities based on the learner’s emotional state through an evolutionary genetic algorithm to change learner’s mood and increase learning performance. This proposed framework was tested using a case study of English as a second language learner during one semester. The students were divided into two groups of participants (each group containing twenty students, forming a total of 40 students). The results of this study demonstrated the importance of learners’ emotions in their learning performance and proved the effectiveness of our proposed framework and the success of the recommended micro-break activities chosen based on learners’ emotions and preferences. The findings of this study have important practical implications in designing adaptive e-learning systems and learning management systems such as Moodle. They also contribute to theoretical implications in the field of AI and learner emotions by suggesting a novel approach to identifying, categorizing, and offering a learning path that can cater to the needs of individual learners.

Les effets de l’accroissement des interactions entre les apprenants et un système de E-learning ont été étudiés dans l’expérience 1, tandis que l’accroissement des interactions via un agent pédagogique a été étudiée dans l’expérience 2. Dans l’expérience 1, nous avons comparé un système d’apprentissage en ligne avec et sans animation interactive pour enseigner des logiciels à des utilisateurs novices. L’animation interactive a considérablement réduit la charge cognitive dans la phase d’apprentissage pour les contenus ayant un fort ou un faible niveau de complexité, cependant, elle n’a pas eu d’effet significatif sur l’évaluation des connaissances. Les effets positifs d’une animation interactive peuvent s’expliquer par la cognition incarnée, qui établit des liens entre l’esprit et le corps, permettant au mouvement de soutenir les tâches cognitives. Dans l’expérience 2, les interactions entre le contenu à apprendre et les apprenants ont été accrue en proposant un avatar, parlant et animé, qui ne nécessitait aucune activité supplémentaire de la part des apprenants, éliminant ainsi les effets de cognition incarnée. Les résultats ont montré que lorsque l’avatar était utilisé avec d’autres éléments visuels, il augmentait la charge cognitive des étudiants. Ce résultat est cohérent avec l’effet de redondance, en particulier pour les contenus très complexes.

Frequent ambiguities in contract terms often lead to costly legal disputes and project delays in the construction industry. Large Language Models (LLMs) offer a promising solution, enhancing accuracy and reducing misinterpretations. As studies pointed out, many professionals use LLMs, such as ChatGPT, to assist with their professional tasks at a minor level, such as information retrieval from the Internet and content editing. With access to a construction regulation database, LLMs can automate contract interpretation. However, the lack of Artificial Intelligence tools tailored to industry regulations hinders their adoption in the construction sector. This research addresses the gap by developing and deploying a publicly available specialised chatbot using the ChatGPT language model. The development process includes architectural design, data preparation, vector embeddings, and model integration. The study uses qualitative and quantitative methodologies to evaluate the chatbot’s role in resolving contract-related issues through standardised tests. The specialised chatbot, trained on construction-specific legal information, achieved an average score of 88%, significantly outperforming ChatGPT’s 36%. The integration of a domain-specific language model promises to revolutionise construction practices through increased precision, efficiency, and innovation. These findings demonstrate the potential of optimised language models to transform construction practices.