Vocational education generates information in several different forms. A student may be associated with a particular course, complete a sequence of activities, receive scores on assessments and display patterns of engagement over time. In a conventional spreadsheet, these elements are usually stored in separate columns or tables. That format preserves individual values but can obscure the relationships among them. A knowledge graph instead represents information as entities and links: a student is enrolled in a course, a course contains activities, an activity contributes to an assessment and an assessment records a result. Such graphs are especially useful when the meaning of a data point depends on its context. A low score, for example, may mean something different when it follows repeated difficulty with prerequisite activities than when it appears as an isolated result.

The researchers’ approach was designed to address a persistent weakness in educational prediction systems: the tendency to treat tabular variables and contextual relationships as independent sources of information. Their architecture first constructed a knowledge graph from multimodal vocational-education data, with nodes representing students, courses, activities and assessments. It then applied Node2Vec, an embedding method that translates graph structure into compact vectors. Node2Vec performs simulated walks through a network, recording which nodes tend to appear near one another and using that information to position related entities close together in a lower-dimensional mathematical space. The resulting vector does not simply describe a student’s raw score or a course’s title; it encodes patterns of connectivity that may reveal how learners interact with particular content and activities.

Those graph embeddings were combined with tabular attributes before classification by XGBoost, or eXtreme Gradient Boosting. XGBoost builds an ensemble of decision trees sequentially, with each new tree concentrating on errors made by the previous ones. The method is effective for nonlinear relationships and mixed data types, and it can capture interactions that would be difficult to specify manually. In this framework, a learner’s structural position in the knowledge graph could be considered alongside conventional attributes such as assessment-related information. The model’s task was not merely to retrieve existing relationships, but to use the combined representation to predict student outcomes or performance within the educational network.

The reported evaluation metrics were striking across several dimensions. The proposed system reached 0.9898 for accuracy, recall and F1-score, while precision was 0.9899. Accuracy measures the proportion of predictions that are correct overall; precision measures how often positive predictions are correct; recall measures how many of the relevant positive cases the system identifies. The F1-score is the harmonic mean of precision and recall, making it useful when both missed cases and false alarms matter. The model also produced a Matthews correlation coefficient of 0.9848 and a Kappa score of 0.9847. These statistics are intended to account more carefully for agreement and class balance than accuracy alone. An AUC of 0.9999 indicates that the classifier almost perfectly separated the evaluated outcome categories across decision thresholds.

The comparison with baseline algorithms was much less flattering for the conventional approaches tested. K-nearest neighbours achieved an accuracy of 0.5903, while Naïve Bayes reached 0.5344 and logistic regression recorded 0.9466. K-nearest neighbours classifies a case according to the labels of nearby examples in feature space, but it may struggle when the representation does not preserve the underlying educational context. Naïve Bayes assumes conditional independence among features, an assumption that is often unrealistic when courses, activities and assessments are tightly connected. Logistic regression performed considerably better, but its linear decision structure may not capture the more complex patterns represented by graph embeddings and gradient-boosted trees. The results therefore suggest that the advantage came from the hybrid representation as much as from the choice of classifier.

If developed further, such a system could support adaptive learning platforms that modify recommendations as a learner’s progress changes. A graph-based model might help identify activities associated with a concept a student has not mastered, connect that weakness to prerequisite material, or flag a learner whose assessment pattern resembles previous cases requiring additional support. Instructors could potentially receive earlier indications that a student is falling behind, while course designers could examine links between activities and performance across a programme. Because knowledge graphs preserve explicit entities and relationships, they may also offer a more interpretable basis for educational decisions than a prediction generated solely from an opaque numerical model. A teacher could inspect the network paths or associated features contributing to a classification rather than receiving only a probability.

The researchers caution, however, that the headline numbers should not be mistaken for proof that AI can reliably forecast every student’s future. The study’s stated limitations include the scope of the dataset and the generalizability of the results across institutions. A model trained on one collection of vocational-education records may encounter very different curricula, grading practices, student populations or patterns of technology use elsewhere. Near-perfect test performance can also arise when data contain strong signals specific to the evaluation set, or when related records are divided between training and testing in ways that make prediction easier than it would be in real deployment. Independent validation, institution-level testing and prospective studies would be needed to determine whether the model can maintain its performance on genuinely unseen learners and programmes.

The work also highlights a broader technical and ethical challenge in educational AI: prediction is only useful when it leads to appropriate action. A system that identifies a student as high risk could help direct tutoring and resources, but an incorrect classification could influence expectations or limit opportunities. Graphs built from educational data must be carefully governed because they can connect personal performance with courses, behaviours and institutional records in ways that expose sensitive patterns. The authors report that their study did not involve human participants, patient data, animals or experimental procedures requiring ethical approval, and that it received no external funding. For now, the framework is best understood as a promising research architecture rather than a ready-made replacement for teachers. Its most important contribution may be the demonstration that educational prediction can benefit when AI learns not only from what students score, but also from how learners, knowledge and assessment experiences are connected.

The rapid acceleration of digital technology has heralded an era where artificial intelligence becomes integral to educational environments. AI tools are not merely enhancements; they reconfigure learning paradigms. From personalized learning experiences that adapt to individual student needs to AI-driven analytics that inform teaching methods, the implications are profound. The study’s authors aim to decode these phenomena by examining various dimensions of AI tool adoption, addressing both the enthusiasm and skepticism surrounding these innovations.

Within the framework of UTAUT2, the researchers explore multiple factors influencing AI adoption. Performance expectancy, effort expectancy, social influence, facilitating conditions, hedonic motivation, and price value all play pivotal roles in determining how students engage with AI technologies. The authors meticulously detail each construct, illuminating how they converge and diverge in relation to the educational context. This nuanced understanding informs educators, policymakers, and technology developers about the driving forces behind AI tool utilization.

Interestingly, the study reveals a disparity in AI adoption trends between different educational levels. University students exhibit a higher propensity for AI tool adoption compared to their school counterparts. This variance may stem from differences in technological fluency, access to resources, and the nature of educational demands at varying academic stages. Insight into these distinctions allows stakeholders to tailor AI solutions that cater specifically to the needs of different learning groups.

Moreover, the authors illuminate the critical importance of facilitating conditions, which include access to technology, training, and support systems. In an educational setting, these conditions can significantly mediate the user experience. Notably, schools and universities must invest in robust infrastructure and provide comprehensive training for both students and educators to maximize the potential benefits of AI tools. Without such support, even the most sophisticated technology may fail to gain traction.

Social influence also emerges as a key driver in the study, emphasizing the role peer behaviors and societal norms play in shaping individual attitudes toward AI adoption. As students witness their peers effectively harnessing AI for academic success, they are more inclined to engage with these technologies themselves. This insight can lead to initiatives that foster positive peer influence and promote collaborative learning environments where AI tools can be effectively integrated.

Another fascinating aspect of this research pertains to hedonic motivation, reflecting the enjoyment derived from using AI educational tools. Students who find learning engaging and enjoyable are inherently more likely to adopt these technologies. This finding serves as a powerful testament to the importance of creating interactive, gamified learning experiences that not only educate but also entertain. Educational institutions can thus innovate by designing AI tools that captivate students’ imaginations and stimulate their intrinsic motivation to learn.

The issue of price value also resurfaces as a critical consideration in AI adoption. For many educational institutions, budget constraints are an ever-present challenge. The research suggests that perceived value relative to costs heavily influences students’ inclination to adopt AI tools. Thus, stakeholders must emphasize demonstrating the tangible benefits of these technologies to foster a willingness to invest in AI-enhanced educational resources. Clear evidence of improved learning outcomes will be central to convincing policymakers and institutions to allocate funding for such initiatives.

Delving deeper into the implications of the research, it becomes evident that understanding the nuances of AI tool adoption is crucial for the development of educational policy. Policymakers must consider how various factors interact in the unique context of education, ensuring that access to AI tools is equitable and that training programs are adequately funded. As AI continues to permeate educational systems, an informed policy approach will account for the diverse needs of students, educators, and educational institutions alike.

Ultimately, Mistry and colleagues’ research underscores the dynamic interplay between technology and education. The findings hold promise not just for enhancing individual learning experiences but also for redefining educational pedagogies in the digital age. As AI becomes more embedded in education, understanding these adoption dynamics may lead to improved student outcomes and a more effective educational landscape.

In conclusion, this comprehensive study provides invaluable insights into the adoption and usage of AI tools in education, specifically within the context of Surat city’s students. The UTAUT2 framework serves as a robust lens through which to examine this complex phenomenon, shedding light on the multifaceted factors that drive technology acceptance. As educators, researchers, and policymakers strive to harness the power of artificial intelligence in education, studies like this one are pivotal in guiding future initiatives and ensuring that AI tools serve to benefit all learners in their pursuit of knowledge.

As we continue to witness the evolution of education in a technology-driven world, it is paramount that we remain vigilant in understanding the forces at play in the adoption of AI tools. The future of education may very well hinge on how effectively we embrace and integrate these innovative technologies, shaping not only the landscape of learning but also the future of society at large.

Subject of Research: Adoption and use of artificial intelligence tools in education among school and university students.

Article Title: Adoption and use of artificial intelligence tools in education: a UTAUT2-based study of school and university students in Surat city.

Article References:

Mistry, A., Jhala, P., Maheta, D. et al. Adoption and use of artificial intelligence tools in education: a UTAUT2-based study of school and university students in Surat city. Discov Educ 4, 551 (2025). https://doi.org/10.1007/s44217-025-00979-5

Image Credits: AI Generated

DOI: https://doi.org/10.1007/s44217-025-00979-5

Keywords: Artificial intelligence, education, UTAUT2, technology adoption, learning outcomes, student engagement.