Editorial: The Contemporary Landscape of Smart Learning Environments ^†

1. Introduction

Educational Technology (EdTech) has moved decisively beyond its early role as a digital substitute for textbooks and classrooms. Today, it is a complex ecosystem in which artificial intelligence, data analytics, game design, creative technologies, and large-scale digital platforms are reshaping how teaching is designed, delivered, assessed, and governed. The current phase of EdTech is marked by three dominant movements: the rise of AI- and data-driven personalization, the mainstreaming of game-based and creative pedagogies, and the growth of integrated educational platforms that connect learning with administration, industry, and society. The papers in this Special Issue clearly reflect this transition. Together, they show an EdTech field that is no longer experimental but rather infrastructural, embedded in everyday educational practice, yet still navigating questions surrounding pedagogy, ethics, creativity, and transformation.

Across the literature, there is a recurring tension between “enhancement” and “transformation.” Many technologies improve efficiency, feedback, or access, but fewer fundamentally redesign learning itself. This tension is especially visible in AI systems, game-based learning, and large-scale platforms. This collection of research articles demonstrates an education technology field that is rich in innovation but still defining what it means for technology to genuinely transform education rather than merely automate it.

2. AI and Machine Learning in Education

AI and machine learning (ML) now sit at the core of contemporary EdTech. They enable personalization, automate feedback, generate content, and analyze learning processes at a scale not previously possible. However, their pedagogical impact varies widely, from simple automation of existing practices to fully new learning experiences.

A strong illustration of applied AI is PyChatAI, an AI chatbot designed to support programming education, as shown in Contribution 1. It provides learners with support in theory, coding, debugging, and problem-solving through conversational interaction. This study’s empirical results show that such systems can significantly improve learning outcomes when compared with traditional instruction, particularly by offering immediate, individualized feedback. This reflects a broader shift toward conversational interfaces as a primary medium for learning.

However, deploying AI is not only about building systems; it is also about evaluating them meaningfully. A framework proposed for evaluating GenAI chatbots through learning analytics demonstrates this clearly, as shown in Contribution 2. By combining interaction data, clustering methods, and learning outcome measures, this work demonstrates how AI systems can be assessed not only for usability but also for actual pedagogical impact. This connects AI directly with learning analytics, positioning data as the bridge between technological innovation and educational evidence.

Generative AI also appears in more creative and exploratory contexts, as shown in Contribution 3. In art education, research on generative AI tools indicates that these systems are highly effective at supporting ideation and early-stage concept development but less effective at supporting fine-grained artistic skill or craftsmanship. This highlights a key pattern in AI-based learning: AI is most powerful as a cognitive partner—helping learners explore, generate, and reflect—rather than as a replacement for human creativity or expertise.

Learning analytics itself is becoming increasingly multimodal. Research on automating the processing of eye-tracking and galvanic skin response data demonstrates how physiological data can be transformed into learning analytics pipelines using machine learning tools, as shown in Contribution 4. This takes learning analytics beyond clickstreams and log files into embodied measures of attention, stress, and engagement, presenting new possibilities for understanding learning processes.

Language learning and literacy also benefit from AI-driven personalization. An AI-based children’s dictionary for low-resource languages shows how machine learning and generative tools can support vocabulary learning where traditional resources are scarce, as shown in Contribution 1. This highlights an important ethical and social dimension of AI in education: its potential to address inequities in access to learning materials.

Creative learning also increasingly relies on intelligent systems. In Contribution 6, a portrait drawing learning assistant uses computer vision and normalized cross-correlation to compare student drawings with reference images, providing detailed automated feedback on facial features. This demonstrates how AI can support domains traditionally considered subjective or resistant to automation, such as art.

At a more structural level, Intelligent Tutoring Systems (ITSs) are among the oldest and most established forms of AI and ML in education. In Contribution 7, a systematic review of ITS in mathematics education shows that while ITSs are widespread and effective, most are used at the “augmentation” level—improving traditional instruction rather than transforming it. Only a small number of ITS redesigns learn in fundamentally new ways, such as through learning-by-teaching models. This finding echoes across many AI systems in that technological sophistication does not automatically lead to pedagogical transformation.

Finally, research on educational data mining and predictive modeling provides a broader context for all AI-driven systems. In Contribution 8, a large-scale review of educational data mining (EDM) shows rapid growth in predictive analytics, early warning systems, and performance modeling, alongside rising concerns about bias, privacy, and ethics. AI in education is therefore not just a technical challenge but also a governance and values-based challenge.

3. Game-Based Learning and Creative Pedagogies

Game-based learning has matured from novelty to a mainstream pedagogical strategy. It now includes not only serious games and gamification, but also creative platforms, narrative environments, and playful assessment models.

One important development is the integration of learning analytics into serious games. In Contribution 9, research on serious games for programming demonstrates that in-game traces can be analyzed to understand learner strategies and difficulties, enabling designers to iteratively refine both pedagogy and game mechanics. This positions games not merely as engaging tools, but as data-rich learning environments.

Game-based learning is also moving toward formal assessment. In Contribution 10, the study of a game-based exam implemented on the Genial.ly platform demonstrates that summative assessments can be delivered through narrative-driven, interactive games, thereby reducing student stress while maintaining academic rigor. This is significant as it challenges the long-standing separation between “play” and “testing,” showing that assessment itself can become a learning opportunity.

Creative and artistic domains are increasingly aligned with game-like and interactive structures. In Contribution 6, the portrait drawing assistant, although technically an intelligent tutoring system, also functions as a creative learning environment where learners interact with visual feedback loops similar to those in games. Likewise, generative AI in art education encourages exploratory, playful interaction with ideas, blurring the boundary between tool and creative partner, as shown in Contribution 3.

Language and literacy technologies also align with game-based and playful learning. The AI children’s dictionary employs adaptive and generative techniques to support vocabulary learning in an exploratory, learner-driven manner, as shown in Contribution 5. While not a game in a strict sense, it shares core features of game-based learning, i.e., interactivity, feedback, and intrinsic motivation.

These studies collectively show that game-based learning is no longer limited to “educational games.” It now includes narrative exams, creative platforms, AI-assisted creativity, and playful analytics-driven environments. However, like AI systems, many game-based tools still enhance existing practices rather than fully redefining pedagogy. The challenge remains to design games that do more than motivate and fundamentally reshape how knowledge is constructed, practiced, and assessed.

4. Education Platforms and Institutional Infrastructure

Beyond classroom tools, EdTech increasingly operates at the platform level—integrated systems that connect learning, administration, industry, and data.

The IoT–ML practicum platform exemplifies this trend in technical education. In Contribution 11, by allowing students to design IoT systems, stream data, apply machine learning models, and visualize results within one environment, it creates a realistic simulation of industry workflows. This is not merely a teaching tool but a learning ecosystem that aligns curriculum with professional practice.

At the institutional level, generative AI is also entering administrative and strategic domains. In Contribution 12, the study of GenAI in higher-education customer relationship management shows how AI is being used in recruitment, advising, alumni relations, and student support. This represents a shift from EdTech as classroom technology to EdTech as institutional infrastructure, shaping how universities interact with learners across the entire education lifecycle.

5. Conclusions

The current state of EdTech is defined by integration: AI with pedagogy, games with assessment, creativity with computation, and learning with institutional platforms. The papers in this Special Issue demonstrate a field rich in innovation but still in the process of defining its identity. AI systems personalize and automate, but do not always transform. Games engage and motivate, but do not always redefine learning. Platforms connect education to industry and administration, but raise new ethical and structural challenges.

Editorially, these articles collectively argue that the future of EdTech depends not on technological novelty, but on pedagogical intention. The real challenge is not building smarter systems, more engaging games, or larger platforms—but deciding what kind of learning, creativity, and educational society these technologies are meant to serve.