General call for paper

Discover the Tracks

We are excited that this year’s conference is moving to a new track-based system! To help potential authors in selecting what track to submit to, we will be hosting two recorded information sessions:

• one on Monday February 3rd at 8AM Eastern Standard Time / 1PM Greenwich Mean Time / 9PM China Standard Time
• and one on Tuesday February 4th at 8AM EST / 1PM GMT / 9PM CST.

Register for the information sessions here: https://pitt.zoom.us/meeting/register/y7reWqgRRmCR1QnZPlwjmg

Please consider attending if you have questions about what track to submit to.

Thus, for its main paper submissions, AIED 2025 solicits empirical and theoretical papers relating to both AI and education in the following lines of research and application, which represent our research tracks:

Track 1 – AIED architectures and tools

Papers submitted to this track should describe novel advances related to the engineering and development of AIED systems. Papers may be concerned with describing proof-of-concepts that demonstrate the feasibility of novel techniques, as well as real- world implementations that show the potential for reuse or adaptation by other researchers. Example research areas with applications in education include, but are not limited to, multi-agent architectures; tangible interfaces, wearables; speech technologies; virtual and augmented reality; A/B experimentation platforms. Innovative, domain-specific learning application architectures and tools also find a home in this track, for example, language, science, engineering, mathematics, medicine, military, industry, sports; scaling up and large-scale deployment of AIED systems. While papers may describe an evaluation of the system or tool with end-users, the primary scientific contribution of papers submitted to this track should be technical and systems-oriented.

Sample Keywords: AI system (e.g., tutoring systems, conversational agents, assessment systems, learning management systems, simulations), AI devices and tools, newly developed, proof-of-concept, feasibility studies

---

Track 2 – Machine learning and Generative AI

Papers submitted to this track should describe advances in or applications of AI-based techniques within education, involving knowledge representation and machine learning. Generative AI-based techniques are also welcome within this track. Data-driven processing techniques  (including educational data mining, deep learning, machine learning) in education will constitute the main focus of this track. Example areas are natural language processing for education, video data mining for education, etc.  Papers will likely address novel contributions related to modeling learner, teacher, and other stakeholder processes and outcomes, or contributions to representing learning domains. Evaluation techniques in this track rely on computational analyses related, for example, to the accuracy, validity, or reliability of predictive or generative models. While papers will likely describe evaluations on previous datasets or newly collected data, the primary scientific contribution of these papers will be to AI and its application.

Sample Keywords: classifiers, predictive models, learner modeling, learning analytics, LLMs, clustering, data mining, process data, deep learning, feature engineering/extraction

---

Track 3 – Learning, teaching and pedagogy

Papers submitted to this track should describe approaches to teaching, learning and evaluations of AIED systems and environments  that relate to pedagogical techniques, learning processes, and outcomes, conceived broadly. Both quantitative (survey, correlational, comparative, experimental etc.) and qualitative (case study, ethnography, phenomenology, grounded theory, action research etc.)  analysis, as well as  mixed-methods approaches are encouraged under this paper category. AIED systems targeted here include, but are not limited, to: AI-assisted tutoring and scaffolding; Motivational diagnosis and feedback; Learner engagement/presence; Interactive pedagogical agents and learning companions; Agents that promote cognition, metacognition, self-regulation, co-regulation, motivation and positive affect; Adaptive question-answering and dialogue, Data-driven modeling (educational data mining, deep learning, machine learning,…); Learning analytics and teaching support, Learning with simulations; Explainability of models for teaching and learning. Learning targeted here refers to both formal and informal learning, including game-based learning;  digital collaborative/cooperative and group learning; social networks; inquiry learning; social dimensions of learning; communities of practice; ubiquitous learning environments; learning through construction and making; learning grid; lifelong learning; learning in informal settings (museum, workplace, etc.); learning in the physical space; learning of motor skills. Evaluations here include studies on human learning. Learning spaces include massive open online courses; remote learning at any learning level including k-12 schools, higher education; synchronous, asynchronous, blended learning; mobile learning; active learning in virtual settings; video-based learning; mixed reality and learning. Papers may involve a novel system or a previously existing system, but the primary scientific contribution should be towards understanding the effects of the system and its features on learners, teachers, or other stakeholders. Studies where the focus of the research is fundamentally on the constructs of learning are suitable for this track.

Sample Keywords: Cognitive, behavioral, affective states of learners, pedagogy, effects on learner

---

Track 4 – Human-centered design and design-based research

Papers submitted to this track should address design principles for AIED systems or methods for designing such systems, as well as broadening understanding of contextual and individual factors that might inform users’ interactions with these systems.  Papers submitted to this track can explore the design, use, and evaluation of human-AI hybrid systems for learning: research that explores the potential of human-AI interaction in educational contexts; systems and approaches in which educational stakeholders and AI tools build upon each other’s complementary strengths to achieve educational outcomes and/or improve mutually. Solutions explored in this track include human-AI partnership: shared decision making between systems and users that promote agency and improve learning. Both quantitative and qualitative analysis user-centered design methods are encouraged under this paper category. Papers may involve the study of systems or prototypes that do not currently contain AI, as long as the primary purpose of the paper is to inform the design of AIED systems, putting the user (human) in the center. Evaluations in this track should focus on human-centeredness, or be a means to support human-centred design; or focus on the design and formative studies of AIED systems; in this context, they may include other aspects of the human side of human-AI interaction, such as on human cognition, affect, motivation, engagement, and attitudes. While these papers may also involve the development of a mockup for a new system, the primary scientific contribution should be towards human-centred design, or principles for the design of features of similar systems in similar contexts (as opposed to focusing on the technical implementation of a specific system).

Sample Keywords: human in the centre AI, human-AI partnership, human-in-the-loop, augmented or hybrid systems, humans in the decision-making/ design process, usability with human involvement

---

Track 5 – Teaching AI

Papers submitted to this track should involve methods, principles, or technologies for teaching AI or supporting the development of AI literacy. This includes studies on skills and knowledge that enable individuals to understand, use, and critically evaluate AI; definitions of AI literacy;  learning to use AI; developing a basic understanding of how AI works; learning to communicate and collaborate with AI;  learning to live with AI, understanding limitations and problems of AI. This track especially welcomes work done by or in collaboration with teachers at all levels, from primary to university education. Papers in this track should preferably be based on empirical studies, including small-scale, classroom sized studies; although larger scale studies and theoretical contributions around the topic of teaching AI are also welcomed. Thus, the primary scientific contribution should be towards analysing or improving methods of teaching AI and development of AI literacy.

Sample Keywords: education about AI, teaching AI, AI literacy, critical reflection on AI applications, data literacy

---

Track 6 – Ethics, Equity, and AIED in Society

Papers submitted to this track should take a perspective on AIED as it relates to society at different levels, more broadly, including the ethics of AIED, or designing AIED systems for a more equitable and just future. This includes AIED equity and inclusion-related theoretical or practical studies on socio-economic, gender, and racial issues; AI-assisted techniques to support students from under-resourced schools and communities; sponsorship, scientific validity, participant’s rights and responsibilities, data collection, management and dissemination. Additionally, it includes papers on ethics of AI in education, such as papers on explainability, transparency, accountability, and responsible AIED; learner consent and opt out; surveillance and privacy; the impact of AIED on teachers, learners and classrooms from an ethics perspective; teacher empowerment and student agency; the community’s responsibility for commercial applications; AIED ethical  frameworks and principles for application. This track also includes AIED for development themes, such as leveraging AI technology to address and improve various aspects of development in societies and education, particularly in low and middle-income countries; AIED divide; AIED unplugged; Low-cost solutions; low-tech solutions; frugal Innovation; Jugaad Innovation. These papers may include systematic reviews of the literature or position papers on a particular issue. Both empirical results and theory are welcome in this track, with the primary contribution towards ethics, equity and society.

Sample Keywords: Bias, algorithmic fairness, privacy, transparency, data collection and reuse-analysis, ethics, population groups (gender, racial/ethnic groups, minorities, cultural differences), the generalizability of models, measurement issues and biases, equity, inclusion

---

Track 7 – Theoretical aspects of AIED and AI-based modelling for Education

Papers submitted to this track should include conceptual or theoretical models, methods, knowledge representation, reasoning related to AIED research and AIED systems.  Papers will likely address novel contributions related to theoretical aspects of modelling learners (including open learner models), teachers, and other stakeholders, contributions to representing learning domains or modelling the processes involved in AIED systems. Other areas include, but are not limited, to theoretical contributions and modelling of: facilitators, tasks and problem-solving processes; models of groups and communities for learning; modeling motivation, metacognition, and affective aspects of learning; ontological modeling; computational thinking and model-building; representing and analysing activity flow and discourse during learning; representing and modeling psychomotor learning. Expanding and evaluating cognitive, motivational and affective theories within AIED context also constitutes a target of this track. Papers in this track can further be using bottom-up and top-down approaches to analyse data, in order to inform motivational, learning, and cognitive theories, and gain better understanding of the socio-cognitive nature of learning. The primary contribution of these papers can be of empirical results analysing theoretical aspects, or direct contributions to theories and theoretical models applicable to AIED.

Sample Keywords: knowledge discovery, theory confirmation, theory modification about learning science, cognition, motivation, gathering empirical evidence with a heavy focus on theory, learner models, user models, domain models