2. Themes and trends in AIED research, 2000 to 2010

A report for the UK’s TLRP Technology Enhanced Learning – AIED Theme. May 2011.

Authors: Joshua Underwood and Rosemary Luckin, The London Knowledge Lab.

Click here to download this report as a printer-friendly PDF.

This is the second in a series of reports on Artificial Intelligence in Education. The series also includes:

- What is AIED and why does Education need it?

- Supporting Integration, Synthesis, Uptake & Reuse of AIED Research


This report is one of the outputs from the Artificial Intelligence in Education (AIED) theme of the Technology Enhanced Learning (TEL) research programme. This initial version of the text will be subject to revisions based upon feedback from readers. The AIED theme within the Personalisation strand of TEL is concerned with exploring the ways in which the work conducted under TEL within and across projects can contribute to the (inter)discipline of AIED.

In this document we aim to identify major themes in AIED research over the last decade through analysis of the contents of the International Journal of Artificial Intelligence in Education and the biannual AIED & Intelligent Tutoring System conference programmes. We also point to emerging AIED interests and research challenges for the next decade drawing on recent analyses of the field (e.g. Brna, 2009; Dimitrova, 2010; Luckin, 2010; Woolf, 2010).

Core themes in AIED research over the last decade

Every year the ITS & AIED conference committees organise accepted papers into related groups with common themes. Often the committee identifies a range of appropriate themes that are listed in the call for papers and paper authors choose which themes to identify their work with. Clearly, many papers relate to multiple themes and there is a pragmatic element in the choice of which papers to group together in sessions. Consequently the themes identified in conference programmes and proceedings will not provide an accurate overview of the amount of work in any area and may not reveal emerging themes in which little research has been conducted. Nevertheless, these themes do give some indication of consistent and emerging topics in AIED research over the last 10 years, reflecting topics the committees and authors have chosen to identify as important (see Table 1).

Table 1 shows that Agents, Collaborative Learning, Dialogue Systems, Narrative and Games, Pedagogic Strategies, Authoring Tools, Evaluation, Learner Modelling, Hypermedia & Web-based systems have remained as consistent core themes throughout the decade. The fact that Evaluation is not recognised as a separate theme in 2009 and 2010 is perhaps due to increasing emphasis on including evaluation as a necessary component of work reported in all research themes. Research in Affect & Motivation has also been present throughout the decade but the amount of research in this area has increased considerably. Other themes that appear to be receiving increasingly more attention are: Ontologies & Semantic Web, Data-mining, Machine-Learning, support for Meta-cognition and support for learning in Ill-defined Domains.

In 2009 the outgoing editor of the International Journal of Artificial Intelligence in Education (IJAIED) suggested that main themes in the journal through the decade had been Agents, aspects of Pedagogy, Collaborative Learning, Learner Modelling and Open Learner Modelling (OLM) and Evaluation (Brna, 2009). Other themes present in IJAIED during the decade are Approaches to Feedback, Adaptive Testing, Constraint-based Modelling, Modelling Teaching, Natural Language Processing, Dialogue Systems, Web-based Systems, Design Methods, Narrative Interactive Learning Environments, Affect, Machine Learning and the Semantic Web. Brna (2009) suggests that there has been growth in the number of papers addressing issues in OLMs, Agents, Meta-cognition and Self-regulated Learning but surprisingly little published around use of the Semantic Web and Ontologies, Mobile Learning and Design Methodologies for AIED. Brna (2009) goes on to suggest the need for more papers reporting work in Motivation and Affect, Adaptive Assessment, Research Methodology and Evaluation of AIED systems in Authentic Real World Situations. Building on Brna’s analysis and word cloud representation of keywords in IJAIED papers (Brna, 2009, p.2) we produced a word cloud, using Wordle (a tool for generating “word clouds” from text – http://www.wordle.net), to show frequently repeated topics in IJAIED paper titles between 2000 and 2009 volume 20 issue 2 (see Figure 1).

Table 1. Main themes in ITS & AIED conference programmes/proceedings 2001-10

Figure 1. Frequently repeated topics in titles of IJAIED papers 2000-2009.

Our analysis of topics in IJAIED paper titles between 2000-2009 reveals many of the themes identified by Brna (2009) as well as some other prominent themes and sub-themes (e.g. Bayesian, Case-based, Decision Theory, Model-tracing and Constraint-based approaches, Cognitive Tutors, Hybrid Systems, Self-improving systems, Learning Companions and Learner Centred Design methods) and traditional (Algebra, Physics) and emerging application domains (Meta-cognitive support, Open-ended learning). To a great extent themes for special issues of IJAIED over the last decade (see Table 2) reflect the themes identified above. However, a recently added two volume special issue on AIED systems for ill-defined domains (Aleven, et al., 2009) is not captured in our word cloud representation above. Clearly work towards supporting teaching and learning in ill-defined domains is now a significant theme in AIED research; work in ill-defined domains was identified as a theme in conferences in 2009 and 2010 (see Table 1). AIED work is also reported in other journals and consequently themes drawn exclusively from the ITS and AIED conferences and the IJAIED will not be comprehensive. However, AIED research in special issues of IEEE Transactions on Learning Technologies, e.g. Intelligent and Innovative Support Systems for CSCL (Isotani et al, 2011), Game-based Learning (Shih, Squire & Lau, 2010), Real World Applications of Intelligent Tutoring Systems (Ramos, Frasson & Ramachandran, 2009) and Personalisation (De Bra, Kay & Weibelzahl, 2009), cover similar themes to those already identified through our analysis in this section.

Table 2. IJAIED Special Issues 2000-2010




Ill-Defined Domains

2009 Authoring Intelligent Tutoring Systems
2007 Open Learner Models
2006 Learner Centred Methods for Designing Intelligent Learning Environments
2003 Caring for the Learner
2003 Adaptive & Intelligent Web-based Systems
2001 Analysing Educational Dialogue Interaction
2001 Modelling Teaching

How have themes in AIED evolved over the last decade?

Over the decade AIED research themes have developed in line with changing social and pedagogical concerns and the evolving social-technical infrastructure to some extent these changes are visible in the AIED and ITS conference titles and themes (see Table 3 below). Looking across these conferences and our previous analysis of themes in the AIED literature, various developments are visible through the decade. These may be broadly understood as movements or widenings of focus as outlined in Table 4.

Table 3. AIED & ITS Conference Titles 2001 to 2010



Advanced Models of Learning for the Wired & Wireless Future. Key areas of interest included mobile and distributed systems.



Intelligent Tutoring Systems. Emerging interests identified in the introduction to the proceedings are: the Web and Agents on it, human motivation and emotions.



Shaping the future of learning through intelligent technologies. The call for papers includes novel interfaces as an area of interest.



Intelligent Tutoring Systems. The introduction to the proceedings notes an increased interest in affect and a growing emphasis on evaluation.



Supporting Learning through Intelligent & Socially Informed Technology. The call for papers included: Socially informed design, mixed-reality and ubiquitous learning environments, data mining and machine learning.



Intelligent Tutoring Scales Up. The title reflects an increasing concern with larger scale real world deployments.



Building Technology Rich Learning Contexts that Work.

The title reflects the need for real world evaluation and the importance of context.



ITS Past & Future. Co-located with the first international conference on Educational Data Mining indicating the increasing availability and utility of data from large-scale deployments of AIED systems.



Building Learning Systems that Care: From Knowledge Representation to Affective Modelling. Key themes included: modelling social, cognitive, meta-cognitive, and affective dimensions of learning.



ITS Bridges to Learning. Topics of interest included: informal and lifelong learning, social recommendations, capturing rich-data about learning, theories of learning with advanced technologies, social-cultural-historical contexts.

Table 4. Movements in focus of AIED research 2000-2010




Support for 1-to-1 learning

Support for personal, collaborative and social learning

Support for learning in tightly defined domains and educational contexts

Support for open-ended learning in ill-defined domains across varied physical and social cultural settings and through out the lifetime

Support for knowledge acquisition

Support for knowledge construction, skills acquisition and meta-cognitive, motivational and affective support

Small-scale systems and laboratory evaluations

Large-scale deployments, evaluations in real settings and learning analytics

Focussed analysis of relatively small quantities of experimental data

Discovery and learning from educational data mining of large amounts of data captured from real use
Constrictive technologies and interfaces

Accessible, ubiquitous, wireless, mobile, tangible and distributed interfaces

Designing educational software

Designing technology-enhanced learning experiences

*(This heading does not indicate that the work described below no longer happens, rather it indicates that the work has been developed)

What are the main directions of future AIED research?

Building on the themes and trends we identify from looking at the last decade of AIED research, we now look towards the next decade. What research directions and contributions to Education and Technology Enhanced Learning (TEL) might we expect from AIED during the next decade? The title for the 2011 AIED conference is Next Generation Learning Environments: Supporting Cognitive, Metacognitive, Social and Affective Aspects of Learning, indicating the need for the next generation of intelligent learning environments to integrate and synthesise components and approaches from across the various themes and concerns of AIED research. In this section, we draw on various researchers’ discussions of key themes for future AIED research (Dimitrova, 2010; Luckin, 2010; Woolf, 2010).

Caring for Learners and Collaborators, Richer Models and Synthesis

Dimitrova (2010) suggests that the emerging trends in AIED research from 2000 to 2010 are driven by an increasing concern that learning environments should care about both learners and their collaborators (including tutors, trainers, peers, family and friends), and that this requires a good understanding of the learners’, and their collaborators’ needs, and the full variety of socio-cultural and physical and technological settings in which learning and teaching may occur. Major growth directions in AIED research, as identified by Dimitrova, are in developing still richer learner models, advancing the modelling and exploitation of context, long term (life-long) learner modelling, use of social semantic web to enrich adaptation capabilities (Jovanovic et al., 2008), provision of adaptive feedback and assessment, and synthesis with research in supporting, motivation, meta-cognition and affect (Brna, 2009; Woolf et al., 2009). Indeed, recent EU research funding initiatives call for TEL research that develops adaptive and intuitive systems featuring affective and emotional approaches, including new forms of assessing learning outcomes as well as feedback, guidance mechanisms for both learners and teachers and support for metacognitive skills (European Commission, 2010).

Supporting Autonomy, Motivation & Engagement

Dimitrova (2010) also notes that TEL for workplace learning is moving towards empowering workers to empower themselves (Mödritscher & Wild, 2009). To support and develop learner autonomy we need new adaptivity frameworks that provide systems, which help learners realise how to care about themselves and others (Vinciarelli, Pantic & Bourlard, 2008). Dimitrova links this to the need to develop systems that support learning in less well-defined domains providing adaptive and intuitive instruction in ill-defined domains (Mitrovic & Weerasinghe, 2009). Finally, Dimitrova identifies another emerging trend in adaptive and intuitive systems; the exploitation of techniques from immersive environments, simulation learning and games (Faria, Hutchinson, Wellington & Gold, 2009) to increase learner motivation and engagement.

Understanding Context and the Resources and Help available to Learners

We have already identified an increasing concern with context in AIED research, partly driven by the arrival of mobile devices and ubiquitous computing and the need to consider learners as mobile, learning in and across various settings. We expect AIED to develop both new ways of modelling context and more context-aware adaptive learning environments. Luckin (2010) considers the subject of context and addresses the need for a learner centric definition of context and theoretically grounded models and frameworks for the design of technology rich learning that takes greater account of learners’ contexts. Luckin links context to an understanding of the resources and help that are potentially available to a learner and which may be recruited to scaffold learning. She reviews work conducted on scaffolding and intelligent support through technology.

“As has been noted by a range of researchers, (Puntambekar & Hübscher, 2005; Pea, 2004), scaffolding is used to describe a wide range of support provided by both humans and technology. One thing that is striking, when looking at the range of empirical studies that have been conducted, is the enormous diversity of learners and settings that have been encompassed. These extend far beyond the adult and child interactions studied by Wood and his colleagues. For example, empirical studies have been undertaken with learners aged 5–11 years, studying a range of subjects including science and maths (Holmes, 2005; Butler & Lumpe, 2008). Work has also been completed with learners aged 11–18 years studying maths (Koedinger et al, 1997; Beal & Lee, 2008), science (Azevedo et al, 2005; Puntambeker & Styllianou, 2005) and history (Li & Lim, 2008). There have also been numerous studies with older learners in college and in higher education, including trainee teachers (Oh & Jonassen, 2007); science students (Chen at al, 1992; Crippen & Earl, 2007; Ge & Land, 2004), and technology students (Tuckman, 2007).” (Luckin, 2010 p.41)

Scaffolding with Fading

Luckin discusses the manner in which the term scaffolding has been used to describe a variety of approaches, from those that aim to build intelligent software systems that provide interventions to scaffold individual learner progress, to the use of technology to support collaboration between groups or communities of learners; to visualize or structure the task, the curriculum and the learning circumstances; or to support the development of affect and higher order thinking, such as metacognition. She notes the growing body of opinion that supports the view that fading is a fundamental and intrinsic component of scaffolding (Pea, 2004; Lajoie, 2005; Puntambekar & Hübscher, 2005), and that a line needs to be drawn between scaffolding with fading and scaffolding without fading. We expect AIED research to continue exploring ways to quantify and adaptively fade help provision in response to learners increasing competence.

Distributed Scaffolding in Technology-rich Resource Ecologies

More recent attention to ‘distributed scaffolding’ (see for example, Puntambekar & Kolodner, 2005; Tabak, 2004) recognises the increased complexity that occurs when scaffolding is distributed, and the potential for distributed scaffolding to offer learners more opportunities to notice scaffolding opportunities. Distributed scaffolding represents an important trend that could build upon the synergy between well-tested AIED approaches to scaffolding and new technologies to support consideration of learners’ broader contexts. To date however, there is very little work that uses tangible technology to scaffold learners in the traditional scaffolding sense and on which we can draw for evidence. We expect current and future AIED research to contribute to our knowledge of how scaffolding, with fading, can be distributed effectively in technology-rich physical and social settings.

Technology-enhanced Learning and Grand Challenges in Engineering & Computing

Various Computing and Engineering research Grand Challenge programmes (e.g. Computing Research Association, 2003; Taylor et al, 2008; National Academy of Engineering, 2010) identify the need for future systems: to provide personalised support that enables people to better realise their potential both within and outside formal educational and throughout lifetimes, to encourage and support a broad range of learning including creativity and problem solving, and to improve access and inclusion. Workshops in 2009 brought together leaders in several disciplines to discuss the role of technology in addressing Grand Educational Challenges and to identify promising technologies and directions for future research. Below, drawing on Woolf’s (2010) discussion of results from these workshops we summarise the role of AIED in addressing specific challenges in education.

Personalizing Education & Richer User Models

Advances in AIED research, particularly in user models, will be required to provide deep understanding of students, including their weaknesses, motivational style, competitiveness and needs for acknowledgement or attention (Woolf, 2010). Adaptive systems employing advanced user models will personalise instruction, prompt learner activity and provide individualized feedback to match student traits (e.g. personality, learning style, motivation, and culture) and student states (affect, level of engagement, level of frustration) (Woolf, 2010).

Diminishing Boundaries, Novel Interfaces, Independent & Distributed Learner Models

Artificial boundaries between formal and informal learning need to fade and learning needs to be better connected throughout lives (lifelong learning) and across curricular boundaries (Woolf, 2010). This fading of boundaries may be supported by new user interfaces providing anywhere anytime access to intelligent environments implemented using tangible, ubiquitous and mobile technologies and supported by independent, distributed and lifelong user models.

Social Learning, Modelling Collaborators & Supporting Multiple Roles

Future learning environments “will leverage learning in the entire experiential ecology of the child as social context of the experience and will make effective use of the social network of the child‚ including peers, parents, and outside mentors as well as teachers” (Woolf, 2010, p. 22). AIED models may be expected to grow to include information about a learner’s social context and to model social networks and interactions. This information will be used by adaptive systems to guide, both learners and their collaborators, and promote learning that goes beyond more traditional conceptualisations of collaborative learning and draws on the broader social resources available to learners, teachers and other partners in learning (e.g. parents). Future learning environments will support users in taking on appropriate roles at the right times, e.g. teacher as facilitator/advisor/collaborator, learners as teacher/leader/collaborator, parent as teacher/advisor.

Enhancing the Role of Stakeholders, Participation and Design Methods

Enhancing the participation and role of a wider range of stakeholders in learning maker may require improved design methods and approaches. Woolf (2010) recognises that to date teachers (and other stakeholders) have not always been sufficiently involved in the design of learning environments and their introduction into practice. Research in participatory design methods for AIED (e.g. Luckin, 2010) and support for end users and others in authoring (e.g. Mitrovic & Koedinger, 2009) and delivering learning designs employing intelligent learning environments, should enhance the role of such stakeholders and empower them.

Alternative Teaching Methods and Models

Woolf highlights the need for alternative teaching strategies that engage students in 21st century skills and activities in which learners ‘are responsible for obtaining and shaping knowledge for themselves’ (Woolf, 2010 pp.27). Current research supporting learning in ill-defined domains (Aleven et al, 2009), inquiry learning (Sharples et al, 2011) and exploratory environments (Cocea & Magoulas, 2009) contributes to these objectives. Systems may employ simulations or guided discovery and provide learners with hints and feedback on the processes of inquiry and collaborative knowledge construction using appropriate pedagogic models and scripts.

Assessment Techniques, Learner Models and Data mining

Woolf focuses attention on ‘assessment for learning’, assessment that gathers ‘evidence that informs instructional decisions, and encourages learners to try to learn’ (Woolf, 2010, pp. 21). Challenges include assessing the kinds of 21st Century skills described earlier and tracing the development of these across formal and informal learning and throughout lifetimes. This will require comprehensive models of learner competencies, which can then be used not only to inform teachers but also to prompt learner reflection and self-regulation (Woolf, 2010) and greater autonomy, perhaps using Open Learner Models (Dimitrova, McCalla & Bull, 2007). These models should also support automated unobtrusive continuous assessment and facilitate scaffolding with fading as competence develops (Luckin, 2010). Advances in data mining and machine learning are key areas in AIED research expected to contribute to assessment (Woolf, 2010).

In summary, Woolf (2010) identifies modeling, intelligent environments, mobile tools, networking tools, serious games, and educational data mining, and rich interfaces as key areas of technology research for addressing grand educational challenges over the next 30 years.

Addressing Sustainability: Participatory Design, Co-design and Systemic Considerations

Beyond the technological challenges for future learning environments there are acknowledged pragmatic issues affecting widespread adoption and use. Over the last decade a number of AIED systems have successfully gone to scale and been in sustained use over several years in a variety of settings (for examples see Underwood & Luckin, 2011). However, attention to the needs and concerns of the full range of stakeholders in Education and the practicalities and constraints imposed by the settings of teaching and learning are essential in addressing issues of sustainability and scalability. The AIED community needs to attend to and address issues relating to the incorporation of intelligent technologies in good technology-enabled classroom practices, in particular for example, the role of practitioners with respect to these systems. The overestimation of the power of technologies to change classroom practice and underestimation of forces in classrooms that conspire to marginalize technological potential tend to make technology-enhanced learning interventions difficult to sustain. Consequently such interventions are often short-lasting and infrequently adopted in large-scale practice, i.e., technological features may be workable at a small scale, but insufficient to structure enactment by a wide variety of students and teachers across a diversity of school settings (Kaput & Thompson, 1994; Roschelle & Jackiw, 2000; Roschelle, Knudsen & Hegedus, 2010).

The quest for AIED that leads to real wide spread impact in education needs to include understanding and addressing issues of scalability and sustainability. Research into approaches such as participatory design and co-design, for example involving researchers and teachers and teacher professional development (Roschelle, Knudsen, Hegedus, 2010) is required to contribute to an adequate understanding of sustainability. Similarly, we need to adopt and develop frameworks that support systemic considerations, for example Coburn’s dimensions of depth, sustainability, spread, and shift of ownership (2003).


AIED research is driven by educational problems and is as much about a way of doing research as about technology development. However, the development and evaluation of intelligent adaptive environments that support learning has always been a central theme in AIED research. This work is supported by persistent strands of AIED research in: developing Agents capable of acting on information about a learner and the learner’s actions in order to guide learning effectively by acting as Intelligent Tutors or Learning Companions, developing Dialogue Systems capable of conversing with learners in various modalities including Natural Language, implementing and investigating the effect of Pedagogic Strategies such as Scaffolding and various kinds of Feedback, assessing and representing aspects of learners’ knowledge, misconceptions, learning and other key learner characteristics through Learner Modelling.

Throughout the last decade of AIED research there was an increasing interest in supporting Collaborative Learning and related research expanding User Modelling to include modelling of teachers, other collaborators and groups. This is now expanding towards modelling broader Social Learning networks and resources for learning. Such models may be utilised by systems implementing pedagogic strategies such as distributed scaffolding.

Over the decade there was also substantial successful work in increasing access to AIED learning environments by delivering these as Web-based systems. Current work is set to extend access to AEID systems further by exploiting mobile and ubiquitous technologies. Similarly, research using Adaptive Hypermedia to deliver personalised navigation to learning content can now be expanded through the use of the Semantic Web and Ontologies useful for describing the multitude of learning objects and content now available to learners online.

Another consistent AIED interest through the decade was in developing learning environments that are engaging and motivating and this is particularly evident in work on Narrative Learning Environments and more recently Game-based Learning. Borrowing techniques from games, systems can analyse learner behaviour and act to maintain engagement and drive learning forward by providing just the right amount of challenge (Woolf, 2010). There has also been increasing interest in Affect, for example detecting, modelling and responding to learner’s emotional states such as frustration or joy, and developing systems that express emotions. Much of this work involves developing rich multi-sensory user interfaces and Woolf (2010) notes that AIED systems continue to be a driving force for research in this area and incorporate some of the most advanced Novel Interfaces. AIED research into supporting and promoting Meta-cognition and Self-regulation has also been growing throughout the last decade. Another growing area of research, often employed to prompt users to reflect on learning and support meta-cognitive development, is Open Learner Modelling in which learner models are made inspectable by and possibly opened for learners and/or teachers to edit.

Making it easier for domain experts and others to create intelligent learning environments through the provision of Authoring Tools was also a consistent theme through the decade and remains a strong field of interest. Finding ways to enable faster and easier development of well-designed, contextually appropriate intelligent learning environments remains challenging but should be supported by emerging and future themes in AIED research. Research developing richer understanding of educational settings and learner context should result in richer Learner Models and Context Aware systems capable of more sensitive adaption to settings of learning, context and changes in these. Current research into Independent and Distributed User Models together with better support for knowledge transfer across the various disciplines involved in AIED and support for re-use and component-based development should also facilitate the development of integrated systems. However, research into improving design methods and frameworks for sustainability will also be required in order to improve the likelihood of sustained large-scale real-world use of such systems.

Uptake within Education will also be supported by an increasing emphasis on Evaluation of AIED systems in Authentic Real World Situations. So far, most large-scale evaluations have involved systems that support learning in domains that are typically considered well-defined, such as mathematics. In fact, even though mathematics may traditionally be thought of as a well-defined domain – maybe even the epitome of a well-defined domain – recent pedagogical research has shown just how ill-defined key mathematical topics (like generalisation) are less clearly defined than might at first thought be felt. In the MiGen project, for examples, researchers have been rising to the challenge of constructing and developing support for students and their teachers, in ways that respect the integrity of the mathematical idea of generalisation, but which acknowledge that progress on understanding the idea takes place along fuzzy and idiosyncratic trajectories (Noss, et. al., 2009). There is growing interest and AIED research around developing and evaluating systems to support learning in ill-defined domains such as law, design, history, and medical diagnosis (Aleven, et al., 2009). Developing support for learning in ill-defined domains greatly increases the relevance of AIED systems. The emerging area of Educational Data Mining is being used to discover properties in data from evaluations and reveal factors important for learning such as patterns of system use, learner characteristics or contextual features. Findings from Data Mining can then feed into formative evaluation and redesign of systems. Future systems may also be self-improving using machine learning techniques and data accrued through tracking user actions and assessing learning, to improve the support they provided to learners as they are used (Woolf, 2010).

AIED research covers an increasingly wide variety of themes and technologies in the quest to address current and future Grand Challenges in learning. Basic research pushing forward research in each of the themes is necessary as well as applied work in developing and evaluating integrated systems. However, in order to develop integrated AIED systems synthesise across the various strands of research is required and this can be challenging. Even within the AIED (inter)discipline it is difficult and time consuming to keep track of, integrate and synthesise work happening in all the specialist areas, let alone combine components into working systems. Communication across disciplines is notoriously difficult and integration of approaches and conceptual frameworks even more so (Conole et al, 2010). The need to provide better support for synthesis and integration is recognised within the AIED community. Woolf (2009) suggests the community needs ‘cadres of bibliographies’ and ‘component exchange’ communities. Such resources could be useful both within the research community and beyond to support wider uptake and use of AIED research and technology. However, research is required to specify requirements for such resources and this in itself will require collaboration between AIED researchers, the wider Education community and other stakeholders.


Many thanks to our Advisory Committee: Vania Dimitrova, Judy Kay, Paul Brna, Kaska Porayska-Pomsta, Chee Kit Looi, for their invaluable input to this report.

Next: Supporting integration, synthesis, uptake and reuse of AIED research


Aleven, V., Lynch, C., Pinkwart, N., Ashley, K. (2009). Ill-Defined Domains. International Journal of Artificial Intelligence in Education, 19 (3 & 4)

Azevedo R., Moos, D.C., Winters, F.W., Greene, J.A., Cromely, J.G., Olson, E.D., & Godbole-Chauhuri, P. (2005). Why is Externally-regulated Learning More Effective than Self-regulated Learning with Hypermedia? In Looi, C-K, McCalla, G., Bredeweg, B. & Breuker, J (eds), Artificial Intelligence in Education: Supporting learning through intelligent and socially informed technology, p. 41-48, Amsterdam, Netherlands, IOS Press.

Beal, C. & Lee, H. (2008). Mathematics Motivation and Achievement as Predictors of High School Students’ Guessing and Help-seeking with Instructional Software. Journal of Computer Assisted Learning, 24 (6), 507-14

Brna, P. (2009). Preface for volume 19(1). International Journal of Artificial Intelligence in Education, 19, 1-3.

Butler K. A. & Lumpe, A. (2008). Student Use of Scaffolding Software: Relationships with motivation and conceptual understanding. Journal of Science Education and Technology, 17, 427-36

Chen, N., Wei, C-W., Wu, K-T. & Uden, L. (1992). Effects of High Level Prompts and Peer Assessment on Online Learners’ Reflection Levels. Computers & Education, 52 (2), 283-91

Coburn, C. E. (2003). Rethinking Scale: Moving Beyond Numbers to Deep and Lasting Change, Educational Researcher, 32(6), 3–12.

Cocea, M., Magoulas, G. (2009). Hybrid Model for Learner Modelling and Feedback Prioritisation in Exploratory Learning. The International Journal of Hybrid Intelligent Systems 6(4), 211-230.

Conole, G., Scanlon, E., Mundin, P., and Farrow, R. (2010). Interdisciplinary research – Findings from the Technology Enhanced Learning Research Programme. TLRP, UK. Available 19/01/2010 at http://www.tlrp.org/docs/TELInterdisciplinarity.pdf

Computing Research Association (2003). Grand Research Challenges in Information Systems Available at http://www.cra.org/uploads/documents/resources/rissues/gc.systems_.pdf

Crippen, K.J & Earl, B.L (2007). The Impact of Web-based Worked Examples and Self-explanation on Performance, Problem solving, and Self-efficacy. Computers & Education, 49 (3), 809-21

De Bra, P., Kay, J., Weibelzahl, S. (2009). Special Issue on Personalization, IEEE Transactions on Learning Technologies, January-March, 2(1)

Dimitrova, V (2010). ImREAL project: http://www.imreal-project.eu

Dimitrova, V., McCalla, G., Bull, S. (2007). Open Learner Models: Future Research Directions: Preface to Special Issue on Open Learner Models. International Journal of Artificial Intelligence in Education, 17, 217-226.

European Commission (2010). Technology-enhanced Learning in FP7 – Target Outcomes. At http://cordis.europa.eu/fp7/ict/telearn-digicult/telearn-objectives_en.html checked 1/02/2011

Faria, A.F., Hutchinson, D., Wellington, W., Gold, S. (2009). Developments in Business Gaming: A Review of the Past 40 Years. Simulation Gaming, 40, pp. 464-487.

Ge, X. & Land, S. (2004) A Conceptual Framework for Scaffolding Ill-structured Problem-solving Process Using Question Prompts and Peer Interaction. Educational Technology Research and Development, 52 (2), 5-22.

Holmes, J (2005) Designing Agents to Support Learning by Explaining. Computers and Education, 48 (4), 523-47

Isotani, S., Bourdeau, J., Mizoguchi, R., Chen, W., Wasson, B., Jovanovic, J. (2011) Special Issue on Intelligent and Innovative Support Systems for CSCL, IEEE Transactions on Learning Technologies, January-March, 4(1)

Jovanovic, J., Torniai, C., Gasevic, G., Bateman, S., Hatala, M. (2008). Leveraging the Social Semantic Web in Intelligent Tutoring Systems. Intelligent Tutoring Systems 2008, pp. 563-572, Springer.

Kaput, J. (1994). Democratizing access to calculus: New routes using old roots. In A. Schoenfeld (Ed.), Mathematical thinking and problem solving (pp. 77–155). Hillsdale, NJ: Erlbaum.

Koedinger K.R. Anderson, J.R., Hadley, W.H & Mark, M.A. (1997) Intelligent Tutoring Goes to School in the Big City. International Journal of Artificial Intelligence in Education, 8, 30-43

Lajoie, S (2005) Extending the Scaffolding Metaphor. Instructional Science, 33 (5-6), 541-57

Li, D & Lim, C (2008) Scaffolding Online Historical Inquiry Tasks: A case study of two secondary school classrooms. Computers and Education, 50 (4), 1394-410

Luckin, R. (2010) Re-designing Learning Contexts: Technology-rich, Learner-centred Ecologies. Routledge, London.

Mitrovic, A., Koedinger, K. (2009) Special Issue on Authoring Intelligent Tutoring Systems. International Journal of Artificial Intelligence in Education, 19 (2)

Mitrovic, A., Weerasinghe, A. (2009). Revisiting the definition of ill-definedness and the consequences for ITSs. In V. Dimitrova, R. Mizoguchi, B. du Boulay, A. Graesser (Eds.), Proceedings of 14th International Conference on Artificial Intelligence in Education, AIED09, IOS Press, Frontiers of Artificial Intelligence.

Mödritscher, F., Wild, F. (2009). Why not Empower Knowledge Workers and Lifelong Learners to Develop their own Environments? In: Proceedings of the International Conference on Knowledge Management, I-Know09, pp. 268-277.

National Academy of Engineering. (2010). Grand Challenges for Engineering. Available at http://www.engineeringchallenges.org/cms/8996/9127.aspx

Noss, R., Hoyles C., Mavrikis M., Geraniou E., Gutierrez-Santos, S. & Pearce D. (2009). Broadening the sense of ‘dynamic’: a microworld to support students’ mathematical generalisation. Zentralblatt für Didaktik der Mathematik (International Journal on Mathematics Education), 41 (4), 493-503.

Oh, S. & Jonassen, D. (2007) Scaffolding Online Argumentation During Problem Solving. Journal of Computer Assisted Learning, 23 (2), 95-110.

Pea, R.D. (2004) The Social and Technological Dimensions of Scaffolding and Related Theoretical Concepts for Learning, Education, and Human Activity, Journal of the Learning Sciences, 13, 423-51

Puntambekar, S & Hübscher, R. (2005) Tools for Scaffolding Students in a Complex Learning Environment: What have we gained and what have we missed? Educational Psychologist, 40, (1), 1-12

Puntambekar, S & Kolodner, J.L (2005) Distributed Scaffolding: Helping students learn science by design. Journal of Research in Science Teaching, 42 (2), 185-217

Puntambekar, S & Styllianou, A. (2005) Designing Navigation Support in Hypertext Systems Based on Navigation Patterns. Instructional Science, 33 (5-6), 451-81.

Ramos, C., Frasson, C., Ramachandran, S. (2009). Special Issue on Real World Applications of Intelligent Tutoring Systems, IEEE Transactions on Learning Technologies, April-June, 2(2)

Roschelle, J. & Jackiw, N. (2000). Technology design as educational research: Interweaving imagination, inquiry & impact. In A. Kelly & R. Lesh (Eds.), Research design in mathematics & science education (pp. 777–797). Mahwah, NJ: Lawrence Erlbaum Associates.

Roschelle, J., Knudsen, J., & Hegedus, S. (2010). From new technological infrastructures to curricular activity systems: Advanced designs for teaching and learning. In M. J. Jacobson &P. Reimann (Eds.), Designs for learning environments of the future: International perspectives from the learning sciences. New York: Springer. 233-262.

Sharples, M., Collins, T., Feißt, M., Gaved, M., Mulholland, P., Paxton M., and Wright, M. (2011) A “Laboratory of Knowledge-Making” for Personal Inquiry Learning. In Biswas, G.; Bull, S.; Kay, J.; Mitrovic, A. (Eds.), Proceedings of Artificial Intelligence in Education: 15th International Conference, AIED 2011, Auckland, New Zealand, June 28 – July 2, LNCS 6738, Springer.

Shih, T.K., Squire, K., Lau, R.W.H. (2010) Guest Editorial: Special Section on Game-Based Learning, IEEE Transactions on Learning Technologies, pp. 278-280, October-December

Tabak, I. (2004) Synergy: A complement to emerging patterns. Journal of the Learning Sciences, 13 (3), 305-35

Taylor, J., Greenwood, Wood, W., Rae, J., Rico, M. (2008) A Grand Challenge for Computing: Learning for Life. Available at http://kn.open.ac.uk/public/workspace.cfm?wpid=6042

Tuckman, B. (2007) The Effect of Motivational Scaffolding on Procrastinators’ Distance Learning Outcomes. Computers & Education, 49 (2), 414-22

Underwood, J., & Luckin, R. (2011). What is AIED and why does Education need it? – A report for the UK’s TLRP Technology Enhanced Learning – Artificial Intelligence in Education Theme. May 2011. Available from http://www.tel.ac.uk/personalisation/artificial-intelligence-in-education/what-is-aied-and-why-does-education-need-it/

Vinciarelli A., Pantic, M., Bourlard, H. (2008). Social Signal Processing: Survey of an Emerging Domain, Elsevier.

Woolf, B. (2010). A Roadmap for Education Technology. GROE, Available online at http://www.cra.org/ccc/docs/groe/GROE%20Roadmap%20for%20Education%20Technology%20Final%20Report.pdf checked 31/01/11

Woolf, B. (2009). AIED Grand Challenges. AIED09 Panel: The evolution of AIED @ 14th International Conference on AI in Education, AIED09, July, 2009, Brighton, UK.

Woolf, B., du Boulay, B., Greer, J., Kay, J. Litman, D., Lane, C., Manson, P. (2009). AIED09 Panel: The evolution of AIED @ 14th International Conference on AI in Education, AIED09, July, 2009, Brighton, UK.

Leave a Reply




You can use these HTML tags

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>