"Wenn wir an die Zukunft der Welt denken, so meinen wir immer den Ort, wo sie sein wird, wenn sie so weiter läuft, wie wir sie jetzt laufen sehen, und denken nicht, daß sie nicht gerade läuft, sondern in einer Kurve, und ihre Richtung sich konstant ändert."
"When we think of the world’s future, we always mean the destination it will reach if it keeps going in the direction we can see it going in now; it does not occur to us that its path is not a straight line but a curve, constantly changing direction."
Wittgenstein (1980), pp. 3 / 3e
If, as some anthropologically-minded archæologists would claim, the present is the key to the past, then perhaps the future is the key to the present? In this paper I assume the converse that the present and the past are keys to the future for the case of research in the field of Artificial Intelligence and/in Education (henceforth abbreviated to "AIED").
Any view of what objectives a research field may achieve in the future must be based on a view of the nature of the field in question, up to the present day. I characterise the past, the present and the near future of AIED research in terms of a combination of different roles played by models of educational processes, namely: models as scientific tools, models as components of educational artefacts, and models as bases for design of educational artefacts. It should be noted that the views expressed here are not those of an objective historian of science, but rather of a researcher engaged in the field that is being discussed. In that case, description, prediction and prescription coincide to a certain extent.
One could say that there are basically three sorts of argumentative texts: those that argue (mostly) in favour of a particular view, those that argue (mostly) against one and those that attempt to weigh pro and contra arguments in the balance (the conventional form of academic discourse). This text falls (mainly) into the first category, and so no claim to exhaustivity is made in citing research that could constitute a rebuttal to the views argued for here. In the context of the special issue in which this text appears, I can only hope that some readers will be willing to supply counter-arguments and that a synthesis could emerge from any ensuing debate.
As with any field of scientific research, AIED involves elaborating theories and models with respect to a specific experimental field, in relation to the production of artefacts. What characterises a particular field is the nature of each of these elements and of the relations that are established between them: what types of theories are elaborated? what counts as a model? what is the experimental field studied? how close are the links between theories, models and artefacts?
With respect to other research in the field of education, one of the specificities of AIED research lies in the different roles that models can play. A significant part of AIED research can be seen as the use of computers to model aspects of educational situations that themselves involve the use of computers as educational artefacts, some of which may incorporate computational models. By an educational situation I mean a situation that is designed in some way so that a specific form and content of learning will occur; by "educational process" I do not only mean the processes of learning and teaching, but also the larger scale processes by which social situations that are intended to enable teaching and learning to occur are designed.
There are thus three main roles for models of educational processes in AIED research, are as follows:
1. Model as scientific tool.
A model — computational or other — is used as a means for understanding and predicting some aspect of an educational situation. For example, a computational model is developed in order to understand how the "self-explanation" effect works (VanLehn, Jones & Chi, 1992). This is often termed cognitive modelling (or simulation), although, as I discuss below, the term "cognitive" can have several interpretations.
2. Model as component.
A computational model, corresponding to some aspect of the teaching or learning process, is used as a component of an educational artefact. For example, a computational/cognitive model of student problem solving is integrated into a computer-based learning environment as a student model. This enables the system to adapt its tutorial interventions to the learner's knowledge and skills. Alternatively, the model-component can be developed on the basis of existing AI techniques, and refined by empirical evaluation.
3. Model as basis for design.
A model of an educational processes, with its attendant theory, forms the basis for design of a computer tool for education. For example, a model of task-oriented dialogue forms the basis of design and implementation of tools for computer-mediated communication between learners and teachers in a computer supported collaborative learning environment (e.g. Baker & Lund, 1997). In this case, a computational model is not directly transposed into a system component.
Although researchers often attempt to establish a close relationship between 1 and 2 — e.g. cognitive-computational models of student problem-solving becoming student models in Intelligent Tutoring Systems (henceforth, "ITS(s)") — there is no necessary relation between the two, since it may be that the most effective functional component (in an engineering sense) of an educational artefact does not operate in a way that models human cognition.
These three possibilities are not, of course, mutually exclusive: most often, a given AIED research programme contains elements of each, to a greater or lesser degree. For example, one part of an educational system may be based on study of students' conceptions, and other parts may be based on using existing computer science techniques. However, it is not always possible to do this in a way that simultaneously satisfies requirements of each type of use of models, i.e. produce a satisfactory scientific model that is an effective tutoring system component and which leads to an artefact that is genuinely useful in education. I believe that all three of these possibilities are valid and useful, provided that they are pursued in specific ways, that are coherent with the researcher’s goals.
Before moving on to a discussion of the future of AIED research in terms of these three roles of models, I need to say something about what a model is3. Across different sciences, many different types of abstract constructions count as models — for example, descriptive, explanatory, analytic, qualitative, quantitative, symbolic, analogue, or other models. Without entering into an extended discussion in the philosophy of science, it is possible, and useful here, to identify a small number of quite general characteristics of models.
Firstly — and classically —, the function of a model is to predict the existence or future incidence of some set of phenomena, in a determinate experimental field. For example, models of stock exchange transactions should predict changes in financial indices; models of the weather should predict the weather tomorrow; a model of cooperative problem-solving should predict what forms of cooperation can exist (see below), and ideally what interactive learning mechanisms they trigger; a student model should predict the evolution of a student's knowledge states; and so on.
Secondly, a further, and just as important function of a model is to enable elaboration or refinement of the theory on which it is based, by rendering explicit its commitments on epistemological (what can be known and how?) and ontological (what is claimed to exist?) planes. It is generally accepted that there should be a link between the epistemology and the ontology: one should not posit the existence of entities without saying something about how they can be known. Such a relation between model and theory can lead to explanation of phenomena. A theory is not at all the same thing as a model; it consists of a set of quite general assumptions and laws — e.g. the views according to which human cognition is complex symbolic information processing, or that knowledge is a relation between societal subjects and the socially constituted material world — that are not themselves intended to be directly (in)validated (for that, the theory must engender a model). Theories are foundational elements of paradigms, along with shared problems and methods (Kuhn, 1962).
Thirdly, a model necessarily involves abstraction from phenomena, selection of objects and events, in its corresponding experimental field; it necessarily takes some phenomena into account but not others. It is not relevant to criticise a model as such by claiming that it does not take all phenomena into account, but one can criticise its degree of coverage of an experimental field. The modelling process itself involves complex matching processes during which objects and events are selected and structured so as to correspond to the model, within the constraints of its syntax. Tiberghien (1994) has termed this process one of establishing a meaning, or a semantics, for the model, in relation to its experimental field.
Here artefacts enter into the picture? All research fields necessarily comprise aspects that are more or less close to the production and/or use of artefacts, in the sense of either 'applications' of theories or models, use of artefacts or instruments as experimental tools, sometimes on a large scale, or with respect to the study of artefacts themselves and their use, each of which can be a source of new research problems. Even highly theoretical work in mathematics, or descriptive work in botany, that is carried out as "pure research", may, perhaps decades later, find an unanticipated application via, for example, other domains such as physics or medical research. I do not believe that unidirectional 'application' exists: the relation between artefact, theory and model is always complex and multidirectional. Whilst it is clear that any field needs both theory and a close relation with the production of artefacts, it seems to me that one of the defining characteristics of AIED research is that it is closer to the theoretical end of the spectrum.
There is nothing intrinsically wrong in that: for example, physics has for a long time comprised both theoretical and experimental branches. On that analogy, AIED research would be theoretically-oriented educational science, or even "Learning Science", that adopts a modelling approach.
Despite this variety of roles and types of models, I think that AIED as a field nevertheless still largely operates with a somewhat restricted view of what models are — i.e. symbolic and computational information-processing models. Whilst this view has been important in defining the field as such up to the present, I do not think that it is fruitful or realistic as a unique ‘model’ for what the field currently is and will become. Other types of models of educational processes, that are not necessarily cognitive (in the above sense) nor computational in nature, can, and will I think/hope play an important role in AIED research.
I have sketched a personal and prospective view of AIED research that turns on three possible roles for models: as scientific tools, as components of computational educational artefacts, and as bases for design of such artefacts.
In terms of the first role, my view is that AIED research, over the past three decades, has already mapped out a vast space of phenomena to be studied. We do not need to extend the space of phenomena, but rather to extend the range of theoretical tools from those available in cognitive science, and to adopt a wider (yet more strict) notion of what is and what is not a model. Specifically, and in terms of how I defined models themselves, I claimed that there is no a priori reason why interesting models should not be developed, that extend the notion of ’cognition’ to embrace action and perception, as embedded in artefacts and social relations.
AIED research should and will, I think, open out to a greater extent than is currently the case, into cognitive science, considered in the widest sense of the term. The role of a model, as scientific tool, is to help us to explain, to develop theory, and to predict. As such, any model abstracts from reality. Failure to take a particular phenomenon into account does not invalidate a model, it just restricts its usefulness.
In terms of the second role — models as components — I claimed that individualising ITS are not currently adapted to existing educational practices, largely because of, on a micro-level, problems associated with failing to take teachers, and other social actors, into account. Either we must adapt the components and the artefacts, or else change educational systems; and no doubt, most researchers aim for some realistic combination of both. Depending on the culture concerned, there may be a greater or lesser difference between the timescales of institutional and technological change. I proposed that ITS will, in the near future, be most appropriate for social situations that are less norm-based than most state education systems.
Within such educational situations, intelligent information search for learners using the Web, rather than intelligent explanation generation, will come to the forefront in the near future, depending on the type of learning task involved. Intelligent explanation generation, and help systems in general, may turn out to be more important for teachers rather than for learners, in, for example, distributed learning communities. Models as intelligent components of educational artefacts have, I think, an important role to play in the near future; it is simply that their uses may not be in the situations that AIED researchers originally thought.
Finally, once we remember that (of course) models are not, by their nature, necessarily computational, this opens up a wide range of possible ways in which theories and models can form the bases of design of educational artefacts. What is required is that the specific nature of the relations between theory, model and design of artefacts be made as explicit as possible, as legitimate objects of scientific discussion and as means of generalising findings towards redesign.
Personally, I believe that theories and models will find their most effective application in design of collaborative distributed educational technologies.
I conclude with some brief remarks on the unity and future of AIED research, as a field. Given all the possible evolutions of AIED research that I have sketched, isn't there a strong possibility that AIED could dissipate into educational research and/or that part of cognitive science that is concerned with learning and teaching? Perhaps, and after all, why not? But I do not think so, and for the following reasons.
In terms of the particular view of AIED research I have outlined above, what makes piece of research AIED research is, quite simply, that it has something innovative to say about all three of the possible roles of models, with a greater or lesser emphasis being put on each. Concretely, this means that the research in question proposes a specific, explicit and coherent set of relations between: (1) a theory, (2) a model, (3) an experimental field of educational phenomena, (4) computational-educational artefacts, whose use is part of (3), and (5) an educational design process. It is not enough to propose a model of an educational phenomenon; the research must also describe how the model relates to theory, how it is relevant to study or design of artefacts for teaching and learning, and how that design might proceed. This means that AIED research is very complex, and very difficult to carry out.
I think that those constraints will continue to be sufficient for distinguishing a specific field or area of research, whether it is called AIED or something else.
No comments:
Post a Comment