Adaptive learning is an educational method which uses computers as interactive teaching devices, and to orchestrate the allocation of human and mediated resources according to the unique needs of each learner. Computers adapt the presentation of educational material according to students' learning needs, as indicated by their responses to questions, tasks and experiences. The technology encompasses aspects derived from various fields of study including computer science, education, psychology, and brain science.
Adaptive learning has been partially driven by a realization that tailored learning cannot be achieved on a large-scale using traditional, non-adaptive approaches. Adaptive learning systems endeavor to transform the learner from passive receptor of information to collaborator in the educational process. Adaptive learning systems' primary application is in education, but another popular application is business training. They have been designed as desktop computer applications, web applications, and are now being introduced into overall curricula.<Jason H, Douglas A. Are the conditions right for a 21st-century medical school? The Lancet, 385: 672-3, 2015> Brusilovsky, Peter (2003). "Adaptive and Intelligent Web-based Educational Systems". International Journal of Artificial Intelligence in Education 13 (2–4): 159–172. </ref>
Adaptive learning has been implemented in several kinds of educational systems such as adaptive educational hypermedia, intelligent tutoring systems, Computerized adaptive testing, and computer-based [pedagogical agents], among others.
Adaptive learning or Intelligent tutoring has its origins in the artificial-intelligence movement and began gaining popularity in the 1970s. At that time, it was commonly accepted that computers would eventually achieve the human ability of adaptivity. In adaptive learning, the basic premise is that the tool or system will be able to adjust to the student/user's learning method, which results in a better and more effective learning experience for the user. Back in the 70's the main barrier was the cost and size of the computers, rendering the widespread application impractical. Another hurdle in the adoption of early intelligent systems was that the user interfaces were not conducive to the learning process. The start of the work on adaptive and intelligent learning systems is usually traced back to the SCHOLAR system that offered adaptive learning for the topic of geography of South America. A number of other innovative systems appeared within five years. A good account of the early work on adaptive learning and intelligent tutoring systems can be found in the classic book "Intelligent Tutoring Systems".
It was not until AutoTutor which was developed by the Institute of Intelligent System around the turn of the 21st century that adaptive learning systems got a voice. This was a major step in adaptive learning systems because it added another medium in communication with the end user. According to the founder and lead on the AutoTutor project - Graesser - "Spoken computational environments may foster social relationships that may enhance learning." Also, in some applications audio content is a necessity, such as in language learning applications. Today, the number of new adaptive learning system companies is growing steadily as more classrooms are becoming computerized and other industries are finding uses for the applications of adaptive learning such as professional development.
Technology and methodology
Adaptive learning systems have traditionally been divided into separate components or 'models'. While different model groups have been presented, most systems include some or all of the following models (occasionally with different names):
- Expert model - The model with the information which is to be taught
- Student model - The model which tracks and learns about the student
- Instructional model - The model which actually conveys the information
- Instructional environment - The user interface for interacting with the system
The expert model stores information about the material which is being taught. This can be as simple as the solutions for the question set but it can also include lessons and tutorials and, in more sophisticated systems, even expert methodologies to illustrate approaches to the questions.
Adaptive learning systems which do not include an expert model will typically incorporate these functions in the instructional model.
Student model algorithms have been a rich research area over the past twenty years. The simplest means of determining a student's skill level is the method employed in CAT (Computerized adaptive testing). In CAT, the subject is presented with questions that are selected based on their level of difficulty in relation to the presumed skill level of the subject. As the test proceeds, the computer adjusts the subject's score based on their answers, continuously fine-tuning the score by selecting questions from a narrower range of difficulty.
An algorithm for a CAT-style assessment is simple to implement. A large pool of questions is amassed and rated according to difficulty, through expert analysis, experimentation, or a combination of the two. The computer then performs what is essentially a binary search, always giving the subject a question which is half way between what the computer has already determined to be the subject's maximum and minimum possible skill levels. These levels are then adjusted to the level of the difficulty of the question, reassigning the minimum if the subject answered correctly, and the maximum if the subject answered incorrectly. Obviously, a certain margin for error has to be built in to allow for scenarios where the subject's answer is not indicative of their true skill level but simply coincidental. Asking multiple questions from one level of difficulty greatly reduces the probability of a misleading answer, and allowing the range to grow beyond the assumed skill level can compensate for possible misevaluations.
Richer student model algorithms look to determine causality and provide a more extensive diagnosis of student's weaknesses by linking 'concepts' to questions and defining strengths and weaknesses in terms of concepts rather than simple 'levels' of ability. Because multiple concepts can influence a single question, questions have to be linked to all relevant concepts. For example, a matrix can list binary values (or even scores) for the intersection of every concept and every question. Then, conditional probability values have to be calculated to reflect the likelihood that a student who is weak in a particular concept will fail to correctly answer a particular question. A student takes a test, the probabilities of weakness in all concepts conditional on incorrect answers in all questions can be calculated using Bayes' Law (these adaptive learning methods are often called bayesian algorithms).
A further extension of identifying weaknesses in terms of concepts is to program the student model to analyze incorrect answers. This is especially applicable for multiple choice questions. Consider the following example:
- Q. Simplify:
- a) Can't be simplified
- c) ...
- d) ...
Clearly, a student who answers (b) is adding the exponents and failing to grasp the concept of like terms. In this case, the incorrect answer provides additional insight beyond the simple fact that it is incorrect.
The instructional model generally looks to incorporate the best educational tools that technology has to offer (such as multimedia presentations) with expert teacher advice for presentation methods. The level of sophistication of the instructional model depends greatly on the level of sophistication of the student model. In a CAT-style student model, the instructional model will simply rank lessons in correspondence with the ranks for the question pool. When the student's level has been satisfactorily determined, the instructional model provides the appropriate lesson. The more advanced student models which assess based on concepts need an instructional model which organizes its lessons by concept as well. The instructional model can be designed to analyze the collection of weaknesses and tailor a lesson plan accordingly.
When the incorrect answers are being evaluated by the student model, some systems look to provide feedback to the actual questions in the form of 'hints'. As the student makes mistakes, useful suggestions pop up such as "look carefully at the sign of the number". This too can fall in the domain of the instructional model, with generic concept-based hints being offered based on concept weaknesses, or the hints can be question-specific in which case the student, instructional, and expert models all overlap.
Adaptive learning that is implemented in the classroom environment using information technology is often referred to as an Intelligent Tutoring System or an Adaptive Learning System. Intelligent Tutoring Systems operate on three basic principles:
- Systems need to be able to dynamically adapt to the skills and abilities of a student.
- Environments utilize cognitive modeling to provide feedback to the student while assessing student abilities and adapting the curriculum based upon past student performance.
- Inductive logic programming (ILP) is a way to bring together inductive learning and logic programming to an Adaptive Learning System. Systems using ILP are able to create hypothesis from examples demonstrated to it by the programmer or educator and then use those experiences to develop new knowledge to guide the student down paths to correct answers.
- Systems must have the ability to be flexible and allow for easy addition of new content.
- Cost of developing new Adaptive Learning Systems is often prohibitive to educational institutions so re-usability is essential.
- School districts have specific curriculum that the system needs to utilize to be effective for the district. Algorithms and cognitive models should be broad enough to teach mathematics, science, and language.
- Systems need to also adapt to the skill level of the educators.
- Many educators and domain experts are not skilled in programming or simply do not have enough time to demonstrate complex examples to the system so it should adapt to the abilities of educators.
Distance learning implementation
The field of distance learning is now incorporating aspects of adaptive learning. Initial systems without adaptive learning were able to provide automated feedback to students who are presented questions from a preselected question bank. That approach however lacks the guidance which teachers in the classroom can provide. Current trends in distance learning call for the use of adaptive learning to implement intelligent dynamic behavior in the learning environment.
During the time a student spends learning a new concept they are tested on their abilities and databases track their progress using one of the models. The latest generation of distance learning systems take into account the students' answers and adapt themselves to the student's cognitive abilities using a concept called 'cognitive scaffolding'. Cognitive scaffolding is the ability of an automated learning system to create a cognitive path of assessment from lowest to highest based on the demonstrated cognitive abilities. A current successful implementation of adaptive learning in web-based distance learning is the Maple engine of WebLearn by RMIT university. WebLearn is advanced enough that it can provide assessment of questions posed to students even if those questions have no unique answer like those in the Mathematics field.
Group collaboration is also a hot field in the adaptive learning research area. Group collaboration is a key field in Web 2.0 which extends the functionality of distance learning. Adaptive learning can be incorporated to facilitate collaboration within distance learning environments like forums or resource sharing services. Some examples of how adaptive learning can help with collaboration include:
- Automated grouping of users with the same interests.
- Personalization of links to information sources based on the user's stated interests or the user's surfing habits.
Game Design Implementation
In 2014, an educational researcher concluded a multi-year study of adaptive learning for educational game design. The research developed and validated the ALGAE (Adaptive Learning GAme dEsign) model, a comprehensive adaptive learning model based on game design theories and practices, instructional strategies, and adaptive models. The research extended previous researching in game design, instructional strategies, and adaptive learning, combining those three components into a single complex model.
The study resulted in the development of an adaptive educational game design model to serve as a guide for game designers, instructional designers, and educators with the goal of increasing learning outcomes. Survey participants validated the value of the ALGAE model and provided specific insights on the model's construction, use, benefits, and challenges. The current ALGAE model is based on these insights. The model now serves as a guideline for the design and development of educational computer games.
The model's applicability is assessed as being cross-industry including government and military agencies/units, game industry, and academia. The model's actual value and the appropriate implementation approach (focused or unfocused) will be fully realized as the ALGAE model's adoption becomes more widespread.
Companies currently using adaptive learning technology
A 2013 report commissioned by the Gates Foundation provides a list of almost forty companies currently active in adaptive learning technology.
- ALEKS Corporation, an online assessment and learning company, uses the theory of knowledge spaces in its product (known as ALEKS) to quickly and accurately determine what a student knows and doesn't know in a course.
- Carnegie Learning, a publisher of math curricula, offers adaptive math software (known as the Cognitive Tutor) to high school students, along with traditional textbook offerings.
- CCKF, developer of Realizeit, a content agnostic adaptive learning platform for educational institutions, publishers and professional associations. Also provides a full API to connect to third-party products.
- Cengage Learning, a publishing company whose Aplia product provides adaptive learning technology for Developmental English.
- DreamBox, an adaptive learning platform with individualized paths for personalized learning.
- eSpindle Learning, a nonprofit maintaining an online vocabulary and spelling coaching program based on the adaptive learning concept.
- Knewton, whose adaptive learning API connects to third-party products to help teachers identify and predict knowledge gaps and personalize content for each student "through sophisticated, real-time analysis of reams of student performance data."
- KnowRe, an engaging adaptive mathematics curriculum, provides granular assessments and an engaging and personalized learning environment.
- Desire2Learn, a provider of integrated learning platform, offers Knowillage LeaP which creates personalized learning paths for any learner, using any repository of learning objectives, content, assessments and questions, which are automatically mapped.
- McGraw-Hill Education, a content, software and services-based education company. In 2013, the company acquired the ALEKS Corporation and a 20 percent equity stake in Area9 Aps.
- Pearson, an education company whose adaptive SuccessMaker software provides elementary and middle school reading and math instruction.
- PrepMe, an online learning company, currently uses adaptive learning technology for test preparation, K-12 education, and professional development.
- Sherston Software, a UK education software company, offers PlanetSherston, an adaptive learning platform.
- Smart.fm, a social learning and community website, uses adaptive learning technology with the goal of increasing learning speed and retention.
- Smart Sparrow, has an adaptive learning platform that offers instructional designers and teachers integrated tools to create, publish and analyse their own adaptive content.
- Adaptive educational hypermedia
- Adaptive instruction
- Computerized adaptive testing
- Educational software
- Intelligent tutoring systems
- Personalized learning
- Validated learning
This article incorporates material from the Citizendium article "Adaptive learning", which is licensed under the Creative Commons Attribution-ShareAlike 3.0 Unported License but not under the GFDL.
- J. R. Carbonell (1970). "AI in CAI: An artificial intelligence approach to computer aided instruction". IEEE Transactions on Man-Machine Systems. MMS-11 (4): 190–202.
- Derek Sleeman; John Seely Brown, eds. (1982). Intelligent tutoring systems. Academic Press.
- Charles P. Bloom, R. Bowen Loftin Facilitating the Development and Use of Interactive Learning Environments, Lawrence Erlbaum Associates (1998).
- "What is an Intelligent Tutoring System?" (PDF). Retrieved August 6, 2008.[dead link]
- "A Proposed Student Model Algorithm for Student Modeling and its Evaluation" (PDF). Retrieved August 6, 2008.
- "Cursos Online". Retrieved August 6, 2008.
- "Adaptive Learning Systems - National Institute of Standards and Technology". Archived from the original on 16 September 2008. Retrieved August 17, 2008.
- "Cognitive scaffolding for a web-based adaptive learning environment". Retrieved August 17, 2008.
- "Addressing Different Cognitive Levels for On-line Learning" (PDF). Retrieved August 17, 2008.
- "Towards web-based adaptive learning communities" (PDF). Retrieved August 17, 2008.
- Lavieri, Edward (2014). A Study of Adaptive Learning for Educational Game Design. ProQuest UMI. ISBN 9781321049602. Retrieved 11 December 2014.
- "Bridging the gap". UCI News. July 1, 2013. Retrieved 2014-11-29.
- "Learning to Adapt". Inside Higher Ed. July 13, 2014. Retrieved 2014-11-29.
- Empson, Rip (December 19, 2013). "Powering Smart Content For Publishing Giants, Knewton Lands $51M To Take Personalized Learning Global". Techcrunch. Retrieved 2014-04-05.
- Webley, Kayla (June 6, 2013). "The Adaptive Learning Revolution". TIME. Retrieved 2014-04-05.
- Kimerling, Dan (2007-09-01). "Starts-Ups Change How Students Study for Tests". TechCrunch.
- Miller, Claire Cain (2009-07-16). "A Virtual Game to Teach Children Languages". New York Times. Archived from the original on 9 February 2010. Retrieved 2010-03-16.
- Sharma M. (August 9, 2012). "Virtual patient gets funding injection". Sydney Morning Herald. Retrieved March 21, 2013.