Intelligent Tutoring Systems – Can They Work For You?
An effective tutor knows not only when a response is incorrect but how a student might have been led to select it. She continues to present the student with problems that test a particular concept until she has determined that the student has mastered that concept. She poses questions, analyzes responses, and offers customized instruction and feedback. When the student succeeds, the tutor makes a note of how long the lesson took.
An intelligent tutoring system is computer software designed to do all these things and more. Unlike other computer-aided forms of instruction, intelligent tutoring systems can interpret complex human responses and learn as they operate, adjusting their feedback style and content focus to align with students’ learning needs.
Intelligent tutoring systems have been constructed to help students learn geography, circuits, medical diagnoses, computer programming, mathematics, physics, genetics, chemistry, and countless other subjects. Intelligent Language Tutoring Systems (ILTS) teach natural language to first or second language learners, and require specialized natural language processing tools such as large dictionaries and morphological and grammatical analyzers with acceptable coverage.
Historically non-technological areas such as the educational sciences and psychology have also been influenced by the success of ITSs.
A Brief History
The concept of intelligent machines for instructional use dates back to 1924, when Sidney Pressey of Ohio State University created a machine to instruct students without the intervention of a human teacher. The Pressey Machine, which resembled a typewriter with several keys and a window that provided the learner with questions, allowed users to input answers and provided immediate feedback by recording their scores on a counter.
Following later standards, Pressey’s teaching and testing machine would not be considered intelligent as it was mechanically run and was based on one question and answer at a time, but it set an early precedent for future projects.
In the period following the second World War, mechanical binary systems gave way to binary based electronic machines.These machines were considered intelligent when compared to their mechanical counterparts, as they had the capacity to make logical decisions.
In 1970, Jaime Carbonell suggested that a computer could act as a teacher rather than just a tool. A new perspective would emerge that focused on the use of computers to intelligently coach students called Intelligent Computer Assisted Instruction or Intelligent Tutoring Systems (ITS). ITS drew from work in cognitive psychology, computer science, and especially artificial intelligence. There was a shift in AI research at this time as systems moved from the logic focus of the previous decade to knowledge based systems–systems that could make intelligent decisions based on prior knowledge.
During the rapid expansion of the Web, new computer-aided instruction paradigms such as e-learning and distributed learning provided an excellent platform for ITS ideas.
In recent years, ITSs have come to include a range of practical applications. They have expanded across many critical and complex cognitive domains, and the results have been far reaching. ITS systems have cemented a place within formal education and these systems have found homes in the sphere of corporate training and organizational learning. ITS offers learners several affordances such as individualized learning, timely feedback, and flexibility in time and space.
Reports of improvement in student comprehension, engagement, attitude, motivation, and academic results have all contributed to the ongoing interest in the investment in and research of these systems.
How Do They Work?
The development of an intelligent tutoring system involves four iterative stages: (1) needs assessment, (2) cognitive task analysis, (3) initial tutor implementation, and (4) evaluation.
1. Needs assessment: As is the case with any instructional design process, the first step involves a learner analysis and a consultation with subject matter experts and/or instructor(s). The goal is to specify learning goals and to outline a general plan for the curriculum. Three crucial dimensions are dealt with at this stage: (1) the probability a student is able to solve problems; (2) the time it takes to reach this performance level, and (3) the probability the student will actively use this knowledge in the future. Another important aspect that requires analysis is cost effectiveness of the interface. Moreover, teachers and student entry characteristics such as prior knowledge must be assessed since both groups are going to be system users.
2. Cognitive task analysis: The second step develops a valid computational model of the required problem solving knowledge. Chief methods for developing a domain model include: (1) interviewing domain experts, (2) conducting “think aloud” protocol studies with domain experts, (3) conducting “think aloud” studies with novices, and (4) observation of teaching and learning behavior. The “think aloud” methods involve experts asking learners to report aloud what they are thinking when solving typical problems. Observation of actual online interactions between tutors and students provides information related to the processes used in problem-solving, which is useful for building dialogue or interactivity into tutoring systems.
3. Initial tutor implementation: This stage involves setting up a problem solving environment to enable and support an authentic learning process. It is followed by a series of evaluation activities as the final stage, which is characteristic of any software development process.
4. Evaluation: The final stage includes (1) pilot studies to confirm basic usability and educational impact; (2) formative evaluations of the system under development, (3) parametric studies that examine the effectiveness of system features, and (4) summative evaluations of the final tutor’s effect: learning rate and achievement levels.
Effective intelligent tutoring systems should, in theory:
1. Enable the student to work to the successful conclusion of problem solving.
2. Represent student competence as a production set.
3. Communicate the goal structure underlying the problem solving.
4. Provide instruction in the problem solving context.
5. Promote an abstract understanding of the problem-solving knowledge.
6. Minimize working memory load.
8. Adjust the grain size of instruction with learning.
9. Facilitate successive approximations to the target skill.
Benefits of Intelligent Tutoring Systems
Intelligent tutoring systems can:
1. Be available at any time of the day, even late at night before an exam.
2. Provide real-time data to instructors and developers looking to refine teaching methods.
3. Reduce the dependence on human resources
4. Help students better understand material by allowing them to first explain what they know, then by catering responses accordingly
5. Afford educators the opportunity to create individualized programs due to their personalized nature.
6. Yield higher test scores than traditional systems, especially in students from special education, non-native English, and low-income backgrounds.
7. Provide immediate yes/no feedback, individual task selection, on-demand hints, and support for mastery learning.
Criticism of Intelligent Tutoring Systems
There’s a number of things intelligent tutoring programs can’t do, and critics are quick to point them out. Below are a few blows to the system:
1. It is difficult to assess the effectiveness of ITS programs.
2. Immediate feedback and hint sequences fail to develop deep learning in students.
3. Systems fail to ask questions of students which might explain their actions.
4. The implementation of ITSs may be difficult to justify to an administrative staff.
5. Evaluation of an intelligent tutoring system is often difficult, costly, and time consuming.
6. Human tutors are currently better able to provide appropriate dialogue and feedback.
7. Human tutors are currently better able to interpret and adapt to different emotional states.
Even though there are various evaluation techniques presented in the literature, there are no guiding principles. Careful inspection should be undertaken to ensure that a complex intelligent tutoring system does what it claims to do. This assessment may occur during the design and early development of the system to identify problems and to guide modifications (formative) or after the completion of the system to support formal claims about the construction, behaviour of, or outcomes associated with a completed system (summative).
Despite obvious setbacks, progress is being made in the interest of educational improvement. Designers are now developing functions that allow intelligent tutors to read individuals’ expressions and other signs of emotion in an attempt to engage them, for example. There are many complications in doing this, since emotion is expressed in multiple ways. Nevertheless, these ideas have created a new field within ITS called Affective Tutoring Systems (ATS) to address such complications.
One example of an ITS that addresses emotion is Gaze Tutor, a system developed to track students eye movements to determine whether students are bored or distracted.
Within education there is a plethora of intelligent tutoring systems. An exhaustive list does not exist but several of the more influential programs are listed below.
1. The Cognitive Tutor: Carnegie Mellon University first introduced the Cognitive Tutor, a system that has been widely developed in several levels of math and science at schools across the United States, from algebra and geometry for secondary schools to the Genetics Cognitive Tutor that helps Carnegie Mellon students improve their understanding of gene interaction and regulation.
2. The Andes Physics Tutor and Writing Pal: Developed by Arizona State University, these systems support students in introductory physics courses and writing strategies. Writing Pal has been tested extensively with secondary students and features essay writing practice, game based practice sessions, and feedback to guide emerging writers.
3. ASSISTments: ASSISTments is a free online program developed at Worcester Polytechnic Institute that tutors students in various subjects.
4. Knewton: The privately developed Knewton provides custom learning assistance for students in K-12 and higher education as well as intelligent tutors for the GMAT, LSAT, and SAT. The platform provides instant feedback for students while offering important analytic data to instructors and course designers.
5. Mathematics Tutor: The Mathematics Tutor helps students solve word problems using fractions, decimals and percentages. The tutor records the success rates while a student is working on problems while providing subsequent, lever-appropriate problems for the student to work on. The subsequent problems that are selected are based on student ability and a desirable time in is estimated in which the student is to solve the problem.
6. eTeacher: eTeacher is an intelligent agent that supports personalized e-learning assistance. It builds student profiles while observing student performance in online courses. eTeacher then uses the information from the student’s performance to suggest a personalized courses of action designed to assist their learning process.
7. ZOSMAT: ZOSMAT was designed to address all the needs of a real learning environment. It follows and guides a student in different stages of their learning process. This is a student-centered ITS, meaning it records the progress of a student’s learning and changes based on the student’s effort. ZOSMAT can be used for either individual learning or in a real learning environment alongside the guidance of a human tutor.
8. REALP: REALP was designed to help students enhance their reading comprehension by providing reader-specific lexical practice and offering personalized practice with useful, authentic reading materials gathered from the Web. The system automatically builds a user model according to student’s performance. After reading, the student is given a series of exercises based on the target vocabulary found in reading.
9. CIRCSlM Tutor: CIRCSIM Tutor is an intelligent tutoring system that is used with first year medical students at the Illinois Institute of Technology. It uses natural dialogue based Socratic language to help students learn about regulating blood pressure.
10. Why2-Atlas: Why2-Atlas is an ITS that analyses students’ explanations of physics principles. The students input their work in paragraph form and the program converts their words into a proof by making assumptions of student beliefs that are based on their explanations. In doing this, misconceptions and incomplete explanations are highlighted. The system then addresses these issues through a dialogue with the student and asks the student to correct their essay. A number of iterations may take place before the process is complete.
11. SmartTutor: The University of Hong Kong (HKU) developed a SmartTutor to support the needs of continuing education students. Personalized learning was identified as a key need within adult education at HKU and SmartTutor aims to fill that need. SmartTutor provides support for students by combining Internet technology, educational research, and artificial intelligence.
12. AutoTutor: AutoTutor assists college students in learning about computer hardware, operating systems, and the Internet in an introductory computer literacy course by simulating the discourse patterns and pedagogical strategies of a human tutor. AutoTutor attempts to understand learner’s input from the keyboard and then formulate dialog moves with feedback, prompts, correction and hints.
13. ActiveMath: ActiveMath is a web-based, adaptive learning environment for mathematics. This system strives to improve long-distance learning and support individual and lifelong learning.
14. Cardiac Tutor: The Cardiac Tutor’s aim is to support medical personnel with advanced cardiac treatment techniques. The tutor presents cardiac problems and, using a variety of steps, students must select various interventions. Cardiac Tutor provides clues, verbal advice, and feedback in order to personalize and optimize the learning. Each simulation, regardless of whether the students are successfully able to help their patients, results in a detailed report which students then review.
15. CODES: The Cooperative Music Prototype Design is a Web-based environment for cooperative music prototyping. It was designed to support users, especially those who are not specialists in music, in creating musical pieces in a prototyping manner. The musical examples (prototypes) can be repeatedly tested, played, and modified. One of the main aspects of CODES is interaction and cooperation between the music creators and their partners.
In 1988, the Intelligent Tutoring Systems Conference was created by Claude Frasson of Canada. It is typically held every other year. The 2012 conference was held in Chania (Crete) and hosted by George Papadourakis, Stefano Cerri, and William Clancey. For more information on intelligent tutoring systems, refer to the International Artificial Intelligence in Education (AIED) Society, which publishes The International Journal of Artificial Intelligence in Education (IJAIED) and hosts the International Conference on Artificial Intelligence in Education every odd numbered year.