Different Intelligent Tutoring Systems
This page is still being processed. Please come back later!
Cognitive Tutors
is a type of Intelligent Tutoring System which uses Cognitive Science to model how a student thinks about and learns a subject. An example would be the Carnegie Cognitive Tutor.Intelligent Tutoring Systems (ITS)
"a digital technology that provides immediate and customized instruction and feedback to learners, designed to simulate a human tutor’s behavior and guidance." Groff,J., Personalized Learning: The State of the Field & Future Directions, Center for Curriculum Redesign, 2017.
Natural Language ITS
"Dialog based ITSs have the same main goal as traditional ITSs, which is to increase the level
of engagement and learning gains. However, dialog based ITSs can use different dimensions of
evaluation in classifying learner’s responses, comprehending learner’s contributions, modeling
knowledge, and generating conversationally smooth tutorial dialogs. D’Mello and Graesser [113]
conducted a study to describe how dialog based ITSs can be evaluated along these dimensions
using AutoTutor as a case study." Alkhatlan, A., Kalita, J.K., Intelligent Tutoring Systems: A Comprehensive Historical
Survey with Recent Developments, International Journal of Computer Applications 181(43):1-20, March 2019
Spoken Dialog
"One advantage is in terms
of self-explanation, which gives the student a better opportunity to construct his/her knowledge
[115]. For instance, Hauptmann et al. showed that self-explanation happens more often in speech
than in typed interaction [116]. Another advantage is that speech interaction provides a more
accurate student model. Students use meta-communication strategies such as hedges, pauses, and
disfluencies, which allow the tutor to infer more information regarding student understanding. The
following will discuses some computer tutors, which implement spoken dialogue [114] [115].
ITSPOKE is an ITS which uses spoken dialogue for the purpose of providing spoken feedback and
correcting misconceptions [117]. The student and the system interact with each other in English
to discus the student’s answers. ITSPOKE uses a microphone as an input device for the student’s
speech and sends the signal to the Sphinx2 recognizer [118]. Litman et al. showed that ITSPOKE
is more effective than typed dialogue; however, there was no evidence that ITSPOKE increases
student learning [114]. In addition, it was clear that speech recognition errors did not decrease
learning."Alkhatlan, A., Kalita, J.K., Intelligent Tutoring Systems: A Comprehensive Historical
Survey with Recent Developments, International Journal of Computer Applications 181(43):1-20, March 2019
Affective Tutoring System
"Affective Tutoring Systems (ATS) are ITSs that can recognize human emotions (sad, happy, frustrated,
motivated, etc.) in different ways [119]. It is important to incorporate the emotions of
students in the learning process because recent learning theories have established a link between
emotions and learning, with the claim that cognition, motivation and emotion are the three components
of learning [120][121]. Over the last few years, there has been a great amount of interest in
computing the learner’s affective states in ITSs and studying how to respond to them in effective
ways [122].
Affective tutors use various techniques to enable computers to recognize, model, understand and
respond to students’ emotions in an effective manner. Knowing the emotional states of the student
provides information on the student’s psychological states and offers the possibility of responding
appropriately [119]. A system can embed devices to detect a student’s affective or emotional states.
These include PC cameras, PC microphones, special mouses, and neuro-headsets among others.
These devices are responsible for identifying physical signals such as facial image, voice, mouse
pressure, heart rate and stress level. These signals are then sent to the system to be processed.
Consequently, the emotional state is obtained in real time. The ATS objective is to change a negative
emotional state (e.g., confused) to a positive emotional state (e.g. committed) [72].
In [123], the learners’ affective states are detected by monitoring their gross body language (body
position and arousal) as they interact with the system. An automated body pressure measurement
system is also used to capture the learner’s pressure. The system detects six affective states of the learner: confusion, flow, delight, surprise, boredom and neutral. If the system realizes that the
student is bored, the tutor stimulates him by presenting engaging tasks. If frustration is detected,
the tutor offers encouraging statements or corrects information that the learner is experiencing
difficulty with. Experiments suggest that that boredom and flow might best be detected from body
language although the face plays a significant role in conveying confusion and delight.
Jraidi et al. present an ITS that acts differently when the student is frustrated [124]. For example,
it may provide problems similar to ones in which the student has been successful to help the student.
In case of boredom, the system provides an easier problem to motivate the student again or provides
a more difficult problem if the problem seems too easy. Another approach used in the system to
respond to student emotions integrates a virtual pedagogical agent called a learning companion
to allow affective real time interaction with the learners. This agent can communicate with the
learner as a study partner when solving problems, or provide encouragement and congratulatory
messages, appearing to care about the learner. In other words, these agents can provide empathic
responses which mirror the learner’s emotional states [72].
Wolf and his colleagues also implement an empathetic learning companion that reflects the last
expressed emotion of the learner as long as the emotion is not negative such as frustration or
boredom [125][126]. The companion responds in full sentences providing feedback with voice and
emotion. The presence of someone who appears to care can be motivating to the learners. Studies
show that students who use the learning companion increased their math understanding and level
of interest, and show reduced boredom. Another affective tutoring system that uses an empathetic
companion to respond to learner emotion is a system that practices interview questions with users
[127]. The system perceives the user’s emotion by measuring skin conductance and then takes
appropriate actions. For instance, the agent displays concern for a user who is aroused and has a
negatively valenced emotion, e.g., by saying “I am sorry that you seem to feel a bit bad about that
question”. Their study shows that users receiving feedback with empathy are less stressed when
asked interview questions."Alkhatlan, A., Kalita, J.K., Intelligent Tutoring Systems: A Comprehensive Historical
Survey with Recent Developments, International Journal of Computer Applications 181(43):1-20, March 2019
"information can be used to enhance learning by means of nudges that move
students out of negative states such as boredom or frustration that inhibit learning
into positive states such as engagement or enjoyment. Affective states can be
detected through computational analysis of data extracted from speech, facial
expressions, eye tracking, body language, physiological signals, or combinations
of these (D'Mello and Kory, 2015). In the iTalk2Learn system, for example, a
student’s affective state is determined through detection of keywords and prosodic
features in their speech as they talk aloud when interacting with the system
(Grawemeyer et al., 2015b). Such detailed student modelling can enable affect aware support for the student, which has been shown to contribute to reducing boredom and off-task behavior, with promising effects on learning
(Grawemeyer et al.,, in press). "
du Boulay, Ben; Poulovasillis, Alexandra; Holmes, Wayne and Mavrikis, Manolis (2018). Artificial Intelligence And Big Data Technologies To Close The Achievement Gap. In: Luckin, Rose ed. Enhancing Learning and Teaching with Technology. London: UCL Institute of Education Press, pp. 256–285
"In his commentary of VanLehn’s review (2006) of ITS du Boulay (2006) noted that
the affective, motivational and metacognitive state of the student has only “fleetingly”
been addressed inmost learning systems. Traditional educational systems “have operated
largely at the cognitive level and have assumed that the learner is already able to manage
her own learning, is already in an appropriate affective state and also is already motivated
to learn” (du Boulay et al. 2010, p.197).
In recent years, recognizing the limitations of “cognition-only” approaches, researchers
have begun to model key aspects of students’ motivation, affect, and meta-cognition with
the aim of providing adaptive scaffolding for addressing differences in these areas (Desmarais
and Baker 2012)." Essa, A., A possible future for next generation adaptive learning systems, Smart Learning Environments, 3, 16, 2016
"In his commentary of VanLehn’s review (2006) of ITS du Boulay (2006) noted that
the affective, motivational and metacognitive state of the student has only “fleetingly”
been addressed inmost learning systems. Traditional educational systems “have operated
largely at the cognitive level and have assumed that the learner is already able to manage
her own learning, is already in an appropriate affective state and also is already motivated
to learn” (du Boulay et al. 2010, p.197).
In recent years, recognizing the limitations of “cognition-only” approaches, researchers
have begun to model key aspects of students’ motivation, affect, and meta-cognition with
the aim of providing adaptive scaffolding for addressing differences in these areas (Desmarais
and Baker 2012)." Essa, A., A possible future for next generation adaptive learning systems, Smart Learning Environments, 3, 16, 2016
Game-based Tutoring Systems
"The novelty of an ITS and its interactive components is quite engaging when they are used for
short periods of time (e.g., hours), but can be monotonous and even annoying when a student is required to interact with an ITS for weeks or months [132]. The underlying idea for game based
learning is that students learn better when they are having fun and engaged in the learning process.
Game based tutoring systems engage learners to interact actively with the system, thereby
making them more motivated to use the system for a longer time [133]. Whereas the ITS principles
maximize learning, the game technologies maximize motivation. Instead of learning a subject in
a conventional and traditional way, the students play an educational game which successfully
integrates game strategies with curriculum-based contents. Although there is no overwhelming
evidence supporting the effectiveness of educational game based systems over computer tutors,
it has been found that educational games have advantages over traditional tutoring approaches
[134][135]. Moreno and Mayer [136] summarize characteristics of educational games that make
them enjoyable to operate. These are interactivity, reflection, feedback, and guidance.
To enhance both engagement and learning, Rai and Beck implemented game-like elements in
their math tutor [137]. The system provides a math learning environment and the students engage
in a narrated visual story. Students help story characters solve the problem in order to move the
story forward as shown in Figure 4. Students receive feedback and bug messages as when using a
traditional tutor. The study found that students are more likely to interact with the version of the
math tutor that contains game-like elements; however, the authors suggest adding more tutorial
features to a game-like environment for higher levels of learning.
Another tutoring system that uses an educational game approach is Writing Pal (W-Pal), which
is designed to help students across multiple phases of the writing process [138]. Crystal Island is a
narrative-centered learning environment in biology, where students attempt to discover the identity
and source of an infectious disease on a remote island. The student (player) is involved in a scenario
of meeting a patient and attempts to perform a diagnosis. The study of educational impact using
a game based system by Lester at el. [139] found that students answer more questions correctly
on the post-test than the pre-test, and this finding was statistically significant. Additionally, there
was a strong relationship between learning outcomes, in-game problem solving and increased
engagement"
