AutoTutor and affective autotutor: Learning by talking with cognitively and emotionally intelligent computers that talk back

  title={AutoTutor and affective autotutor: Learning by talking with cognitively and emotionally intelligent computers that talk back},
  author={Sidney K. D’Mello and Arthur C. Graesser},
  journal={ACM Trans. Interact. Intell. Syst.},
We present AutoTutor and Affective AutoTutor as examples of innovative 21st century interactive intelligent systems that promote learning and engagement. [] Key Method AutoTutor constructs a cognitive model of students' knowledge levels by analyzing the text of their typed or spoken responses to its questions. The model is used to dynamically tailor the interaction toward individual students' zones of proximal development.

Figures from this paper

AutoTutor and Family: A Review of 17 Years of Natural Language Tutoring
This paper summarizes and integrates significant findings produced by studies using AutoTutor and related systems, and considers advances in pedagogical agent roles and in tutoring technologies, such semantic processing and tutoring delivery platforms.
Conversations with AutoTutor Help Students Learn
  • A. Graesser
  • Education
    International Journal of Artificial Intelligence in Education
  • 2015
This article selectively highlights the status of AutoTutor’s dialogue moves, learning gains, implementation challenges, differences between human and ideal tutors, and some of the systems that evolved from autoTutor.
Cognitive Intelligent Tutoring System based on Affective State
The goal of the virtual tutor is to mimic like a human tutor in order to advance the communication and effectiveness of the students learning experience and to improve the student’s interaction and to engage their attention.
An Affect-Aware Intelligent Tutoring System for EmoRegulators: A Restricted-Perception Wizard-of-Oz Approach
This project addresses the problem of how to create an intelligent, adaptive system capable of being aware of, understanding and regulating players’ emotions during an interaction session in EmoRegulators, a serious game that teaches players to be aware of their emotions and to regulate them with a model heavily based on restricted perception Wizard-of-Oz studies.
Virtual tutor and pupil interaction: A study of empathic feedback as extrinsic motivation for learning
Results showed that the overall duration of agent-pupil interactions varied, children found the bimodal agent more empathic, and produced significantly more correct answers, and there was a positive correlation between accuracy and mean reaction times for correct answers with the bIModalAgent.
Automated Disengagement Tracking Within an Intelligent Tutoring System
A new automated disengagement tracking system (DTS) that detects learners’ maladaptive behaviors, e.g. mind-wandering and impetuous responding, in an intelligent tutoring system (ITS), called AutoTutor is described.
Impact of Individual Differences on Affective Reactions to Pedagogical Agents Scaffolding
It is shown that achievement goals and personality traits can significantly modulate students’ affective reactions to the PAs in MetaTutor, a hypermedia-based intelligent tutoring system.
The Application of Affective Computing Technology to E-Learning
This chapter discusses the domain of affective computing and reviews the area of affective tutoring systems: e-learning applications that possess the ability to detect and appropriately respond to
AFFLOG: A Logic Based Affective Tutoring System
In this work, the Affective Logic (AFFLOG) Tutor is presented. An Affective Tutoring System that uses knowledge representation and reasoning tools such as Answer Set Programming and the Event


Responding to Learners' Cognitive-Affective States with Supportive and Shakeup Dialogues
Two affect-sensitive variants of an existing intelligent tutoring system called AutoTutor are described, one of which addresses the presence of the negative states by providing empathetic and encouraging responses and the other takes students to task by directly attributing the source of the emotions to the learners themselves and responding with witty, skeptical, and enthusiastic responses.
AutoTutor Improves Deep Learning of Computer Literacy : Is it the Dialog or the Talking Head ?
All versions of AutoTutor improved performance in assessments of deep learning, but not shallow learning; effects of the medium were more subtle, which suggests that it is the message (the dialog moves of autoTutor) that is more important.
Emotions and Learning with AutoTutor
The relationship between emotions and learning was investigated by tracking the emotions that college students experienced while learning about computer literacy with AutoTutor, which revealed that post-test scores were significantly predicted by pre- test scores and confusion, but not by any of the other emotions.
Predicting Affective States expressed through an Emote-Aloud Procedure from AutoTutor's Mixed-Initiative Dialogue
Correlation and regression analyses confirmed the hypothesis that dialogue features could significantly predict the affective states of confusion, eureka, and frustration, and discussed the prospects of extending AutoTutor into an affect-sensing intelligent tutoring system.
Teaching Tactics and Dialog in AutoTutor
The Tutoring Research Group at the University of Memphis has developed a computer tutor that simulates the discourse patterns and pedagogical strategies of a typical human tutor and contrasts two versions that follow somewhat different teaching tactics.
AutoTutor Detects and Responds to Learners Affective and Cognitive States
The affect-sensitive AutoTutor detects the emotions of a learner by monitoring conversational cues, gross body language, and facial features, and synthesizes affective responses through animated facial expressions and modulated speech.
AutoTutor: A simulation of a human tutor
A Time for Emoting: When Affect-Sensitivity Is and Isn't Effective at Promoting Deep Learning
An affect-sensitive version of AutoTutor, a dialogue based ITS that simulates human tutors, is developed and evaluated and indicated that the affective tutor improved learning for low-domain knowledge students, particularly at deeper levels of comprehension.
AutoTutor: A tutor with dialogue in natural language
The design was inspired by explanation-based constructivist theories of learning, intelligent tutoring systems that adaptively respond to student knowledge, and empirical research on dialogue patterns in tutorial discourse.
Aplicaciones del diálogo humano de tutoría al autotutor: un sistema inteligente de tutoría
The dialog patterns from natural tutoring interactions with AutoTutor are explored and how short pedagogical feedback is related to learning is analyzed to support the conclusion that autoTutor is an effective intelligent tutoring system that uses pedagogy strategies that are appropriate for individual learners.