Tutoring & learning

Paper session

会議の名前
CHI 2020
An Interaction Design for Machine Teaching to Develop AI Tutors
要旨

Intelligent tutoring systems (ITSs) have consistently been shown to improve the educational outcomes of students when used alone or combined with traditional instruction. However, building an ITS is a time-consuming process which requires specialized knowledge of existing tools. Extant authoring methods, including the Cognitive Tutor Authoring Tools' (CTAT) example-tracing method and SimStudent's Authoring by Tutoring, use programming-by-demonstration to allow authors to build ITSs more quickly than they could by hand programming with model-tracing. Yet these methods still suffer from long authoring times or difficulty creating complete models. In this study, we demonstrate that Simulated Learners built with the Apprentice Learner (AL) Framework can be combined with a novel interaction design that emphasizes model transparency, input flexibility, and problem solving control to enable authors to achieve greater model completeness in less time than existing authoring methods.

キーワード
{Simulated Learners
Interaction Design
Programming-by-Demonstration
Machine Teaching
Intelligent Tutoring Systems
著者
Daniel Weitekamp
Carnegie Mellon University, Pittsburgh, PA, USA
Erik Harpstead
Carnegie Mellon University, Pittsburgh, PA, USA
Ken R. Koedinger
Carnegie Mellon University, Pittsburgh, PA, USA
DOI

10.1145/3313831.3376226

論文URL

https://doi.org/10.1145/3313831.3376226

動画
Exploring the Potential of an Intelligent Tutoring System for Sketching Fundamentals
要旨

Sketching is a practical and useful skill that can benefit communication and problem solving. However, it remains a difficult skill to learn because of low confidence and motivation among students and limited availability for instruction and personalized feedback among teachers. There is an need to improve the educational experience for both groups, and we hypothesized that integrating technology could provide a variety of benefits. We designed and developed an intelligent tutoring system for sketching fundamentals called Sketchtivity, and deployed it in to six existing courses at the high school and university level during the 2017-2018 school year. 268 students used the tool and produced more than 116,000 sketches of basic primitives. We conducted semi-structured interviews with the six teachers who implemented the software, as well as nine students from a course where the tool was used extensively. Using grounded theory, we found ten categories which unveiled the benefits and limitations of integrating an intelligent tutoring system for sketching fundamentals in to existing pedagogy.

キーワード
Human-Computer Interaction
Drawing
Sketching
Art Education
Design Education
Sketch Recognition
Intelligent Tutoring System
User Experience Design
著者
Blake Williford
Texas A&M University, College Station, TX, USA
Matthew Runyon
Texas A&M University, College Station, TX, USA
Wayne Li
Georgia Institute of Technology, Atlanta, GA, USA
Julie Linsey
Georgia Institute of Technology, Atlanta, GA, USA
Tracy Hammond
Texas A&M University, College Station, TX, USA
DOI

10.1145/3313831.3376517

論文URL

https://doi.org/10.1145/3313831.3376517

Sara, the Lecturer: Improving Learning in Online Education with a Scaffolding-Based Conversational Agent
要旨

Enrollment in online courses has sharply increased in higher education. Although online education can be scaled to large audiences, the lack of interaction between educators and learners is difficult to replace and remains a primary challenge in the field. Conversational agents may alleviate this problem by engaging in natural interaction and by scaffolding learners' understanding similarly to educators. However, whether this approach can also be used to enrich online video lectures has largely remained unknown. We developed Sara, a conversational agent that appears during an online video lecture. She provides scaffolds by voice and text when needed and includes a voice-based input mode. An evaluation with 182 learners in a 2 x 2 lab experiment demonstrated that Sara, compared to more traditional conversational agents, significantly improved learning in a programming task. This study highlights the importance of including scaffolding and voice-based conversational agents in online videos to improve meaningful learning.

キーワード
Conversational agent
scaffolding
voice interaction
interactivity
online videos
online education
experiment
著者
Rainer Winkler
University of St. Gallen, St. Gallen, Switzerland
Sebastian Hobert
University of Goettingen, Goettingen, Germany
Antti Salovaara
Aalto University, Espoo, Finland
Matthias Söllner
University of Kassel, Kassel, Germany
Jan Marco Leimeister
University of St. Gallen, St. Gallen, Switzerland
DOI

10.1145/3313831.3376781

論文URL

https://doi.org/10.1145/3313831.3376781

Reinforcement Learning for the Adaptive Scheduling of Educational Activities
要旨

Adaptive instruction for online education can increase learning gains and decrease the work required of learners, instructors, and course designers. Reinforcement Learning (RL) is a promising tool for developing instructional policies, as RL models can learn complex relationships between course activities, learner actions, and educational outcomes. This paper demonstrates the first RL model to schedule educational activities in real time for a large online course through active learning. Our model learns to assign a sequence of course activities while maximizing learning gains and minimizing the number of items assigned. Using a controlled experiment with over 1,000 learners, we investigate how this scheduling policy affects learning gains, dropout rates, and qualitative learner feedback. We show that our model produces better learning gains using fewer educational activities than a linear assignment condition, and produces similar learning gains to a self-directed condition using fewer educational activities and with lower dropout rates.

受賞
Honorable Mention
キーワード
Online education
adaptive learning
reinforcement learning
著者
Jonathan Bassen
Stanford University, Stanford, CA, USA
Bharathan Balaji
Amazon, Seattle, WA, USA
Michael Schaarschmidt
University of Cambridge, Cambridge, United Kingdom
Candace Thille
Amazon, Seattle, WA, USA
Jay Painter
Amazon, Seattle, WA, USA
Dawn Zimmaro
Amazon, Seattle, WA, USA
Alex Games
Amazon, Seattle, WA, USA
Ethan Fast
Stanford University, Stanford, CA, USA
John C. Mitchell
Stanford University, Stanford, CA, USA
DOI

10.1145/3313831.3376518

論文URL

https://doi.org/10.1145/3313831.3376518

Isopleth: Supporting Sensemaking of Professional Web Applications to Create Readily Available Learning Experiences
要旨

Online resources can help novice developers learn basic programming skills, but few resources support progressing from writing working code to learning professional web development practices. We address this gap by advancing Readily Available Learning Experiences, a conceptual approach for transforming all professional web applications into opportunities for authentic learning. This article presents Isopleth, a web-based platform that helps learners make sense of complex code constructs and hidden asynchronous relationships in professional web code. Isopleth embeds sensemaking scaffolds informed by the learning sciences to (1) expose hidden functional and event-driven relationships, (2) surface functionally related slices of code, and (3) support learners manipulating the provided code representations. To expose event-driven relationships, Isopleth implements a novel technique called Serialized Deanonymization to determine and visualize asynchronous functional relationships. To evaluate Isopleth, we conducted a case study across 12 professional websites and a user study with 14 junior and senior developers. Results show that Isopleth’s sensemaking scaffolds helped to surface implementation approaches in event binding, web application design, and complex interactive features across a range of complex professional web applications. Moreover, Isopleth helped junior developers improve the accuracy of their conceptual models of how features are implemented by 31% on average.

著者
Joshua Hibschman
Northwestern University, Evanston, Illinois, United States
Darren Gergle
Northwestern University, Evanston, Illinois, United States
Eleanor O'Rourke
Northwestern University, Evanston, Illinois, United States
Haoqi Zhang
Northwestern University, Evanston, Illinois, United States
DOI

10.1145/3310274

論文URL

https://doi.org/10.1145/3310274