Hi GIFT users... below is an exciting opportunity for you to contribute to a special issue of the International Journal of AI in Education (AIED), a top-notch journal.
The title of our special issue is: Generalized Intelligent Framework for Tutoring (GIFT): Creating a stable and flexible platform for innovations in AIED research
Below are the details for the call for papers... they also appear at: http://www.ijaied.org/journal/cfp/
If you have experience with GIFT or have research that you think can contribute to the development of GIFT as a research platform, please think about contributing to this special issue.
Special Issue Associate Editors¶
- Robert Sottilare, Army Research Laboratory, USA
- Arthur Graesser, University of Memphis, USA
- James Lester, North Carolina State University, USA
- Ryan Baker, Teachers College of Columbia University, USA
Important Dates¶
- Submission of Complete Manuscripts June 17, 2016
- Reviews due to authors August 17, 2016
- Revisions due Oct 31, 2016
- Second round of reviews to authors Dec 31, 2016
- Camera-ready version Jan 31, 2017
Publication of Special Issue - Each paper will appear on the Online First as soon as it has been accepted and processed.
The full Special Issue will be assembled in the second quarter of 2017.
Submission instructions¶
Submit papers at http://aied.edmgr.com/ using the special submission type: "SI GIFT".
Motivation and Scope¶
Over the last five years, the Generalized Intelligent Framework for Tutoring (GIFT) has emerged as a standard for authoring, deploying, managing, and evaluating Intelligent Tutoring System (ITS) technologies. A goal for GIFT is to capture best practices across the spectrum of automated instruction to reduce the time and skills needed to author tutors, to enhance the effectiveness of instructional strategies implemented by tutors, and to provide a testbed for ITS researchers to evaluate various adaptive instructional tools and methods. GIFT has been used to construct and evaluate tutors in various domains including management of interaction with learners in existing external simulations, serious games, and computer-based training environments to teach physics (e.g., Newtonian Talk), training military tasks and tactics (e.g., Virtual BattleSpace and Virtual Medic), and solve cognitive problems (e.g., logic and Sudoku puzzles). To date, nearly 700 users in 50 countries and 70 organizations have used and helped improve the authoring tools, individual learner and team models, instructional management techniques, domain models, learning effectiveness evaluation tools, and architectural services in GIFT, but there is a long way to go to realize a fully generalizable architecture for cognitive, affective, physical, and social training and educational environments.
A catalyst for this special issue is the GIFT Symposium (GIFTSym) series which was originally organized as a workshop at the AIED 2013 in Memphis. GIFTSym continues annually with published proceedings and provides a forum for GIFT users and stakeholders to discuss their successes and challenges in using and evaluating GIFT across domains and learner populations. Scientists outside the GIFT user community have also participated in GIFTSym to provide critique on both the design and implementation of GIFT as a generalized tutoring architecture.
A goal of this special issue is to identify new best practices for GIFT and the ITS community. We also seek innovative AI contributions which provide the community a platform or testbed in which to conduct their research and guide them through the experimentation and analysis processes. There remain challenges with authoring ITSs (e.g., time and specialized skills required), delivering and consumption of instruction (e.g., remote sensing and intermittent connectivity), instructional management (e.g., methods to tailor instruction and selection of optimal strategies), and evaluation methods (e.g., time and skill required to set up evaluations, and consistency of evaluation methods).
This special issue also seeks innovative contributions for AI-based tools and methods which reduce experimental workload and facilitate the evaluation of ITS technology from a researcher’s point-of-view. In addition to specific designs and implementations in GIFT, we are seeking opportunities to enhance GIFT tools and methods to more efficiently acquire and analyze leaner and environment data, assess learner and team states, reduce authoring burden, and select optimal strategies and tactics. Literature reviews and meta-analyses that provide a thorough overview of the state of the art related to some aspects of the above-mentioned problems are also welcome.
Topic of Interests¶
The scope includes (but is not limited to) the topics below:
Architectural topics
- Service-oriented architectural design features for GIFT (or similar ITS frameworks)
- Multi-agent architectural designs to support learner assessment in GIFT (or similar ITS frameworks)
- ITS interoperability standards for reuse
- Team tutoring architectures
Authoring tools and methods
- AI-based authoring tools for tutoring tasks in various domains (cognitive, affective, physical, and social/collaborative)
- Integrating interactive environments (e.g., simulations and serious games) with GIFT for adaptive training
- Augmentation technologies for adaptive instruction
- Enhancing user experiences (UXs) for ITS authoring tasks
Individual learner and team modeling
- Real-time vs. long-term modeling of individual learner and team knowledge acquisition, skill development and performance
- Interoperable learner models
- Low cost, unobtrusive sensing and learner state classification
- Intelligent support to develop critical thinking and problem solving skills
Instructional management strategies
- AI-based learning and instructional strategies
- Cognitive and metacognitive support strategies
Domain modeling
- AI-based adaptation and personalization methods for learning environments
Effectiveness Measures
- Measures of learning and performance effect for individual learners and teams
- Tools for educational informatics in GIFT (or similar ITS frameworks) to support learning at scale
