Special Issues now open for submissions

Here are the special issues that is accepting submissions: The following special issues have closed for submissions and the submissions are under review. You can look forward to these in the coming issues of the journal.




Learning at Scale: What Works & Lessons Learned

Special Issue Associate Editors

Daniel M. Russell email Google, Inc., USA
Ido Roll email University of British Columbia, Canada
Dragan Gasevic email University of Edinburgh, UK

Important Dates

Submission of complete manuscript December 18, 2016
Reviews sent to authors February 11, 2017
Revised manuscript due April 16, 2017
Reviews sent to authors June 16, 2017
Final version of manuscript due August 16, 2017
Publication of Special Issue Each paper will appear on Online First as soon as it has been accepted and processed.
The full Special Issue will be assembled in the third quarter of 2017.

Submission instructions

Submit papers at http://aied.edmgr.com/ using the special submission type: "SI L@S".

Motivation and Scope

The annual Learning at Scale conference series (http://learningatscale.acm.org/las2016/) has created a track record of high quality papers about the practices, methods, and science for teaching large numbers of students. This special issue will consolidate what we have found that works well in terms of pedagogy, technology, analytics, and theory. Overall, this special issue will make a contribution to the science and practice of large online learning/teaching systems.

For this special issue we solicit paper submissions reporting on rigorous research on methodologies, studies, analyses, tools, pedagogies, or technologies for learning at scale. Learning at Scale includes MOOCs, games (including massively multiplayer online games), citizen science communities, and other types of learning environments which (a) provide learning experiences to large number of learners and/or (b) produce detailed, high volume data about the learning process.

Papers that tackle specific aspects of scale are particularly encouraged, for example, papers that deal with learning or educational phenomena that can only occur, be supported, or be observed with very large numbers of students, or in which the system improves after being exposed to data from previous use by many students.

Topic of Interests

The scope includes (but is not limited to) the topics:
  • Usability studies and effectiveness studies of design elements for students or instructors, including:
    • Status indicators of student progress
    • Status indicators of instructor effectiveness
    • Tools and pedagogy to promote community, support learning, or increase retention in at-scale environments
  • Analysis of log data about student behavior, e.g.:
    • Assessing reasons for student outcome as determined by modifying tool design
    • Modeling students based on responses to variations in tool design
    • Evaluation strategies such as quizzes or discussion forum design
    • Instrumenting systems and data representation to capture relevant indicators of learning.
  • Personalization and adaptation, based on log data, user modeling, or choice.
  • Studies of applications of existing and newly developed learning theories to the MOOC context (peer learning, project based learning, etc.).
  • Large online learning in the developing world
  • New tools and techniques for learning at scale, including:
    • Games for learning at scale
    • Automated feedback tools (for essay writing, programming, etc)
    • Automated grading tools
    • Tools for interactive tutoring
    • Tools for learner modeling
    • Interfaces for harnessing learning data at scale
    • Innovations in platforms for supporting learning at scale
    • Tools to support for capturing, managing learning data
    • Tools and techniques for managing privacy of learning data
  • Investigation of observable student behaviors and their correlation with learning, e.g.:
    • What do more successful learners do more of?
    • What do more successful instructors do more of?
    • Self- and co-regulation of learning at scale
    • Collaborative learning in courses that have scale
    • Depth and retention of learning and understanding
  • Improvements to learning, community, and pedagogy in large-scale in-person and blended online and in-person courses
    • Instructional principles for learning at scale
    • Facilitation of informal subcommunities



Generalized Intelligent Framework for Tutoring (GIFT): Creating a stable and flexible platform for innovations in AIED research

Special Issue Associate Editors

Robert Sottilare, email Army Research Laboratory, USA
Arthur Graesser, email University of Memphis, USA
James Lester, email North Carolina State University, USA
Ryan Baker, email Teachers College of Columbia University, USA

Important Dates

Submission of Complete Manuscripts August 17, 2016
Reviews due to authors October 17, 2016
Revisions due December 31, 2016
Second round of reviews to authors Feb 28, 2017
Camera-ready version March 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 third 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:
  • 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 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



MARWIDE: Multidisciplinary Approaches to Reading and Writing Integrated with Disciplinary Education

Special Issue Associate Editors

Danielle McNamara, email Arizona State University, USA
Smaranda Muresan, email Columbia University, USA
Rebecca J. Passonneau, email Columbia University, USA
Dolores Perin, email Teachers College of Columbia University, USA

Submission instructions

Submit papers at http://aied.edmgr.com/ using the special submission type: "SI ­ MARWIDE".

Motivation

As students progress through their formal education, they face enormous challenges in extending their language skills to reading and writing, and adapting them to specific genres and subject matter areas, each with their own conventions. Development of a wide range of new technologies to support students’ learning of reading, writing and discussion skills across subject matter areas is becoming increasingly critical, due to long­standing trends in students’ lack of proficiency in reading and writing, as reported by the National Center for Education Statistics. Relevant research to support these skills is distributed across several fields, including learning design, the psychology of reading and writing, natural language processing, and human­ computer interaction. The MARWIDE special issue provides an opportunity for practitioners and researchers from diverse fields to present new work that demonstrates the benefits of interdisciplinary approaches to support students’ integration of written language skills (reading and writing) with subject matter learning. Given the repeated refrain from various councils on education and from leaders in the workforce that many high school students graduate with less than ideal reading and writing skills, juxtaposed against the powerful role that good written communication skills can play in lifelong learning, the benefits of technology and educational practices that can help students acquire these skills inside and outside the classroom can be profound. This special issue invites previously unpublished work on computer-­based learning to support students’ development of written language skills in science, social science, English language arts, and other subject areas.

Topic of Interests

The scope includes (but is not limited to) the topics:
  • Collaborative learning environments and methods to support one or more of students’ discussion skills, writing skills, reading skills
  • Analysis of genre-­dependent discussion, writing or reading skills
  • Automated analysis of students’ writing to understand their mastery of content, argumentation, or other aspects of disciplinary learning
  • Intelligent tutoring systems for students’ reading or writing
  • Research on students’ writing-­to­-learn, reading­-to­-learn, or similar practices
  • Student engagement with computer-­based learning environments for reading or writing
  • Automated methods for quantitative or qualitative assessment of students’ writing
  • Automated analysis of classroom discourse
  • Teachers’ use of computer-­based methods to support reading or writing instruction, or classroom discussion
  • Longitudinal analyses of students’ acquisition of reading, writing or discussion skills
  • Analysis of students’ meta­-comprehension of their reading, writing or discussion skills
  • Computer-­based support for peer learning of reading, writing or discussion skills
  • Differences in educational conventions for reading and writing skills across genres
  • Interdependence of reading and writing skills
  • Component skills involved in mastery of reading or writing and educational interventions directed at specific skills



Special issue on AI-supported Education in Computer Science

Special Issue Associate Editors

Nguyen-Thinh Le, email Humboldt Universität zu Berlin, Germany
Kristy Boyer, email North Carolina State University, USA
Sharon I-Han Hsiao, email Arizona State University, USA
Sergey Sosnovsky, email German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany
Tiffany Barnes, email North Carolina State University, USA

Submission instructions

Submit papers at http://aied.edmgr.com/ using the special submission type: "Special issue on AI-supported Education in Computer Science".

Motivation

Over the last two decades, Computer Science (CS) has emerged as a field of study at almost all levels of education. At the same time, basic CS literacy has become not only an important skill required for a wide range of modern professions, but also an essential competency for everyday life. Yet, CS is a relatively young domain that is still developing effective teaching traditions. CS is also a very dynamic domain, where technologies, skills and even subfields are constantly emerging and evolving.

The field of CS education faces tremendous challenges related to improving the quality of CS instruction and increasing the diversity of students in CS classes. One of the solutions to these problems lies with effective technology-enhanced learning and teaching approaches, and, especially, those enhanced with AI techniques.

The challenge of developing AI support for CS education has two complementary foci. First, the field needs to see innovative and highly effective tools that support core CS competencies, such as computational thinking and modeling, program understanding, writing, debugging, and testing. Such tools should rely on deeper understanding of CS pedagogy, CS students and the CS-related domains, and advanced AI techniques to support it. Second, teachers who are working to employ existing and emerging tools need support on several fronts: for integrating those tools into their educational practices, customizing and restructuring learning activities, and creating new ones. By addressing these challenges and problems as a research community, we will be poised to make great strides in building intelligent, highly effective AI-supported educational tools for CS and developing innovative approaches to support teaching and learning in this field.

The catalyst for this special issue is the workshop series AIEDCS (AI-supported Education for Computer Science) organized at the AIED and ITS conferences since 2013. In addition to carrying extended versions of the invited papers from the AIEDCS workshops, this special issue seeks innovative contributions on both technical and pedagogical aspects of design, development, and evaluation of AI-supported tools for CS education. In addition, literature review papers 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:
  • Individualized support for CS education, including both cognitive and metacognitive
  • Affect modeling in CS education
  • Adaptation and personalization in CS learning environments
  • Intelligent support for CS problem solving
  • Intelligent methods for assessment of CS literacy and/or computational thinking
  • Discourse and dialogue research related to classroom, online, collaborative, or one-on-one learning of CS
  • Authoring tools for CS education
  • Teaching and learning approaches for CS using AI-supported tools
  • Methods for peer review and support
  • Support for learning CS at scale
  • Online learning environments for CS




Formative Feedback in Interactive Learning Environments

We are pleased to invite submissions to Formative Feedback in Interactive Learning Environments, a special issue of the International Journal of Artificial Intelligence in Education (IJAIED). The special issue is open to a wide range of topics relating to learning from and providing feedback.

Special Issue Associate Editors

Ilya Goldin, email Pearson (USA)
Malcolm Bauer, email Educational Testing Service (USA)
Peter Foltz, email Pearson (USA)
Susanne Narciss, email Universität Passau (Germany)

Submission instructions

Submit papers at http://aied.edmgr.com/ using the type "SI - Feedback".

Motivation & Scope

Educators and researchers have long recognized the importance of formative feedback for learning. Formative feedback helps learners understand where they are in a learning process, what the goal is, and how to reach that goal. While experimental and observational research has illuminated many aspects of feedback, modern interactive learning environments provide new tools to understand feedback and its relation to various learning outcomes.

Specifically, as learners use tutoring systems, educational games, simulations, and other interactive learning environments, these systems store extensive data that record the learner’s usage traces. The data can be modeled, mined and analyzed to address questions including when is feedback effective, what kinds of feedback are effective, and whether there are individual differences in seeking and using feedback. Such an empirical approach can be valuable on its own, and it may be especially powerful when combined with theory, experimentation or design-based research. The findings create an opportunity to improve feedback in educational technologies and to advance the learning sciences.

These themes will be explored in a special issue of the International Journal of Artificial Intelligence in Education, which follows on a related workshop held at the International Conference of Artificial Intelligence in Education in 2013. Some of the topics relevant to the special issue are:

  • Feedback content: selecting and specifying the information provided within feedback
  • Feedback scheduling and timing, e.g., delayed vs. immediate feedback, feedback on work in progress vs. on complete work
  • Feedback sequencing, e.g., from general to specific
  • Form of feedback: discourse properties of feedback, visual presentation, multimodal presentation
  • Feedback providers: tutoring systems, virtual agents, peer learners, instructors, experts, self-assessment
  • Motivation, engagement, affect and feedback
  • Effects and outcomes: effects of feedback on current problem performance, next problem performance, transfer, retention, future learning, motivation, affect, achievement orientation
  • Research methods: analytics / data mining, theory, experimentation, design
  • Research methods: analytics / data mining, theory, experimentation, design
  • Computational models of feedback
  • Interaction of feedback with learner characteristics, including cognitive, metacognitive, affective characteristics, underserved learners, special education learners
  • Learner activities related to feedback: e.g., seeking help and feedback, proactive vs requested feedback, post-feedback behaviors, perception of feedback, acting upon feedback
  • Interaction of feedback with domain characteristics, including feedback in well-defined vs. open-ended problem-solving, design tasks, writing tasks, workplace learning, informal learning
  • Feedback in learning environments, including distance learning, blended learning, MOOCs
  • Feedback generation: automated, semi-automated, collaborative, social, crowdsourced, adaptation, personalization
  • Implementation: user interfaces, logging, instrumentation, modularization