WS CALL FOR ABSTRACTS: AI & Guided Experiential Learning

This will be a workshop aligned to the AI in Education Conference focused on Guided Experiential Learning (GEL).
Added by Goldberg, Ben over 1 year ago


CALL FOR ABSTRACTS FOR PAPERS/DEMONSTRATIONS: A Workshop on AI to Support Guided Experiential Learning (GEL)

We are excited to announce that we are hosting a FULL-DAY workshop at the upcoming International Conference on Artificial Intelligence in Education (AIED; We are inviting PAPERS and DEMONSTRATIONS that address the four themes outlined in the overview below. We are particularly interested in work that uses AI and adaptive methods to guide and support skill acquisition and higher-level learning objectives or that can be applied to do this, but will consider contributions of any type that will further a discussion about how AIED method apply to GEL.


Benjamin Goldberg, PhD:
Robby Robson, PhD:

Kevin Owens, University of Texas-Austin; Dr. Gautam Biswas, Vanderbilt University; Dr. Andy Smith, North Carolina State University; Dr. Randall Spain, US Army DEVCOM Soldier Center; Dr. Anne Sinatra, US Army DEVCOM Soldier Center; Lisa Townsend, US Army DEVCOM Soldier Center; Mike Hernandez, Eduworks; Dr. Scotty Craig, Arizona State University

AI is revolutionizing the way we learn, work, and acquire new skills. With its ability to process and analyze vast amounts of data, automatically generate con-tent, and provide intelligent tutoring support, AI is helping educators and trainers develop and deliver personalized, effective, and engaging learning experiences. This workshop explores how AI can be used to influence and optimize Guided Experiential Learning (GEL).

In 1984 Kolb defined experiential learning as “the process whereby knowledge is created through the transformation of experience” [1], often ex-pressed as learning-by-doing. In our context, GEL is a pedagogical framework for learning-by-doing that emphasizes longitudinal skill development and proficiency gained through focused, repetitive practice under real world-like conditions [2]. Critical to GEL is instructional scaffolding across an ecosystem of experiential resources that promote skill development, including games and simulations delivered using virtual-, augmented-, and mixed-reality based applications. Skills targeted using a GEL framework are developed over time under controlled conditions that are dictated by learner states and learning theory [1, 3]. Episodic events help learners codify declarative/procedural knowledge and acquire psychomotor skills with varied task contexts and complexity while providing opportunities to gain the tacit knowledge required to progress from novice to expert. While GEL is effective for all human task training, when combined with simulations it is ideal for occupations performed in volatile, uncertain, complex, and ambiguous (VUCA) settings. These include medicine, sports, military, public safety, aviation, and other industries that are investing in simulation and extended reality solutions to support training.

The complexity of designing and assessing experiential learning and the technology-enabled, data-rich environments in which GEL takes place make GEL an ideal candidate for using AI. It can assist in the design, delivery, and evaluation of experiential events that contribute to longer-term skill and proficiency objectives and to optimize learning. This leads to research challenges that form the proposed workshop themes:

  • Multi-Modal Data Strategy:
    GEL takes place across interactive environments where learners engage with physical objects, and increasingly in games and simulations supported by virtual, augmented, and mixed reality. Before any AI or machine learning (ML) techniques can be applied, strategies are needed to collect and interpret data from these environments. Multimodal learning analytics is an emerging area of AI in Education [4]. Exciting advancements are being made in the use of video, audio, and sensor data to deliver insights into student learning processes and support learner modeling. To get to AI-enabled GEL, researchers must mature a data strategy to define how sources can be collected and applied across interactive multi-modal environments.
  • Modeling Skill Acquisition and Competency
    Predictive learner analytics is another growing area of interest in AI in education. By observing learner behaviors and outcomes over time and across multiple environments, and by using sources of data that provide evidence of learning, AI can be applied to develop predictive models of learner and team competency state, which will help inform next-step pedagogical decisions and provide in-sights for talent management [5]. Evaluating the quality of a learning event on overall competency acquisition is also a critical function to enable self-optimizing learning environments designed for GEL.
  • AI and Experience Design
    Assessing the proficiency of an individual or team on a real-world task is no longer a matter of simply giving them a test and scoring it. Instead, it is necessary to observe performance across multiple trials, delivered under multiple conditions. From this perspective, a learning experience must not only be designed to support task execution; it must also be designed to allow for context-specific monitoring and assessment of foundational behaviors, processes, and procedures across a set of tasks, conditions, and standards. In addition, to support GEL, a learner requires several experiential opportunities under variations in condition and complexity [1, 3], thus creating a content creation and curation challenge.
  • Support, Feedback and Coaching
    Instructional support, feedback, and coaching are critical for GEL. Determining when, how, and what forms of feedback and support to deliver to facilitate effective learning remain open areas of research [7]. In addition, when considering GEL and longitudinal skill development, assisting learners in defining what they should practice next, and how best to practice it is a useful question that AI can help through objective analysis and decision support functions.

All papers must be original and not simultaneously submitted to another journal or conference. All figures, tables, and images must be original and not previously published.

The following paper categories are welcome:
  • Papers (5-10 pages using template) describing design, application, and/or science-based potential enhancements to GIFT
  • Demonstrations (5-6 pages using template) showcasing mature use cases that highlight advancements in performance assessments, pedagogical reasoning and coaching, data visualization, adaptive and intelligent training, and after action reviews.
  • 30 APRIL: Deadline to submit an Extended Abstract (~500 words) of the proposed work
  • 2-WEEKS FOLLOWING SUBMISSION: Decisions will be made on a rolling basis and will be based on the submitted abstract.
  • 15 JUNE: Camera-ready paper due
  • 03 or 07 JULY: Date of Workshop
  1. Kolb, D. A.: The process of experiential learning. Experiential learning: Experience as the source of learning and development. Englewood Cliffs, N.J: Prentice-Hall (1984).
  2. Hernandez, M., Blake-Plock, S., Owens, K., Goldberg, B., Robson, R., Center, S., ... Ray, F.: Enhancing the Total Learning Architecture for Experiential Learning. In Interservice/Industry Training, Simulation, and Education Conference (I/ITSEC), Orlando, FL (2022).
  3. Anders Ericsson, K.: Deliberate practice and acquisition of expert performance: a general overview. Academic emergency medicine, 15(11), 988-994 (2008).
  4. Emerson, A., Cloude, E. B., Azevedo, R., Lester, J.: Multimodal learning analytics for game‐based learning. British Journal of Educational Technology, 51(5), 1505-1526 (2020).
  5. Namoun, A., Alshanqiti, A.: Predicting student performance using data mining and learning analytics techniques: Systematic literature review. Applied Sciences, 11(1), 237 (2020).
  6. Kondratjew, H., Kahrens, M.: Leveraging experiential learning training through spaced learning. Journal of Work-Applied Management, 11(1), 30-52 (2019).
  7. Lester, J. C., Spain, R. D., Rowe, J. P., Mott, B. W.: Instructional support, feedback, and coaching in game-based learning. Handbook of game-based learning, 209-237 (2020).

2023_07_AIED-GEL_ws_agenda_1.0.pdf (91.5 KB) Goldberg, Ben, 06/14/2023 06:26 PM