For a better experience, click the Compatibility Mode icon above to turn off Compatibility Mode, which is only for viewing older websites.

EAGER: TAEMILE: Towards Automating Experience Management in Interactive Learning Environments

PLEASE NOTE: PIs and Co-PIs are listed alphabetically.


EAGER: TAEMILE: Towards Automating Experience Management in Interactive Learning Environments


Jichen Zhu (PI)


Aroutis N. Foster, Ph.D. (Co-PI)
Assistant Professor

Glen Muschio (Co-PI)

Date of Award

Effective Dates: 9/1/13 — 8/31/14


National Science Foundation logoNational Science Foundation (NSF)

Amount of Award: $149,999


Learning, in the age of rapid technological innovation and social transformation, faces unprecedented challenges and opportunities to adapt to the evolving needs and preferences of the learners.

Learn and Lead, bands of speedy ribbonsAs interactive media grow to be more sophisticated, players increasingly expect to exercise their autonomy through various emerging forms such as user-generated content, open exploration in sandbox games and procedurally generated content that adapts to how the user interacts with the system. Similar to the positive transformations it has initiated in many other domains (e.g., interactive narrative), user autonomy, when designed well, can make the learning process more engaging and more personalized.

Studies have shown, however, that unchecked learner autonomy and unguided or pure
discovery-based learning are not the best strategies for learning. The lure of pure discovery-based learning is rooted in the erroneous assumption that most students have access to the necessary and sufficient declarative, procedural, and conditional knowledge to be meta-cognitively aware of what needs to be done and have access to adequate strategies to direct their learning. Especially in the initial stages of the learning process, learners still need a “more advanced other” such as the teacher to aid with the regulation of the cognitive, motivational, and behavioral aspects of the learning process. By contrast, guided discovery learning has many advantages over traditional didactic and pure-discovery-based learning pedagogies in scaffolding active learning and nurturing complex understanding of content. The fundamental problem and the key to all forms of interactive learning environments, is the conflict between learners’ increasing desire for autonomy and the necessary pedagogical structure needed for learning.

To address this problem, our long-term research goal is how to automatically co-regulate, balancing learners’ autonomy and the pedagogical processes intended by educators. In particular, we focus on exploring experience management (EM), a family of new AI techniques that are gaining popularity in entertainment-based interactive systems but are not yet sufficiently explored in educational domains.

Our approach is to combine EM with a transformative play-based learning pedagogical model, Play-Curricular activity-Reflection Discussion (PCaRD). We explore how to co-regulate the pedagogical process with dynamic adjustment of the game, enabled by an experience manager and the play-based pedagogical model PCaRD. As a first step towards personalized and dynamic co-regulation, this exploratory project seeks to collect preliminary data about 1) the relationship between a learner’s achievement goal orientations (learning orientation) and play style, and 2) the impact of dynamically adjusting the learning environment using EM on learner’s autonomy and learning outcomes.

We believe EM provides a promising new direction for education because the narrative paradox and the problem we want to solve are manifestations of the same conflict, that between freedom and structure.