ERIC Number: EJ1220412
Record Type: Journal
Publication Date: 2019
Pages: 32
Abstractor: As Provided
ISBN: N/A
ISSN: EISSN-2227-7102
EISSN: N/A
Educational Stakeholders' Independent Evaluation of an Artificial Intelligence-Enabled Adaptive Learning System Using Bayesian Network Predictive Simulations
How, Meng-Leong; Hung, Wei Loong David
Education Sciences, v9 Article 110 2019
Artificial intelligence-enabled adaptive learning systems (AI-ALS) are increasingly being deployed in education to enhance the learning needs of students. However, educational stakeholders are required by policy-makers to conduct an independent evaluation of the AI-ALS using a small sample size in a pilot study, before that AI-ALS can be approved for large-scale deployment. Beyond simply believing in the information provided by the AI-ALS supplier, there arises a need for educational stakeholders to independently understand the motif of the pedagogical characteristics that underlie the AI-ALS. Laudable efforts were made by researchers to engender frameworks for the evaluation of AI-ALS. Nevertheless, those highly technical techniques often require advanced mathematical knowledge or computer programming skills. There remains a dearth in the extant literature for a more intuitive way for educational stakeholders--rather than computer scientists--to carry out the independent evaluation of an AI-ALS to understand how it could provide opportunities to educe the problem-solving abilities of the students so that they can successfully learn the subject matter. This paper proffers an approach for educational stakeholders to employ Bayesian networks to simulate predictive hypothetical scenarios with controllable parameters to better inform them about the suitability of the AI-ALS for the students.
Descriptors: Stakeholders, Artificial Intelligence, Bayesian Statistics, Probability, Hypothesis Testing, Problem Solving, Intelligent Tutoring Systems, Pretests Posttests, Simulation, Prediction, Evaluation Methods
MDPI AG. Klybeckstrasse 64, 4057 Basel, Switzerland. Tel: e-mail: indexing@mdpi.com; Web site: http://www.mdpi.com
Publication Type: Journal Articles; Reports - Descriptive
Education Level: N/A
Audience: N/A
Language: N/A
Sponsor: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A