Abstract

The growing adoption of e-learning in police education underscores the need for instructional designs that are cognitively efficient, pedagogically grounded, and informed by data driven insights. This study integrates Cognitive Load Theory (CLT), Multimedia Learning Theory (MLT), and Learning Analytics (LA) to evaluate and improve the effectiveness of digital learning modules at the Dubai Police Academy. Using LMS behavioral data from 321 cadets, the research analyzes engagement patterns, performance indicators, and learner perceptions of instructional clarity, multimedia integration, and cognitive load. A Random Forest model was developed to examine whether pre-assessment behavioral metrics specifically logins, time spent on tasks, and module completion rates can serve as reliable predictors of academic success. To ensure methodological validity, assessment-based variables such as quiz scores were excluded from the feature set to prevent target leakage, allowing the model to rely solely on behavioral indicators rather than outcome based information. The behavioral only model demonstrated that consistent engagement, particularly higher levels of module completion, is a strong early indicator of cadet performance. These findings highlight the importance of reducing extraneous cognitive load, improving the coherence of multimedia materials, and leveraging predictive analytics to support timely instructional interventions. The study concludes by presenting an integrated framework that unites cognitive theory with behavioral analytics to guide the development of adaptive, personalized elearning experiences tailored to the operational and educational needs of law enforcement training environments.

Publication Date

4-28-2025

Document Type

Thesis

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research

Advisor

Ayman Ibrahim

Comments

This thesis has been embargoed. The full-text will be available on or around 3/3/2027.

Campus

RIT Dubai

Download

Share

COinS