Treffer: Dataset for MOOC Update Optimization using NSGA-II (Cyber Security MOOC, SWAYAM, July 2024)

This dataset supports the research study on multi-objective optimization of MOOC updates for the Introduction to Cyber Security course on SWAYAM. It integrates anonymized learner survey data, a structured Candidate Updates Table, optimization code, and full outputs generated using the Non-Dominated Sorting Genetic Algorithm II (NSGA-II). The dataset is a revised and extended release of an earlier version. It corrects prior inconsistencies, adds missing details (objective function definitions, diversity metric, reproducibility elements), and includes all appendices and outputs referenced in the manuscript. Contents MOOC_Feedback_Anonymized.csv 437 anonymized survey responses collected during the July 2024 course cycle. Includes open-ended qualitative feedback and structured survey items. Candidate_Updates_Table.csv Structured dataset of 26 candidate course updates derived from survey feedback. Attributes: Update description, normalized learner value (0–1), effort units (1–3), category (content, assessment, engagement, support). nsga2_mooc_update_planning.py Final working Python/Colab implementation of NSGA-II. Includes Pareto optimization routine, Shannon entropy diversity metric, and reproducibility settings (population size, generations, mutation/crossover rates, random seed). nsga_outputs.zip Generated results from optimization experiments across budgets B = 8, 10, 12, 14, 16. Files include: Pareto tables (CSV) for each budget Pareto front plots (PNG) Convergence diagnostics (PNG) Representative solutions (Table 7, CSV) README.md Instructions for replicating the optimization workflow in Google Colab. Guidance on file structure, dependencies, and how to regenerate tables and figures reported in the paper. Usage Notes The dataset enables independent reproduction of Figures 1–6 and Tables 1 & 7 in the associated manuscript. All survey responses are anonymized to protect participant privacy. Code and data are provided under an open license to encourage reuse in related MOOC optimization research.