Dataset for: AI-Driven Personalization of Gamification in Education: A Systematic Literature Review (2020–2025)
Description
This dataset supports the systematic literature review titled "AI-Driven Personalization of Gamification in Education: A Systematic Literature Review." It contains the complete data extraction, quality assessment scores, and coded analysis for all 75 included studies published between 2020 and 2025, retrieved from Scopus, Web of Science, and IEEE Xplore. The workbook includes: (1) search and screening records following PRISMA 2020 guidelines, (2) quality assessment scores across six criteria for each study, (3) full data extraction covering bibliographic information, AI techniques, gamification elements, learning outcomes, educational contexts, challenges, and proposed frameworks, and (4) coded summaries for each of the six research questions (RQ1–RQ6). This dataset enables full reproducibility of the review findings and supports secondary analyses by other researchers.
Files
Steps to reproduce
This dataset was produced following Kitchenham and Charters (2007) systematic review guidelines and reported per PRISMA 2020. 1. Search and Screening: Searches were conducted on January 15, 2025, across Scopus, Web of Science, and IEEE Xplore using Boolean combinations of AI, gamification, and education terms, limited to peer-reviewed journal articles (2020–2025). Records were exported in RIS format to Rayyan for deduplication and screening. From 896 initial records, 387 duplicates were removed, 509 underwent title/abstract screening, 171 proceeded to full-text review, and 75 met all inclusion criteria: (a) integration of AI and gamification, (b) educational context, (c) English-language peer-reviewed journal, and (d) 2020–2025 publication period. 2. Quality Assessment and Data Extraction: Each study was scored against six criteria (relevance, AI clarity, gamification integration, methodology rigor, outcome reporting, reproducibility) on a 0/0.5/1 scale (max 6). A structured Excel form captured bibliographic data, AI techniques, gamification elements, learning outcomes, educational context, challenges, and proposed frameworks. 3. Analysis: Descriptive statistics were computed per research question. Bibliometric and thematic analyses were performed using Python (pandas, matplotlib). All figures were generated programmatically from the coded dataset. Tools: Rayyan (screening), Microsoft Excel (extraction), Python 3.12 (analysis).