AI-Ready Large-Scale Student Performance Dataset: Quiz Assessments, Bloom's Taxonomy & ML Applications

📊 Dataset Overview This large-scale dataset captures student performance (426,003 data points) from 91 B.Ed (Bachelor of Education) students enrolled in a foundational Computer Literacy course during the Fall 2023 semester in Pakistan. The students typically had English as a secondary language and were encountering formal computer literacy concepts for the first time. The dataset includes detailed, anonymized student responses to 23 quizzes, each comprising 40 multiple-choice questions (MCQs). It features: ✅ Correct/incorrect answers for each question attempt. 🧠 Bloom’s Taxonomy cognitive levels (Knowledge, Comprehension, Application, etc.) tagged for each question. ⏱️ Timestamps for analyzing time-based performance patterns. 🔄 Data on both timed assessments and practice quizzes with multiple reattempts allowed. 🔢 Topic identifiers for each question. 📊 Dataset Details Participants: 91 B.Ed Students (Semester 2) Course: Computer Literacy Collection Period: September 2023 - December 2023 Number of Quizzes: 23 Questions per Quiz: 40 MCQs Total Questions (Unique): 971 Total Data Points: 426,003 individual question attempts/records Assessment Types: Includes both timed quizzes and untimed practice quizzes allowing reattempts. 📄 Documentation Please refer to the included README file (README.md) for a complete data dictionary, detailed methodology, potential research applications, and citation guidelines. DOI: 10.5281/zenodo.15070930