E-learning Student Engagement and Disengagement Image Dataset for Educational Research

The Student Engagement and Disengagement Image Dataset appears to be a valuable resource for research focused on recognizing student engagement levels in e-learning environments. High quality images of students are required to solve classification and recognition problem of student engagement and disengagement in e-learning. To build the machine learning models, neat and clean dataset is the elementary requirement. With this objective we have created the dataset of the Student Engagement and Disengagement Image Dataset, comprising 16,000 images of students aged 5+ years.
The dataset was divided into two primary categories: Engagement and Disengagement, reflecting the behavioral states of the students. These two main folders were then subdivided into four age groups: 5-10 years, 11-15 years, 16-20 years, and 21 and above years. To further categorize the dataset, each age group folder was divided into gender-specific subfolders, labeled as "Boy" and "Girl"
Dataset Structure
Categories:
• Engagement: Images of students actively engaged in their e-learning activities, displaying focus and participation.
• Disengagement: Images of students showing signs of distraction, boredom, or lack of attention during the learning process.
Age Groups: The dataset is organized into four distinct age categories to cover different developmental stages:
• 5-10 years
• 11-15 years
• 16-20 years
• 21 and above years
Gender Subfolders: Each age group is further subdivided by gender:
• Boy
• Girl
All images were captured using high-resolution mobile phone cameras, ensuring clear and detailed visuals suitable for machine learning applications. The images were taken in diverse environments with different backgrounds and lighting conditions to make the dataset robust and adaptable to real-world e-learning scenarios.
The proposed dataset can be used for training, testing, and validation of machine learning models designed to classify or recognize student engagement and disengagement in e-learning environments.

学生参与度与疏离度图像数据集似乎成为研究识别电子学习环境中学生参与水平的重要资源。为了解决电子学习中学生参与与疏离的分类与识别问题，需收集高质量的学生图像。构建机器学习模型，整洁且纯净的数据集是基本要求。为此，我们创建了学生参与度与疏离度图像数据集，该数据集包含5岁及以上学生的16,000张图像。数据集被分为两大类：参与与疏离，反映了学生的行为状态。这两个主要文件夹随后被细分为四个年龄段：5-10岁、11-15岁、16-20岁以及21岁及以上。为了进一步分类数据集，每个年龄段文件夹被划分为性别特定的子文件夹，分别标记为“男孩”和“女孩”。

数据集结构

类别：
• 参与度：展示学生积极参与电子学习活动、展现专注与参与的图像。
• 疏离度：展示学生在学习过程中表现出分心、无聊或注意力缺失的图像。
年龄段：该数据集被组织为四个不同的年龄段，以涵盖不同的发育阶段：
• 5-10岁
• 11-15岁
• 16-20岁
• 21岁及以上
性别子文件夹：每个年龄段进一步细分为性别特定的子文件夹：
• 男孩
• 女孩
所有图像均使用高分辨率手机摄像头拍摄，确保清晰且详细的视觉图像，适用于机器学习应用。图像在多样化的环境中拍摄，具有不同的背景和光照条件，以使数据集更加坚韧且适应现实世界的电子学习场景。
所提议的数据集可用于训练、测试和验证旨在在电子学习环境中对学生的参与与疏离进行分类或识别的机器学习模型。