International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 11 Issue: 05 | May 2024
www.irjet.net
p-ISSN: 2395-0072
A Comprehensive E-Learning Platform developed using MERN-Stack with Automated Grading Functionalities Prasad Kandalkar1, Yash Chindhe2, Samarth Langote3, Atharva Tarlekar4, Prof. Pramila M. Chawan5 1,2,3,4B. Tech Student, Dept of Computer Engineering and IT, VJTI College, Mumbai, Maharashtra, India 5Associate Professor, Dept of Computer Engineering and IT, VJTI College, Mumbai, Maharashtra, India
---------------------------------------------------------------------***-------------------------------------------------------------------React.js, and Node.js) to provide a user-friendly and interactive learning environment. But its true innovation lies in the integration of an Automated Essay Scoring (AES) system powered by machine learning. By utilizing a pretrained Long Short-Term Memory (LSTM) network, this platform can generate automated essay scores, significantly streamlining the assessment process for instructors. This not only saves valuable time but also allows for the provision of more timely feedback to students, fostering a more effective and engaging learning experience.
Abstract - The digital revolution is transforming the educational landscape, and engineering education is no exception. While traditional methods provide a strong foundation, they often struggle to adapt to the diverse learning styles and needs of contemporary students. Furthermore, manual assessment methods, particularly for essay-based assignments, create bottlenecks in the learning process. Time-consuming grading delays valuable feedback, hindering student progress and engagement. This research presents a novel solution: a comprehensive elearning platform specifically designed for engineering education, integrated with an Automated Essay Scoring (AES) system powered by machine learning. The platform leverages the MERN stack (MongoDB, Express.js, React.js, and Node.js) to provide a user-friendly and interactive learning environment. The innovative AES component utilizes a pre-trained Long Short-Term Memory (LSTM) network trained on a relevant engineering essay dataset. This allows the platform to generate automated essay scores, streamlining the assessment process for instructors and facilitating the timely delivery of feedback to students. This not only enhances instructor efficiency but also fosters a more engaging and effective learning experience.
The following sections will delve deeper into the details of this proposed platform. We will explore the benefits of e-learning platforms in engineering education, examine relevant research on AES, and provide a comprehensive breakdown of the system's architecture and functionalities. Furthermore, the methodology for data preprocessing, machine learning model development, and web application creation will be presented. Finally, the evaluation methods for both platform usability and AES model accuracy will be outlined.
2. LITERATURE REVIEW E-learning Platforms in Engineering Education The growing demand for accessible and flexible learning opportunities has fuelled the development and implementation of e-learning platforms in engineering education. Studies have consistently demonstrated the positive impact of these platforms on various aspects of the learning process.
Key Words: E-learning platform, MERN stack, Automated Essay Scoring (AES), Machine Learning, Engineering Education, Assessment, Feedback
1.INTRODUCTION The landscape of engineering education is undergoing a dynamic transformation. Traditional methods, while laying a strong foundation, often lack the flexibility and personalization needed to cater to the diverse learning styles and needs of today's students. Furthermore, the reliance on manual assessment practices, particularly for essay-based assignments, can create bottlenecks in the learning process. Time-consuming grading delays the delivery of valuable feedback, hindering student progress and engagement. This research addresses these challenges by proposing the development of a comprehensive e-learning platform specifically designed for engineering education. This platform leverages the power of the MERN stack (MongoDB, Express.js,
© 2024, IRJET
|
Impact Factor value: 8.226
|
Alsawadi et al. (2019) conducted a study investigating the effectiveness of a web-based learning environment for teaching undergraduate engineering courses. Their findings revealed significant improvements in student learning outcomes compared to traditional lecture-based methods.
Sun et al. (2020) explored the use of a blended learning approach that combined online modules with traditional classroom instruction for an engineering mechanics course. The results indicated that the blended learning approach led to increased
ISO 9001:2008 Certified Journal
|
Page 32