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
Adaptive Learning Paths in Personalized Education: Utilizing Recommender Systems and Cosine Similarity Gousia Hazra Anjum khan1, Aashutosh Nishad2, Kalyani Netam3 , Jasmine Kispotta4 Assistant Professor, Dept. of Computer Science and Engineering, GEC Raipur, CSVTU Bhilai Student, Dept. of Computer Science and Engineering, GEC Raipur, CSVTU Bhilai Student, Dept. of Computer Science and Engineering, GEC Raipur, CSVTU Bhilai Student, Dept. of Computer Science and Engineering, GEC Raipur, CSVTU Bhilai ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Traditional learning methods have been used
embraces this diversity, offering flexible, learner-centered approaches that empower learners to take ownership of their learning journey. By providing customized pathways, adaptive resources, and targeted interventions, personalized learning systems have the potential to unlock each learner's full potential, cultivate lifelong learning habits, and bridge achievement gaps across diverse learner populations. From research we learned that Personalized learning (PL) has emerged as an effective practice to address the diverse needs of learners in recent years. Many definitions have been published to define PL by government offices, educational policy organizations, educational foundations and initiatives, influencers, and researchers. The most commonly referenced definition was provided in 2010 by the US Department of Education Office of Educational Technology, which defined personalization as “instruction that is paced to learning needs, tailored to learning preferences, and tailored to the specific interests of different learners” (US DOE, 2010). The majority of personalization efforts were centered around identifying and accommodating students’ “interests” and “needs,” though few additional details were offered to operationally define these terms. Definitions included myriad design approaches to accommodate learner characteristics, including pace, delivery approach, coverage, and sequence of instruction, as well as methods of scaffolding, delivering, and assessing mastery of content. The learner outcomes that personalized learning could target spanned motivation, skill, and achievement, and not all definitions clearly defined an aim. Perhaps the most salient feature of this thematic representation of personalized learning was the complexity endemic in the definitions. With the exception of a very general definition provided by Cuban (2018), every definition included more than one learner characteristic, design component, and/or learner outcome. This suggests that implementations of personalized learning are likely to be complex, where the effects of multiple design factors may need to be parsed or interacted, and parallel analyses may need to be conducted to examine effects on discrete variables among those targeted in a design. This complexity induces challenges for the systematic study of personalized learning, as enacted in authentic educational settings. Figure from Bernacki, Matthew & Greene, Meghan &
for years but often struggle to meet the diverse needs and preferences of individual students, decreasing learning efficiency and affecting overall outcomes. Employing the same approach for all students is not advisable. In today's digital age, students have access to abundant learning resources, yet each student's unique requirements, influenced by their mental state and background. Here personalization comes into play. Personalized learning systems that have emerged as a solution to address the diverse needs and preferences of students in a classroom. This research paper presents an approach to personalized learning using Natural Language Processing (NLP) and Machine Learning (ML) algorithms. The proposed system takes user details to generate tags and utilizes collaborative and content-based filtering techniques to recommend study content according to student preferences. By this we can improve the students’ overall performance and give them a better career. Key Words: Personalized Learning System, Natural Language Processing, Cosine Similarity, Adaptive Learning, Tag based Recommender System
1.INTRODUCTION In the digital education era, personalization and adaptive approaches are emerging to focus on individual learners' unique needs and preferences. Empowered by advancements in Natural Language Processing (NLP) and Machine Learning (ML) algorithms, personalized learning systems promise to revolutionize traditional education by providing tailored experiences that adapt to each learner's pace, interests, and styles. Leveraging learner and resource data, these systems deliver targeted recommendations, adaptive content delivery, and realtime feedback to enhance engagement, motivation, and learning outcomes.
1.1 Significance of Personalized Learning Traditional one-size-fits-all educational models often struggle to accommodate the diverse needs, backgrounds, and learning trajectories of individual learners. Personalized learning, on the other hand, 1 recognizes and
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 977