Online Personalized learning remediation/tutoring tool

  • Unique Paper ID: 178405
  • Volume: 11
  • Issue: 12
  • PageNo: 4761-4765
  • Abstract:
  • With the given project, we set out to explore the use of Generative AI coupled with the Retrieval-Augmented Generation system-end methodologies for optimizing teaching pedagogy. Using the system, it ingests educational data with embeddings created by Sentence Transformers, indexed, and queried through Pinecone to obtain relevant or pedagogical insights. Integrating the Groq API ensures that teaching strategies are tailored concerning context such as students' average marks and feedback. One of the issues discussed is embedding-based retrieval systems and vector similarity, as well as the role of generative models in producing usable teaching suggestions. This is a major step in the direction of AI-driven personalized education. The Pedagogy Suggestion System is touted as an AI-powered teaching assistant that helps educators become better teachers. It takes in structured datasets that contain information on courses, teaching techniques, student feedback, and performance metrics. Based on its analysis of the datasets, it detects the most appropriate teaching methods to recommend for a given course. In contrast, the Andragogy Suggestion System is geared toward adult learners, who commonly seek to advance their career, learn some new skills, or work toward personal development. The system generates tailored learning plans that fit an individual’s unique learning style, strengths, and weaknesses, along with their goals.

Copyright & License

Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{178405,
        author = {PAWAN KUMAR D and NIHAL GAGAN and SAI ABHISHEK and S PUNITH KUMAR and DARSHAN NAIK and S SARAVAN KUMAR},
        title = {Online Personalized learning remediation/tutoring tool},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4761-4765},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178405},
        abstract = {With the given project, we set out to explore the use of Generative AI coupled with the Retrieval-Augmented Generation system-end methodologies for optimizing teaching pedagogy. Using the system, it ingests educational data with embeddings created by Sentence Transformers, indexed, and queried through Pinecone to obtain relevant or pedagogical insights. Integrating the Groq API ensures that teaching strategies are tailored concerning context such as students' average marks and feedback. One of the issues discussed is embedding-based retrieval systems and vector similarity, as well as the role of generative models in producing usable teaching suggestions.
This is a major step in the direction of AI-driven personalized education. The Pedagogy Suggestion System is touted as an AI-powered teaching assistant that helps educators become better teachers. It takes in structured datasets that contain information on courses, teaching techniques, student feedback, and performance metrics. Based on its analysis of the datasets, it detects the most appropriate teaching methods to recommend for a given course. In contrast, the Andragogy Suggestion System is geared toward adult learners, who commonly seek to advance their career, learn some new skills, or work toward personal development. The system generates tailored learning plans that fit an individual’s unique learning style, strengths, and weaknesses, along with their goals.},
        keywords = {Generative AI (Gen AI), Retrieval-Augmented Generation (RAG), Sentence Transformers, Pinecone, Embedding-based Retrieval, Education, Vector Databases, Data-Driven Teaching Strategies.},
        month = {May},
        }

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 12
  • PageNo: 4761-4765

Online Personalized learning remediation/tutoring tool

Related Articles