Research_paper_recommendation_system_using_tf Idf_algorithm
Research Paper Recommendation System Using TF-IDF Algorithm
This is research paper recommendation system using TF-IDF(Term Frequency Inverse Document Frequency) algorithm with an easy-to-use UI.
Table of Contents
About the Project
This project is a Research Paper Recommendation System that utilizes the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm to recommend relevant research papers based on user input. Whether you provide a detailed description or just a keyword, the system identifies and suggests the most pertinent papers from a curated dataset. The dataset includes research papers in the field of Artificial Engineering published between the years 2010 and 2019.
Key Features
TF-IDF Algorithm
- Term Frequency (TF): Measures how frequently a term appears in a document. The frequency increases as the number of times a word appears in a document increases.
- Inverse Document Frequency (IDF): Assesses the importance of a term within the entire dataset. It helps reduce the weight of common terms that appear frequently across many documents.
- TF-IDF: By combining these two metrics, the system can evaluate the relevance of each document in relation to the user's query, prioritizing documents that contain important terms more frequently.
User Interface
- The system features an intuitive and user-friendly UI, making it accessible to users of all technical backgrounds. Users can input a description or keyword to search for relevant papers.
- The interface is built using HTML and styled with Tailwind CSS, providing a clean, responsive, and modern design that enhances user experience.
Dataset
- The recommendation system is powered by a comprehensive dataset of research papers in the artificial engineering domain, spanning the years 2010 to 2019. This dataset includes a wide array of topics and research areas, ensuring that users receive well-rounded and relevant recommendations.
Screenshots
Tech Stack
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contact
Karan Khatri - LinkedIn
Project Link: https://github.com/Karan6354/Research_paper_recommendation_system_using_TF-IDF_algorithm
Acknowledgements
I would like to thank the following resources that have made this project possible:
TailwindCSS: TailwindCSS made it easy to style and design our application with its utility-first CSS framework. Its responsive and customizable design components greatly improved our development workflow and the overall look and feel of the application.
Scikit-learn (sklearn): This powerful machine learning library provided essential tools for implementing and evaluating our models. Its extensive collection of algorithms and easy-to-use interface were instrumental in the project's data analysis and predictive modeling processes.
Pandas: Pandas was crucial for data manipulation and analysis. Its data structures and functions for working with structured data allowed us to efficiently clean, preprocess, and analyze large datasets.
Flask: This lightweight web framework was used to build the application's backend. Flask's simplicity and flexibility made it easy to create a robust and scalable server-side application, facilitating smooth integration with our front-end and machine learning models.
I am grateful for these tools and the developers behind them for their contributions to the open-source community. Their support and continuous development have significantly enhanced our project's success.
