文件列表:

backend/
frontend/
package-lock.json

# Khabar Nama Project ## Overview The Khabar Nama project is an advanced Natural Language Processing (NLP) initiative designed to extract pertinent data from the DAWN news dataset. Leveraging TF-IDF and cosine similarity techniques from the sklearn library, the project aims to provide valuable insights and facilitate informed decision-making. ## Technologies Used - **Frontend:** React - **Backend:** Docker container - **NLP Techniques:** TF-IDF, Cosine Similarity - **Data Preprocessing:** Stemming, Lemmatization, Stop Word Removal ## Features 1. **Web Application:** Intuitive React-based interface for user interaction. 2. **Containerized Backend:** Docker deployment ensures seamless scalability and portability. ## Data Preprocessing The project employs various preprocessing techniques to enhance data quality: - **Stemming:** Reducing words to their base or root form for consistency. - **Lemmatization:** Further refining words to their base form. - **Stop Word Removal:** Eliminating common and non-informative terms for dataset refinement. ## How to Use 1. Clone the repository. 2. Set up the React frontend. 3. Deploy the Docker container for the backend. 4. Explore the extracted insights from the DAWN news dataset. ## Contributors - Saad Dastgir - Muhammad Umair khan - Ahsan Abbasi ## Acknowledgments - Special thanks to the sklearn library for providing robust NLP tools and enhancing the project's capabilities. - Thanks to Dr. Arif ur rehman(HOD CS Bahria University) for Supervising the Project.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：