Only1EmriQ/African-Plagiarism-Checker

This project is a web-based plagiarism detection system designed to address the specific needs of African universities. It focuses on semantic similarity analysis against a specialized database of African academic journals and research papers. # African-Plagiarism-Checker Dual Input Method: Support for PDF/DOCX file uploads and raw text pasting (up to 10,000 characters). Semantic Analysis: Uses Natural Language Processing (NLP) to detect paraphrased content, not just exact word matches. Context-Aware Results: Highlights flagged sentences and provides direct clickable links to the original academic sources. Modern UI: A responsive, university-grade dashboard featuring a circular similarity gauge and detailed match reports. 🛠️ Technical Stack: Frontend: Next.js 14, TypeScript, Tailwind CSS, Lucide Icons. Backend: Python 3.10+, FastAPI, Uvicorn. NLP Engine: Sentence-Transformers (BERT-based models), PyPDF for text extraction. Architecture: Three-Tier Client-Server Architecture. 📥 Installation & Setup 1. Clone the Repository Bash git clone github.com cd African-Plagiarism-Checker 2. Backend Setup (FastAPI) Bash cd backend python -m venv venv # Activate venv: Windows: venv\Scripts\activate | Mac/Linux: source venv/bin/activate pip install -r requirements.txt python -m uvicorn main:app --reload The backend will be available at localhost 3. Frontend Setup (Next.js) Bash cd frontend npm install npm run dev The frontend will be available at localhost 📜 Academic Reference: This project was developed as part of an undergraduate dissertation in the Department of Computer Science, University of Calabar (UNICAL). It follows the official reporting template for undergraduate research. 📄 License: This project is for academic purposes. Refer to university guidelines for reuse and distribution.