{"id":22656525,"url":"https://github.com/goldsharon/sentimaster","last_synced_at":"2026-04-05T23:34:49.550Z","repository":{"id":266717669,"uuid":"899073986","full_name":"GoldSharon/Sentimaster","owner":"GoldSharon","description":"Sentimaster is an AI-powered web tool that analyzes restaurant reviews. It uses a fine-tuned GPT-2 model to classify sentiment, giving businesses real-time insights for better service and decision-making.","archived":false,"fork":false,"pushed_at":"2024-12-05T17:54:30.000Z","size":221,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-29T07:44:57.843Z","etag":null,"topics":["ai","aws","customerfeedback","deeplearning","flask","gpt2","machinelearning","modeldeployment","naturallanguageprocessing","nlp","pytorch","sentimentanalysis","webapplication"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GoldSharon.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-12-05T15:17:50.000Z","updated_at":"2024-12-05T17:58:14.000Z","dependencies_parsed_at":null,"dependency_job_id":"12811c83-ea41-4b83-bb9e-7fe834f158d8","html_url":"https://github.com/GoldSharon/Sentimaster","commit_stats":null,"previous_names":["goldsharon/sentimaster"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoldSharon%2FSentimaster","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoldSharon%2FSentimaster/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoldSharon%2FSentimaster/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GoldSharon%2FSentimaster/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GoldSharon","download_url":"https://codeload.github.com/GoldSharon/Sentimaster/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246156029,"owners_count":20732359,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","aws","customerfeedback","deeplearning","flask","gpt2","machinelearning","modeldeployment","naturallanguageprocessing","nlp","pytorch","sentimentanalysis","webapplication"],"created_at":"2024-12-09T10:14:44.994Z","updated_at":"2025-12-30T23:18:33.676Z","avatar_url":"https://github.com/GoldSharon.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# **Sentimaster: Sentiment Analysis Tool**\n\nSentimaster is a web-based sentiment analysis tool developed to analyze restaurant reviews using AI-powered sentiment classification. Built using a fine-tuned GPT-2 model, Sentimaster empowers businesses with real-time actionable insights from customer feedback to improve customer service and decision-making.\n\n---\n\n## **Tech Stack**\n\n- **GPT-2** (124M parameters) for sentiment analysis model  \n- **Flask** for backend web framework  \n- **AWS EC2** for deployment  \n- **HTML**, **CSS**, **JavaScript** for frontend development  \n- **PyTorch** for model training and inference  \n- **Tiktoken** for tokenization  \n\n---\n\n## **Features**\n\n- **Sentiment Analysis**: Classifies restaurant reviews as either \"Positive\" or \"Negative\".  \n- **Real-Time Feedback**: Users can submit reviews through the web interface and receive real-time sentiment analysis.  \n- **Model**: Fine-tuned GPT-2 (124M parameters) on restaurant-specific data for improved accuracy.  \n- **Deployment**: Deployed using Flask, accessible via a web browser.  \n\n---\n\n## **Installation**\n\n1. Clone this repository to your local machine:  \n   ```bash\n   git clone https://github.com/GoldSharon/Sentimaster.git\n   ```\n\n2. Navigate to the project directory:  \n   ```bash\n   cd Sentimaster\n   ```\n\n3. Install the required dependencies:  \n   ```bash\n   pip install -r requirements.txt\n   ```\n\n4. Ensure that you have the pretrained model weights (`model_and_optimizer.pth`) placed in the project directory.  \n   - If the model weights are not available, follow the training guidelines provided in the documentation or scripts to train the model.  \n\n---\n\n## **Usage**\n\n1. Run the Flask app:  \n   ```bash\n   python app.py\n   ```\n\n2. The application will be available at:  \n   [http://127.0.0.1:5000/](http://127.0.0.1:5000/)  \n\n3. Open your browser and go to the URL. Enter a restaurant review in the text field, and the model will classify the sentiment as \"Positive\" or \"Negative\".  \n\n---\n\n## **Model Architecture**\n\n- **GPT-2 (124M parameters)** is used for sentiment analysis, fine-tuned on restaurant-related reviews to improve domain-specific accuracy.  \n- **Architecture Details**:  \n  - 12 layers, 768 embedding dimensions, and 12 attention heads.  \n  - Trained and optimized using the Adam optimizer with a learning rate of 0.0004.  \n\n---\n\n## **API Endpoints**\n\n- `/`: Home route, renders the input form for the review.  \n- `/submit`: POST method, accepts the review and returns sentiment classification.  \n- `/result`: Displays the result of the sentiment analysis.  \n\n---\n\n## **Example Workflow**\n\n1. The user submits a restaurant review via the form.  \n2. The model classifies the sentiment of the review (Positive/Negative).  \n3. The result is displayed on a new page, showing whether the review is positive or negative.  \n\n---\n\n## **Impact**\n\nBy using Sentimaster, businesses can:  \n- Gain insights from customer feedback.  \n- Improve customer service and satisfaction.  \n- Make data-driven decisions for business growth and improvement.  \n\n---\n\n## **Contributions**\n\nFeel free to fork the repository, create issues, and submit pull requests. Contributions are always welcome!  \n\n---\n\n## **License**\n\nThis project is licensed under the **MIT License**.  \n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoldsharon%2Fsentimaster","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgoldsharon%2Fsentimaster","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoldsharon%2Fsentimaster/lists"}