{"id":19914586,"url":"https://github.com/subratamondal1/emotionai","last_synced_at":"2025-03-01T09:19:08.650Z","repository":{"id":209508821,"uuid":"724254271","full_name":"subratamondal1/EmotionAI","owner":"subratamondal1","description":"Fine Tuning BERT on Emotion Dataset with Transformers","archived":false,"fork":false,"pushed_at":"2024-04-27T19:14:27.000Z","size":420,"stargazers_count":0,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-11T23:16:08.224Z","etag":null,"topics":["bert-fine-tuning","huggingface-transformers","supervised-machine-learning","text-classification"],"latest_commit_sha":null,"homepage":"https://subratamondal1-emotionai-emotionaiapp-7r6pf3.streamlit.app/","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/subratamondal1.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":"2023-11-27T17:53:42.000Z","updated_at":"2024-08-10T09:13:35.000Z","dependencies_parsed_at":"2023-11-29T19:27:51.261Z","dependency_job_id":"e3e93eef-b4d5-43ca-9ee4-95dc4c30b732","html_url":"https://github.com/subratamondal1/EmotionAI","commit_stats":null,"previous_names":["subratamondal1/emotionai"],"tags_count":0,"template":false,"template_full_name":"skills/copilot-codespaces-vscode","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/subratamondal1%2FEmotionAI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/subratamondal1%2FEmotionAI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/subratamondal1%2FEmotionAI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/subratamondal1%2FEmotionAI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/subratamondal1","download_url":"https://codeload.github.com/subratamondal1/EmotionAI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241342603,"owners_count":19947233,"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":["bert-fine-tuning","huggingface-transformers","supervised-machine-learning","text-classification"],"created_at":"2024-11-12T21:36:30.225Z","updated_at":"2025-03-01T09:19:08.629Z","avatar_url":"https://github.com/subratamondal1.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# \u003ch1 align=\"center\"\u003e\u003ca href=\"https://subratamondal1-emotionai-emotionaiapp-7r6pf3.streamlit.app/\" target=\"_blank\" rel=\"noopener noreferrer\" \u003eHuman Emotion Detector\u003c/a\u003e\u003c/h1\u003e\n\n\n## Overview\nEmotionAI is an interactive web application that utilizes a fine-tuned DistilBERT model to classify emotions from text. It is designed to provide real-time sentiment analysis to users by predicting emotions conveyed in the input text.\n\n## Installation\n\n### Prerequisites\n- Python 3.6 or higher\n- pip package manager\n\n### Setup\nTo set up the project locally, follow these steps:\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/subratamondal1/emotionai.git\n   ```\n2. Navigate to the project directory:\n   ```bash\n   cd emotionai\n   ```\n3. Install the required dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n## Usage\nTo run the EmotionAI application, execute the following command in the terminal:\n\n```bash\nstreamlit run app.py\n```\n\nThe web application will be hosted locally, and you can interact with it by entering text to analyze the emotions.\n\n## Machine Learning Model\nThe application uses a DistilBERT model that has been fine-tuned for emotion classification. The model is accessed via the Hugging Face Transformers library and is capable of classifying text into various emotion categories with high accuracy.\n\n## Technologies Used\n- Streamlit for web application development\n- Hugging Face Transformers for accessing pre-trained models\n- Pandas for data manipulation\n- Matplotlib for data visualization\n- GitHub Actions for CI/CD and automation\n\n## Challenges and Solutions\n\n### Challenge 1: Real-time Inference\nPerforming real-time inference with a deep learning model can be resource-intensive and slow.\n\n**Solution:**\nWe optimized the model inference by using a lightweight version of BERT, DistilBERT, which maintains high accuracy while being faster and smaller.\n\n### Challenge 2: User Experience\nCreating an intuitive user interface that allows for easy interaction with the machine learning model.\n\n**Solution:**\nStreamlit was used to build a user-friendly web interface that enables users to input text and view the emotion classification results in an understandable format.\n\n### Challenge 3: Automation of Workflows\nManaging and updating the application and its dependencies can be cumbersome.\n\n**Solution:**\nGitHub Actions was employed to automate workflows, including CI/CD pipelines, which facilitated consistent updates and maintenance of the codebase.\n\n## Contributing\nWe welcome contributions to the EmotionAI project. Please read `CONTRIBUTING.md` for details on our code of conduct, and the process for submitting pull requests to us.\n\n## License\nThis project is licensed under the MIT License - see the `LICENSE` file for details.\n\n## Acknowledgments\n- Hugging Face for providing the Transformers library and pre-trained models\n- Streamlit for their open-source framework for creating data applications\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsubratamondal1%2Femotionai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsubratamondal1%2Femotionai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsubratamondal1%2Femotionai/lists"}