{"id":19972546,"url":"https://github.com/rajveersinghcse/email-classification","last_synced_at":"2026-06-09T03:04:56.109Z","repository":{"id":195665788,"uuid":"685827130","full_name":"rajveersinghcse/Email-Classification","owner":"rajveersinghcse","description":"📧Email classification using a Machine Learning Models. It categorizes emails as either \"ABUSIVE\" or \"NON ABUSIVE\" based on their content, allowing users to quickly assess the nature of the email messages they input.","archived":false,"fork":false,"pushed_at":"2024-03-24T05:58:22.000Z","size":37923,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-01T18:25:35.474Z","etag":null,"topics":["email","email-classification","internship","project"],"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/rajveersinghcse.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":"2023-09-01T05:23:49.000Z","updated_at":"2024-09-20T05:18:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"4f0fba36-9e7d-443e-a805-9713c9d14c43","html_url":"https://github.com/rajveersinghcse/Email-Classification","commit_stats":null,"previous_names":["rajveersinghcse/email-classification"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rajveersinghcse/Email-Classification","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajveersinghcse%2FEmail-Classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajveersinghcse%2FEmail-Classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajveersinghcse%2FEmail-Classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajveersinghcse%2FEmail-Classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rajveersinghcse","download_url":"https://codeload.github.com/rajveersinghcse/Email-Classification/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rajveersinghcse%2FEmail-Classification/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34089355,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-09T02:00:06.510Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["email","email-classification","internship","project"],"created_at":"2024-11-13T03:08:30.841Z","updated_at":"2026-06-09T03:04:56.092Z","avatar_url":"https://github.com/rajveersinghcse.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"---\n\n# Email Classification for Abusive Content Detection\n\nThis project focuses on building a classification model to distinguish between abusive and non-abusive emails. With the increasing prevalence of online harassment and offensive communication, automated systems for identifying abusive content have become essential.\n\n## Table of Contents\n\n- [Introduction](#introduction)\n- [Dataset](#dataset)\n- [Approach](#approach)\n- [Dependencies](#dependencies)\n- [Results](#results)\n- [Contributing](#contributing)\n- [License](#license)\n\n## Introduction\n\nThis project aims to develop a machine-learning model that accurately categorizes emails into abusive and non-abusive categories. This can be particularly useful for email providers, social media platforms, and other online communication platforms to filter out harmful content and ensure a safer environment for their users.\n\n## Dataset\n\nThe dataset used for training and evaluation comprises a diverse collection of emails labeled as abusive or non-abusive. The dataset has been preprocessed to remove personally identifiable information and sensitive content.\n\n## Approach\n\nThe classification model is built using natural language processing (NLP) techniques and machine learning algorithms. The process involves:\n\n1. **Data Preprocessing**: Cleaning and tokenizing the text data, removing stopwords, and performing other necessary preprocessing steps.\n2. **Feature Engineering**: Extracting relevant features from the text data, such as TF-IDF vectors or word embeddings.\n3. **Model Selection**: Evaluating various classification algorithms such as Naive Bayes, SVM, and neural networks to determine the most effective approach.\n4. **Training and Evaluation**: Training the selected model on the labeled dataset and evaluating its performance using metrics such as accuracy, precision, recall, and F1-score.\n5. **Deployment**: Integrating the trained model into an application or service for real-time classification of incoming emails.\n\n## Dependencies\n\n- Python 3.x\n- scikit-learn\n- NLTK\n- Pandas\n- NumPy\n\n## Results\n\nThe performance of the model on the test dataset is as follows:\n\n- Passive Aggressive Classifier---------\u003e99.56%\n- Naive Bayes---------------------------\u003e97.10%\n- TFIDF----------------------------------\u003e99.61%\n- TFIDF: Bigrams------------------------\u003e99.71%\n- TFIDF: Trigrams------------------------\u003e99.71%\n\n## Contributing\n\nContributions to this project are welcome. If you have any suggestions for improvements or would like to report issues, please submit a pull request or open an issue on GitHub.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frajveersinghcse%2Femail-classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frajveersinghcse%2Femail-classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frajveersinghcse%2Femail-classification/lists"}