{"id":22665499,"url":"https://github.com/edochiari/tiktok-project","last_synced_at":"2025-03-29T09:42:57.078Z","repository":{"id":261682462,"uuid":"885034078","full_name":"EdoChiari/TikTok-Project","owner":"EdoChiari","description":"This project builds a predictive model to help TikTok classify user-reported content claims, improving moderation efficiency by identifying and prioritizing content that may need review. Insights from this model enable TikTok to manage reports more effectively, ensuring a safer and more engaging platform.","archived":false,"fork":false,"pushed_at":"2024-11-08T10:30:31.000Z","size":1560,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-04T00:52:14.880Z","etag":null,"topics":["content-claims","dataanalysis","datacleaning","hypothesis-testing","jupyter-notebook","regression","tiktok"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EdoChiari.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-11-07T20:46:34.000Z","updated_at":"2024-11-08T10:35:56.000Z","dependencies_parsed_at":"2024-11-07T21:37:32.289Z","dependency_job_id":"2258ee46-a132-440d-bd13-50694f612586","html_url":"https://github.com/EdoChiari/TikTok-Project","commit_stats":null,"previous_names":["edochiari/tiktok-project"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdoChiari%2FTikTok-Project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdoChiari%2FTikTok-Project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdoChiari%2FTikTok-Project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EdoChiari%2FTikTok-Project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EdoChiari","download_url":"https://codeload.github.com/EdoChiari/TikTok-Project/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246168086,"owners_count":20734389,"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":["content-claims","dataanalysis","datacleaning","hypothesis-testing","jupyter-notebook","regression","tiktok"],"created_at":"2024-12-09T13:31:49.926Z","updated_at":"2025-03-29T09:42:57.044Z","avatar_url":"https://github.com/EdoChiari.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TikTok Claims Classification Project\n\n## Overview\nThis project focuses on developing a predictive model to support TikTok’s moderation team by classifying user-submitted content claims efficiently. By analyzing user reports on videos and comments, the project aims to build a model that distinguishes between content with user claims versus opinions. This approach will help TikTok reduce the backlog of reports, prioritize moderation efforts, and maintain a safe and engaging community.\n\n## Project Goals\n1. **Classify Content Claims**: Build and evaluate a model to predict whether a video contains a claim or an opinion, enabling TikTok to streamline content moderation.\n2. **Enhance Moderation Efficiency**: Provide a scalable solution for handling high volumes of user reports, improving the speed and accuracy of content review processes.\n3. **Deliver Insights for Stakeholders**: Generate actionable insights from user reports to aid TikTok leadership in understanding content trends and moderation needs.\n\n## Deliverables\nThe final project deliverables include:\n\n- **Model Evaluation**: Comprehensive assessment of the classification model, including accuracy, precision, and recall, to gauge its effectiveness in content claim prediction.\n- **Data Visualizations**: Interactive Tableau dashboards summarizing user report trends, claim types, and other key insights, accessible to non-technical stakeholders.\n- **Feature Analysis**: Examination of features that contribute most to accurate claim classification, with discussions on potential causative relationships.\n- **Future Model Improvements**: Recommendations for additional features and data sources that may enhance the accuracy and relevance of the model.\n\n## Tools and Libraries Used\n- **Data Analysis and Visualization**: Pandas, NumPy, Matplotlib, Seaborn, Tableau\n- **Machine Learning**: Scikit-learn (for regression and classification models)\n- **Notebook Environment**: Jupyter Notebook\n\n## Project Structure\nThe project is organized as follows:\n\n1. **Data Preparation**: Building and organizing a comprehensive dataset from user reports for claims classification, ensuring data quality and suitability for analysis.\n2. **Exploratory Data Analysis (EDA)**: Analyzing user reports to identify claim patterns, trends, and factors that may impact claim classification.\n3. **Hypothesis Testing**: Conducting hypothesis tests to determine the significance of various factors within user reports, informing model feature selection.\n4. **Model Building and Evaluation**: Developing and testing a regression model to classify content claims, followed by evaluation using key performance metrics.\n5. **Executive Summary**: A presentation-ready summary for stakeholders, highlighting findings, model performance, and potential impact on moderation efforts.\n\n## Conclusion\nThis project offers TikTok a data-driven approach to improve content moderation by predicting user claims more effectively. With a model that enhances the prioritization of user reports, TikTok can maintain a safe, enjoyable platform while efficiently managing moderation resources.\n\n## Badges\n\nAdd badges from somewhere like: [shields.io](https://shields.io/)\n\n[![MIT License](https://img.shields.io/badge/License-MIT-green.svg)](https://choosealicense.com/licenses/mit/)\n[![GPLv3 License](https://img.shields.io/badge/License-GPL%20v3-yellow.svg)](https://opensource.org/licenses/)\n[![AGPL License](https://img.shields.io/badge/license-AGPL-blue.svg)](http://www.gnu.org/licenses/agpl-3.0)\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedochiari%2Ftiktok-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fedochiari%2Ftiktok-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedochiari%2Ftiktok-project/lists"}