Looking for challenging opportunities in Data Science, Big Data Analytics, and DevOps to apply expertise in driving data-driven insights and optimizing infrastructure efficiency.
This project aims to develop a hate speech detection system for Twitter by leveraging Graph Convolutional Networks (GCNs) to classify users based on their engagement in hateful behavior. Through data collection, graph construction representing user interactions, and the implementation of GCN models, the system will accurately classify users into categories such as hate speech users, non-hateful users, and neutral users. The ultimate goal is to create a scalable and effective solution that can assist in content moderation efforts, promote user awareness, and facilitate safer online spaces.
Led a project employing NLP and machine learning techniques to automate forum post categorization based on titles. Developed an intelligent system using Python, Selenium, and LSTM models, enhancing content organization and user experience in online forums. Incorporated a robust MLOps training pipeline, ensuring continuous integration and delivery (CI/CD), and played a key role in the development and maintenance of the model deployment pipeline, facilitating seamless model updates and scalability.