A Comprehensive Study on the Real-Time Text Categorization of User Generated Content using Artificial Intelligence

With the rapid increase in social media usage, there has been a corresponding surge in user-generated content (UGC) being generated on a daily basis. This has created a demand for efficient and effective real-time text classification of UGC to monitor and extract valuable insights for businesses and organizations. Our goal in doing this systematic review was to compile all of the most up-to-date information on the best practices for user-generated content (UGC) text categorization in real-time on social media. Various sources, such as academic databases, digital libraries, and online periodicals, are combed through to find relevant material for the review. The focus is primarily on recent research conducted between 2015 and 2023, with an emphasis on identifying emerging trends, challenges, and opportunities in the field. The review critically examines the different approaches employed for text classification, encompassing machine learning, deep learning, and natural language processing techniques. Furthermore, it explores the specific social media platforms where text classification is carried out, such as Twitter, Facebook, and Instagram. The review highlights the key challenges associated with real-time text classification of UGC, such as handling large data volumes, dealing with language ambiguity, and the need for continuous training and updates. Additionally, the study underscores the potential opportunities for future research in this domain, such as the development of hybrid models that combine multiple approaches to enhance accuracy and scalability. The insights gained from this systematic review will be valuable for researchers, practitioners, and businesses engaged in real-time text classification of UGC on social media platforms.