AI-Driven Text Analytics. 3 credits, 3 contact hours

Catalog description

Prerequisites: CS 100 or DS 100 , and IS 331 or CS 331 or MIS 385 . The Web and other unstructured/semi-structured, hyper-textual, distributed information repositories all have their unique characteristics and require different techniques to better understand them. AI-driven text analytics aims at discovering useful information and knowledge from various types of unstructured textual elements using machine learning, data mining, and artificial intelligence approaches. The outcomes can be used for site management, personalization, customer sentiment analysis, and beyond. Topics covered in this course include crawling, indexing, ranking and filtering algorithms using text and link analysis, applications to search, classification, tracking, monitoring, and Web intelligence. Natural language processing techniques for storage, classification, and topic modeling will demonstrate applications for unstructured data. Most recent developments in Large Language Models (LLMs) and prompt engineering will be discussed as well. Programming assignments give hands-on experience. A group project highlights class topics.