CoLab: BusinessAnalytics NLP

Level: Undergraduate

Business Analytics, NLP, and Textual Data. Companies and many federal agencies have collected a significant amount of unstructured data (documents, images, etc) and they need to digitize all of it to be able to use it and connect it datasets within their environment. This co-lab will provide a foundation in Natural Language Processing (NLP) techniques to analyze and extract text from a variety of documents to address practical business and organizational problems. There will be four 90-minute sessions to learn (one per week), time in between for teams to create using what they learn, and a fifth 90-minute session for teams to share what they create with a "Shark Tank"-like panel. Day 1: Text Summarization techniques – create small abstracts for each document in the corpus Day 2: Sentiment Analysis - Identify opinions/emotions on sentences/documents/tweets Day 3: Skill extraction - extract skills with years of experience from corpus of resumes Day 4: Use AWS Textract to extract useful documents form PDFs Corporate Partners: Damon Griggs, CEO of Dovel Technologies and Georgetown MBA alumnus; and Rod Fontecilla, Ph.D. | SVP, Chief Innovation Officer, and Chief Data Scientist, Dovel Technologies. Dovel is a 2000+ employee firm headquartered in Northern Virginia and serving a variety of public and private clients, especially in health IT and life sciences. Their work involves advanced data analytics and AI. Faculty Partner: Prof. Jason Schloetzer, McDonough School of Business