DAN623 NLP-Text Analytics

[3–0, 3 cr.]

This course focuses on the computational aspect of Natural Language Processing (NLP) technologies and aims at finding a balance between traditional and modern NLP techniques. It covers major concepts and techniques for processing, cleaning, visualizing, and analyzing textual data to extract interesting information, discover knowledge, and support decision-making in business applications. Students will learn fundamental pre-processing techniques (i.e., tokenization, stemming, lemmatization, part-of-speech tagging, and named entity recognition), text representation (i.e., vector-space and language models, and modern distributed representation of words), and various text analytics tasks (i.e., text categorization and classification, document summarization, and sentiment analysis). Hands-on labs and projects in parallel to course lectures and readings will allow students to develop practical skills in building foundational NLP tools that can be applied to address real-world business analytics problems.