COM 3930: Text Analysis and Natural Language Processing

Abstract

Description Vast amounts of information is created in the form of unstructured data – web pages, social media posts, emails, presentations, analysts’ reports, news content, etc. The ability to extract useful information from such data sources is a critical tool in the toolbox of a data scientist. This course examines computational methods for analyzing human language textual data in order to detect meaning and extract information. Applications of these methods include sentiment analysis, information retrieval, and trend prediction. Course Outcomes  Students will be able to articulate the fundamentals of natural language processing  Students will be able to competently use several major software packages for NLP  Students will be able to apply machine learning for text analysis  Students will be able to implement Information Retrieval Algorithms  Students will be able to implement and use Word Embedding algorithms such as Word2Vec Major Topics Covered in Course  What is natural language processing and the challenge of doing it computationally  Major tasks that NLP undertakes  Uses and limitations of n-gram analysis  Using NLP and syntactical analysis for text mining  Understanding and implementing search engines  Using and implementing modern word embedding techniques such as Word2Vec