Text Analytics

0.5 Course Units

This course introduces modern text analytics, and the tools of natural language processing. Text and language are powerful repositories of knowledge and information, but the semi-structured nature of language makes deriving insights from text challenging. Modern analytic techniques introduced in this course make it significantly easier even for non-specialists to use text and language data to drive deep insights. The course will use several examples from real world applications in different industries such as ecommerce, healthcare and finance to illustrate these techniques. Students should be familiar with regression models at the level of Stat 6130 or Stat 1020, and the Python language at the level of Stat 4770 or Stat 7770. Familiarity with the Jupyter notebook development environment is presumed, as well as common Python packages such as pandas, NLTK and SpaCy. Those with more knowledge of Statistics, such as from Stat 7220/4220, or computing skills will benefit. The predominant software used in the course is Jupyter notebooks that use a Python interpreter. Familiarity with basic probability models is helpful but not presumed. Fall or Spring Mutually Exclusive: STAT 7240 0.5 Course Units