Refer to Discussion Forum, Facilitator Introduction and Expectations
MSDS 682 - Text Analytics
Investigates linguistic, statistical, and machine learning techniques for modeling the information in textual sources. Includes information retrieval, natural language processing, text classification, and sentiment analysis and the software systems for performing these analyses.
MSDS 650 Data Analytics
In this course, you will learn the fundamental concepts of text analytics and perform text analytics on different applications.
Key concepts to be covered in this course include:
Upon completion of this course, learners should be able to:
Manning, C. D., Raghavan, P., and Schutze, H. 2008. Introduction to Information Retrieval. Cambridge University Press, 2008. Retrieved from: http://www-nlp.stanford.edu/IRbook/.
Miner, G., Delen, D., Elder, J., Fast, A., Hill, T., and Nisbet, A. R. (2012).Practical Text Mining and Statistical Analysis for Non-structured Text Data Applications. Elsevier Inc. Available online http://www.gbv.de/dms/ilmenau/toc/668584769.PDF.
Bird, S., Klein, E., & Loper, E. (2009). Natural Language Processing with Python. O’Reilly Media, Inc.
None
None
The NLTK book: http://www.nltk.org/book/
Munzert, S., Rubba, C., Meißner, P., and Nyhuist, D. (2015). Automated Data Collection with R: A practical guide to web scraping and text mining. John Wiley & Sons. (E-book). Retrieved from http://kek.ksu.ru/eos/WM/AutDataCollectR.pdf.
Data Camp: Text Mining: Bag of Words (video). Retrieved from https://www.datacamp.com/courses/intro-to-text-mining-bag-of-words.
The following e-books are available to you for free through the Regis Library collections. Go to http://libguides.regis.edu/az.php?a=s and select Safari Books Online. You will be required to log in using your Regis credentials. NOTE: Limited to 3 concurrent users. Please logout when you are through.
Kumar, A., and Paul, A. (2016). Mastering Text Mining with R. Packt Publishing. (E-book).
Ravindran, S. K., and Garg, V. (2015). Mastering Social Media Mining with R. Packt Publishing (E-book).
Classroom-based and Online Formats: Sign on to WorldClass (D2L) and become familiar with the course navigation. See Course Assignments and Activities table below.
Classroom-based Format: This assignment is due the first night of class.
Online Format: The instructor will specify the due date for this assignment.
| Week | Readings | Graded Assignments or Assessments (Percentage) |
|---|---|---|
| 1: Text Analytics |
From the Expert Reading List for week 1 |
Introductions Discussion Questions/threads (1.5%) Exercise (8%) |
| 2: Informational Retrieval |
From the Expert Reading List for week 2 |
Discussion Questions/threads (1.5%) Exercise (8%) |
| 3: Natural Language Processing (NLP) |
From the Expert Reading List for week 3 |
Discussion Questions/threads (1.5%) Project (12%) |
| 4: Text Categorization |
From the Expert Reading List for week 4 |
Discussion Questions/threads (1.5%) Project (12%) |
| 5: Text Clustering |
From the Expert Reading List for week 5 |
Discussion Questions/threads (1.5%) Project (12%) |
| 6: Social media |
From the Expert Reading List for week 6 |
Discussion Questions/threads (1.5%) Project (12%) |
| 7: Sentiment Analysis |
From the Expert Reading List for week 7 |
Discussion Questions/threads (1.5%) Project (12%) |
| 8: Other applications – health care |
From the Expert Reading List for week 8 |
Discussion Questions/threads (1.5%) Project (12%) |
| TOTAL: 100% |
| Assignments | Weighted Percentage |
|---|---|
| Discussion Questions (8 at 1.5% each) | 12% |
| Assignments (8 at 11% each) | 88% |
| TOTAL | 100 % |
Review the Regis University Policies on the Regis University website.
Students taking in-person courses are expected to attend all classes for a course during the term. Missing classes may result in a failing grade or substantial grade penalties, at the discretion of the course instructor. Class absences should be discussed in advance with the course instructor.
NOTE TO LEARNERS: On occasion, the course facilitator may, at his or her discretion, alter the Learning Activities shown in this Syllabus. The alteration of Learning Activities may not, in any way, change the Learner Outcomes or the grading scale for this course as contained in this syllabus. Examples of circumstances that could justify alterations in Learning Activities could include number of learners in the course; compelling current events; special facilitator experience or expertise; or unanticipated disruptions to class session schedule.