Weekly readings are specified below. A “+” indicates additional readings will be made available via a link from this page. Lecture slides in PDF are obtained by clicking on the link to the topic.

Homeworks (prefixed with “HW”) are exercises that you should complete for the class following the one labeling the row in which they appear. In some cases we will begin the homework in class; therefore, it is imperative that you do the reading before the class where the homework is assigned. Homeworks will not be graded, but they must be handed in to GitHub classroom. The due date for each of the four large (graded) assignments (prefixed with “A”) will be specified in the assignment description.

Please note that this schedule is tentative and may change as the semester progresses. Please visit this page often!

Date Topic Reading Assignments Supplemental materials
1/22 Introduction (PPT) J&M Ch. 1
1/27 Morphology and general text processing (PPT) NLTK Ch. 1, J&M Ch. 3 pp. 45-68 HW: Ex. 2.2, J&M UNIX for Poets
1/29 Minimum Edit Distance (PPT) J&M Ch. 3.11 HW: J&M Ex. 3.10 and 3.11
2/3 Language models, probabilistic approaches, n-grams J&M Ch. 4 (through 4.5.2), NLTK Ch. 2
2/5 Ngram models, smoothing, discounting J&M Ch. 4.5-4.9, 4.12
2/10 Naive Bayes and Text Classification J&M (3ed) Chapter 4
2/12 Language models, probabilistic approaches, n-grams J&M Ch. 4 (through 4.5.2), NLTK Ch. 2 UNIX for Poets
2/17 Introduction to NLTK and Python (PPT) NLTK Ch. 3, 4, 5 Python3 tutorial
2/19 TBA

s366/private/lectures/sentiment-analysis.pdf|Sentiment Analysis]] | J&M ch. 6 (3rd ed.), J&M ch. 18 (3rd ed.) R1 | | |