Syllabus
Course Description
IPHS 290 Cultural Analytics
Integrated Program for Humane Studies
Office Hours
Professor Elkins
TueThur 1-2pm, Fri 1:10-2:10
or appointment at elkinsk@kenyon.edu
Professor Chun
MWF 1:10-2:10
or appointment at chunj@kenyon.edu
Calendar
| Week | Date | Topic | Motivating Example | Technical Background | Coding Assignment |
|---|---|---|---|---|---|
| 1 | 29 Aug (Mon) | Mapping | Redlining, Detention Centers, Dispossession & the Homestead Act | GeoPy and GeoPandas | DataCamp Working w/Geospatial Data in Python |
| 2 | 5 Sep (Mon) | MINI-PROJECT #1 | Geospatial Mapping | GeoPy and GeoPandas | Kaggle GeoSpatial Analysis |
| 3 | 12 Sep (Mon) | Web Scraping | Scrape Example | HTML, XPaths, CSS, Spiders | DataCamp Web Scraping in Python |
| 4 | 12 Sep (Mon) | APIs | API and Bots | Twitter API, REST, JSON | DataCamp Analyzing Social Media in Python |
| 5 | 26 Sep (Mon) | Introduction to NLP | RegEx, TF-IDF, NER, Polyglot | NLTK, SpaCy, Gensim | DataCamp Introduction to NLP in Python |
| 6 | 7 Nov (Mon) | Social Networks | GoT and Twitter Examples | GraphX and Twitter | DataCamp Introduction to Network Analysis in Python |
| 7 | x Nov (Mon) | MINI-PROJECT #2 | Social Networks | NetworkX | TBA |
| 8 | 3 Oct (Mon) | Sentiment Analysis | Parsing and Linguistic Example | NLTK & SpaCy | DataCamp Sentiment Analysis in Python |
| 9 | 10 Oct (Mon) | Advanced NLP | Vectorization, Pipelines, DNN | SpaCy | DataCamp Advanced NLP with SpaCy |
| 10 | 17 Oct (Mon) | Topic Modeling | Topic Modeling Example | Gensim | Gensim 4 Core Tutorials |
| 11 | 31 Oct (Mon) | Diachronic Sentiment Analysis | SentimentArcs Cambridge & Time Series Processing | SentimentArcs Paper/Chapter | DataCamp Manipulating Time Series Data in Python |
| 12 | 7 Nov (Mon) | MINI-PROJECT #3 | Diachronic Sentiment Analysis | SentimentArcs | TBA |
| 13 | 14 Nov (Mon) | Web Servers | Museum Curation | GitHub.io and mkdocs | Github Pages Mkdocs |
| 14 | 28 Nov (Mon) | Final Project | Work in-class on project | Digital Kenyon | Lab all week |
Course Description
Cultural analytics is the study of society and social phenomena by analyzing data and the way it flows. This involves gathering, transforming, visualizing and narrativizing data in various forms including numeric, textual, geospatial, and as time series.
This course presumes some coding experience or the introductory course to Digital Humanities, IPHS200 Programming Humanity. We start with geospatial data and mapping. Next, we’ll build on our skills using web scrapers and API’s to create original datasets from social media sites like Twitter. Then we’ll learn various natural language processing techniques underlying sentiment analysis and topic clustering to explore text for insights. Finally, we'll learn how to graph and explore the relations between data in the form of social networks.
This is a methods class focused on learning both the conceptual and practical applications of maps, texts, and networks. A carefully curated sequence of key abstract concepts explored through the most popular and useful libraries will mark our progression through the semester. We'll also read some of the best examples of work in the field and use these to inspire our own experiments.
We’ll do some hands-on projects on DataCamp like analyzing the social network of Game of Thrones and exploring the shifting topics/sentiment of Trump/Trudeau on social media. But we'll also have three project weeks during which we'll break into groups and move through the entire process, from brainstorming ideas to visualizing and analyzing the results. In the final segment of the course, we'll learn how to showcase projects on individual Github sites and work on final projects centered on individual interests.
By the end of this course you will:
- Deepen your proficiency in Python, data visualization, and data wrangling
- Learn how to automate dataset creation via web scraping and programmic APIs
- Learn the fundamentals of geospatial analytics
- Learn core Natural Language Processing techniques including scraping, cleaning, representing, transforming and analyzing text
- Learn the fundamentals time series analysis
- Learn basic graph theory, algorithms, metrics and visualizations
- Present your code on Github and project on a personal website
- Learn how to identify interesting multi-disciplinary research questions and judiciously use a wide range of computational technologies to analyze, critique and productively address such questions
Grading
-
25% DataCamp
-
15% Reading/Concept Quizzes
-
40% 3 Mini-projects
-
20% Final Project
There is no final exam
Attendance
In accordance with standard Kenyon policy, absences greater than 25% of the class will result in a failing grade. You are allowed three absences, no questions asked, before your attendance grade drops.
These absences count as combination sick/personal days, i.e. please do not take 3 personal days and then ask for additional sick days. In cases of extreme illness or other unforeseen events, please ensure the advising office is aware and that you’ve been granted an excused absence. We will be notified accordingly.
Quizzes
Short quizzes will test comprehension of key terms and information. Quizzes cannot be made up if you miss class. 3 quizzes will be dropped to accomodate 3 absences. Then the 3 lowest grades will be dropped.
Datacamp Assignments and Mini-Projects
You will receive a free Datacamp account with assignments due for each class session. Assignments are graded solely on completion, but you must complete them fully (i.e. no 0’s). Please make sure the checkmarks are there on each section on the outline of the course.
Final Project
For the final project, you may a) complete a data analysis or cultural analytics project working with numeric or linguistic data or b) create an in-depth analysis of a particular technology. b) should demonstrate understanding of both the technology and the ethical/social issues surrounding that technology.
Final Thoughts on Grades
This class is meant to be a fun and exploratory introduction. Students will bring different strengths and backgrounds to this interdisciplinary class, and the emphasis will be on developing these personal interests and competencies. If you do the work, you will do well.
Responsible Employee Information
We will be studying and/or discussing a number of issues that may cause discomfort or distress. If you wish to speak with either of us about any readings, assignments or class discussions, please understand that we may be required to report information about sexual misconduct to the Title IX Coordinator. For confidential support, you may contact the following resources: The Health and Counseling Center, Sexual Misconduct Advisors (SMAs) the College chaplains, and staff at New Directions Domestic Abuse Shelter & Rape Crisis Center
Statement of Academic Integrity and Disability Accommodations
At Kenyon we expect all students, at all times, to submit work that represents the highest standards of academic integrity. It is the responsibility of each student to learn and practice the proper ways of documenting and acknowledging those whose ideas and words they have drawn upon (see Academic Honesty and Questions of Plagiarism in the Course Catalog). Ignorance and carelessness are not excuses for academic dishonesty. If you are uncertain about the expectations for this class, please ask for clarification. Students with disabilities who will be taking this course and may need academic accommodations are encouraged to make an appointment to see me as soon as possible. Also, you are required to register for support services with the Office of Disability Services in the Olin Library, Center for Innovative Pedagogy.