Top

Language, Power, and Computation: Computational Text Analysis

David P. Feldman

Palak Taneja

College of the Atlantic, Spring 2025

Basic Info

Computational text analysis (CTA) is an emerging field that uses computation to analyze texts. CTA draws on the fields of computer science, machine learning, computational linguistics, and literary theory. Using machine learning and statistics, computers can be used to explore how language is used in particular contexts, including how frequently different words are used, the sentiment of a word/text, as well as nuances in the ways words are associated with one another. We will use CTA to engage in "Distant Reading", a term coined by literary theorist Franco Moretti. Distant Reading stands in contrast to the more familiar "Close Reading": a deep engagement with a particular text or a passage from a text. Distant Reading engages not with a particular text, but with a large corpus of texts: e.g., all novels published in English in the 20th century, all articles written in The New York Times and The Washington Post in the last decade, or the lyrics of all top-100 pop songs from the 1980s. Computational techniques applied to large collections of texts allow one to ask broad questions about structural and linguistic change over time and to look for patterns of language use that would not be evident from analysis of one or even several individual texts. Distant Reading, and computational text analysis more generally, is not intended to replace close reading, but to complement it. We will use CTA to explore how power structures and systems such as race, gender, and colonialism manifest themselves in bodies of text.

This class meets the QR and the HS requirements. It does not meet the ES requirement.


Who/when/where


Goals and Expectations

  1. Stay physically and mentally healthy and maintain intellectual and personal connection during a potentially difficult time.
  2. Gain a grounded introduction to various techniques in natural language processing, including word frequency analysis, semantic embeddings, sentiment analysis, and topic modeling.
    1. Understand qualitatively how these methods work.
    2. Be able to implement these methods using existing python packages.
    3. Understand the strengths and limitations of these methods.
  3. Gain experience posing research questions that can be addressed with computational text analysis, particularly questions that explore how racism, sexism, nationalism, and colonialism manifest in bodies of texts. This includes situating and contextualizing your research and presenting your results.
  4. Improve your programming skills and analytical/computational thinking.
  5. Have fun while growing and learning.

Community Agreement

Let's think about what type of community we want to create this term. Here is a community agreement based on one written by Federico Ardila-Mantilla.

This course aims to offer a joyful, meaningful, and empowering experience to every participant; we will build that rich experience together by devoting our strongest available effort to the class. You will be challenged and supported. Please be prepared to take an active, critical, patient, creative, and generous role in your own learning and that of your classmates.

Participation and Engagement

We will do a lot of different things in our class sessions, including discussing readings. The readings we do will range widely in content, style, and difficulty. There are several goals and motivations we have for discussions:

Expectations for class discussions:

We should all work to create an inviting atmosphere and ensure that there is opportunity for all to contribute. At the same time, there is no need for everybody to contribute equally. It is natural for some people to talk more than others, and we think this is normal and good. Also, we expect that students will engage and contribute at different levels, depending on prior coursework. Again, we see this diversity of backgrounds as a strength and not a weakness; there are roles for everyone to play. Asking good questions is as important as providing answers.

The point of discussions is not to figure out who is right and who is wrong, but to help all of us get to a deeper, and not necessarily uniform, understanding. Disagreements can and will happen, of course, but those disagreements will be investigated in a way that respects every participant's right to their own opinion.

Attendance policy: Because of the workshop/seminar nature of this class, attendance and active participation are crucial. As such, your attendance in class is necessary not only to your success but also to the success of your classmates. Therefore, you are allowed two unexcused absences without penalty. Please don't hesitate to contact us in case of illness, emergencies, and other extenuating circumstances.

What your Evaluation is Based on

Your evaluation will be based loosely on the following:

In general, we recommend against grades; we believe they are more likely than not to interfere with genuine, reflective learning. This is especially true in this class, where we have found that many of the class activities really don't lend themselves to letter grading. We do not have any quota of A's, B's, etc.


More Course Info and Advice

Structure and Pacing


What this Class Isn't

  1. This is not a class on artificial intellegence (whatever that means).
  2. We will not cover large language models (LLMs) such as ChatGPT, etc.
  3. This is not an introductory programing class, in the sense that it's not designed to systematically cover a standard set of introductory coding topics and skills. That said, the course does cover some coding techniques, and so could be a good chance to "level up" your coding skills -- including for those who have no coding experience.


Help/Coding Sessions

Once we get into the more programming-intensive part of the course, there will be help/coding sessions. You are warmly invited and encouraged to attend these sessions. Help sessions are relaxed, informal, and hopefully fun. Things that happen at help sessions:

  1. The TAs and/or I am around to offer help on assignments and the final project.
  2. Some students work in groups at help sessions, others work more or less alone.
  3. Help sessions are also a chance to ask general questions about the course. Conversations also sometimes wander into other areas: politics, the state of the world, what's for dinner, what classes are offered next term, and so on.
  4. Help sessions are a great way to meet other students in the class.
  5. Almost always there will be coffee/tea and/or snacks.


Individual Meetings

We are happy to meet with students one-on-one. The best way to set up an appointment is to send an email. There are lots of reasons why you might want to meet:

  1. You have some in-depth questions that there isn't time to explore in a help session.
  2. You have a question that you think is too basic or you're uncomfortable asking in a help session. (You shouldn't be uncomfortable, since, as the saying goes, there are no dumb questions! But we understand that you might be uncomfortable nevertheless.)
  3. You want to explore possibilities for your project.
  4. You want to discuss some challenges you're facing in the class.
Please don't hesitate to reach out if there's anything you want to discuss. You should also feel free to reach out to the TA.


Diversity, Inclusion, and Belonging

It is our intention that students from all backgrounds and perspectives be well served by this course, that students' learning needs be addressed both in and out of class, and that the diversity that students bring to this class be viewed as a resource, strength, and benefit. we aim to present materials and activities that are respectful of diversity: gender, sexuality, disability, age, religion, socioeconomic status, ethnicity, race, and culture.

Learning about diverse perspectives and identities is an ongoing process. We are always looking to learn more about power and privilege and the harmful effects of racism, sexism, homophobia, classism, and other forms of discrimination and oppression. Your suggestions are encouraged and appreciated. Please let us know of ways to improve the effectiveness of the course for you personally, or for other students or student groups. If something was said or done in class (by anyone, including us) that made you feel uncomfortable, please let me know. You can also reach out to Provost Ken Hill or Associate Dean Kourtney Collum.


Gender-based discrimination: Title IX

COA is dedicated to establishing and maintaining a safe and inclusive campus where all community members have equal access to COA’s educational and employment opportunities. We strive to promote an environment of respect, safety, and well-being and will not tolerate gender-based or sexual discrimination nor sexual harassment of any kind.

As faculty members, we are considered "responsible employees" and are required to share any disclosures of sexual or gender-based misconduct with the Title IX Coordinator. This includes disclosures of experiences that happened before an individual's time at COA. This is to ensure that all community members who have experienced sexual misconduct receive support, options, and information about their rights and resources. Community members are not obligated to respond to this outreach, and this will not generate a report to law enforcement.

For more information regarding Title IX, our institutional policy, and to access helpful resources, visit COA’s Title IX website: https://www.coa.edu/human-resources/title-ix.

If you have any questions or want to explore support and assistance, please contact COA’s Title IX Coordinator, Puranjot Kaur, at pkaur@coa.edu. Speaking to the Title IX Coordinator does not automatically initiate a college resolution. Instead, much of her work is around providing supportive measures to ensure you can continue to engage in COA's programs and activities.

Note on Pregnancy and Related Conditions:

Title IX prohibits discrimination based on sex in education programs and activities. This prohibition on discrimination extends to pregnancy and related conditions. Pregnancy and related conditions encompass pregnancy, childbirth, miscarriage, termination of pregnancy, false pregnancy, lactation, or recovery from any of these conditions.

Students experiencing pregnancy or related conditions may voluntarily initiate contact with the Title IX Coordinator to request reasonable adjustments available under Title IX. Reasonable adjustments may include but are not limited to: excusing student absences; allowing students to make up missed work; opportunities to move around during class; additional breaks; missing some or all of a class session to nurse or pump, and to have the opportunity to make up any work missed. Information on lactation space on campus can be found here: http://www.coa.edu/human-resources/title-ix/support-resources/lactation-space.

Students who believe they have been subject to discrimination because of pregnancy or related condition status may file a formal complaint with the Title IX Coordinator. If you are a pregnant or parenting student, and you are in need of any adjustments. please let me know at your earliest convenience.


Statements about Academic Honesty and Hours of Academic Engagement


Schedule

Important Links

Week 01

Class: Monday, March 31, 2025


Class: Thursday, April 3, 2025


Week 02

Class: Monday, April 7, 2025

  • Before class
  • In Class
    1. Discuss reading
    2. Discuss colab exploration
    3. Introduction to NLTK, stop words, tokens, word frequencies


Class: Thursday, April 10, 2025


Week 03

Class: Monday, April 14, 2025

  • tba


Class: Thursday, April 17, 2025

  • tba


Week 04

Class: Monday, April 21, 2025

  • tba


Class: Thursday, April 25, 2025

  • tba


Week 05

Class: Monday, April 28, 2025

  • tba


Class: Thursday, May 1, 2025

  • tba


Week 06

Class: Monday, May 5, 2025

  • tba


Class: Thursday, May 8, 2025

  • tba


Week 07

Class: Monday, May 12, 2025

  • tba


Class: Thursday, May 15, 2025

  • tba


Week 08

Class: Monday, May 19, 2025

  • tba


Class: Thursday, May 22, 2025

  • tba


Week 09

Class: Monday, May 26, 2025

  • tba


Class: Thursday, May 29, 2025

  • tba


Week 10

Class: Monday, June 2, 2025

  • tba


Class: Thursday, June 5, 2025

  • tba


Resources

Software and Data

Books and Such

Other Courses

Tutorials and Explainers


The building in which we gather for this class, and all of College of the Atlantic, is located on traditional lands of the Wabanaki people. The four Native American tribes in Maine today are the Maliseet, Micmac, Penobscot, and Passamaquoddy, collectively referred to as the Wabanaki. I believe it is important to acknowledge that our presence on this land entangles us in the web of colonialism, past and present. The future, however, is still unwritten.