Postgraduate Course: Computational Text Analysis (PGSP11584)
|School||School of Social and Political Science
||College||College of Arts, Humanities and Social Sciences
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
||Availability||Available to all students
|Summary||This course will give students training in the use of computational text analysis techniques. The course will prepare students for dissertation work that uses textual data and will provide hands-on training in the use of the R and Python programming languages. The course will provide a venue for seminar discussion of examples using these methods in the empirical social sciences as well as lectures on the technical and/or statistical dimensions of their application.
There are no formal pre-requisites for enrolment in this course. However, for those with no background in mathematics or statistics it is preferable that they take Core quantitative data analysis 1 and 2 (SCIL11009).
The course has two principal learning aims: 1) training in the application of computational text analysis techniques with the use of R or Python programming languages; 2) an in-depth introduction to both the background of text analysis techniques and more recent examples of computational text analysis. Computational text analysis has taken off as a field in recent years, as attested by three recent review articles devoted to the topic across Sociology, Political Science, and Economics (see https://www.annualreviews.org/doi/abs/10.1146/annurev-polisci-052615-025542 and https://www.annualreviews.org/doi/abs/10.1146/annurev-soc-081715-074206 and https://www.aeaweb.org/articles?id=10.1257/jel.20181020).
The course will give students the ability to conduct their own research using these techniques as well as the requisite background in the history of text analysis. Text analysis has a history that predates the use of computational methods and students will be introduced to the conceptual elements of its application historically, as well as the advances afforded by computational techniques. Each lecture will focus on the more technical and/or statistical dimensions of computational text analysis techniques. Seminars will be devoted to the discussion of applied examples. The seminars will be organized by thematic topic and readings will be selected that speak to the technical aspects of the most recent lecture. Topics that may be covered include: word frequency analysis; topic modelling; structural topic modelling; and word embedding.
Each week students will be expected to attend the lecture or seminar, depending on the week as these will alternate. In seminar weeks, students will be expected to read all of 2-3 essential readings, which will form the basis for a class discussion.
NOTE: For the first two weeks, students will complete introductory R exercises. These will be run out of the Research Training Centre, who will be offering introductory R instruction in weeks 1 and 2 of Semesters 1 and 2. These will be formative but provide the requisite basic training in the use of R and RStudio. Lectures will still run in these weeks but there will be no tutorials.
In subsequent lecture weeks, students will also be expected to complete a formative coding exercise in either the R or Python programming language. These will be set by the instructor and made accessible to students. Every week, students will also have a tutorial where they can raise questions related to the technical components of the lecture and discuss coding issues and concerns.
Assessment will take the form of one major summative assessment. This will be a 4000 word essay on a subject of the students¿ choosing (with prior approval by the instructor) using a dataset of their own choosing and applying at least one computational text analysis technique. The students will provide the code they used in reproducible format and will be assessed on both the substantive content of their essay contribution as well as their demonstrated competency in coding and text analysis.
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| None
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Academic year 2022/23, Available to all students (SV1)
|Learning and Teaching activities (Further Info)
Seminar/Tutorial Hours 20,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
||Summative essay + code for text analysis used (100%)
||Coding choices can be discussed in tutorial settings with the TA
|No Exam Information
On completion of this course, the student will be able to:
- Be competent in R or Python for computational text analysis
- Have knowledge of the applied literature in computational text analysis
- Provide reproducible workflows for text analyses with R Markdown or Jupyter notebooks
- Appraise the relationship between theory, measurement, and method in applied examples of computational text analysis techniques
- Design, conduct, and discuss a piece of research using computational text analysis techniques
|- Klaus Krippendorff. Content Analysis: An Introduction to Its Methodology. Third Edition. Sage. 2013.|
- Daniel Jurafsky and James H. Martin Speech and Language Processing, 2nd Edition. Prentice Hall. 2008.
- Kozlowski, AC et al. "The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings." American Sociological Review. 84(5) 905¿949.
- Nelson, LK, 2020. "Computational Grounded Theory: A Methodological Framework." Sociological Methods & Research. 49(1):3-42.
|Graduate Attributes and Skills
||o Communication and IT skills
o Autonomy and self-directed research
o Reflection and critical faculties
|Course organiser||Dr Chris Barrie
|Course secretary||Ms Emilia Czatkowska
Tel: (0131 6)51 3244