Course Quantitative text analysis for humanities scholars: A corpus-based approach to large-scale text analysis

Course description
The course offers an introduction to analyzing texts through a combination of close reading strategies and quantitative corpus-based approaches.
The course aims to introduce participants to the skills and knowledge necessary to conduct large-scale analyses of discourse in various contexts using quantitative corpus-based methods. During the course, we will work mainly with media texts as an example, but the methods introduced will be applicable to many different types of text, e.g., social media posts, policy documents, news articles, and literary texts. We will mainly be working with corpora of English texts, but the methods introduced can equally well be applied to Danish text corpora.
Upon completing the course, participants will have acquired a deeper understanding of the process of constructing a digital text corpus. They will have learnt how to operationalize research questions effectively and have gained hands-on experience in performing large-scale text analysis through quantitative corpus linguistic methods.
The quantitative and corpus-based approach presented in the course is relevant in a wide range of different research contexts including sociolinguistics, critical discourse analysis, media studies, literary studies and more.
The course also includes a basic introduction to working with text in Python. Participants will learn to use Python to preprocess and analyze large text corpora, they will also learn how to use NLP tools such as sentiment analysis and topic modeling to identify linguistic patterns and features in discourse.
No prior experience with Python or statistics is required. 

Aim
This course aims to introduce participants to the skills and knowledge necessary to conduct large-scale analyses of discourse in various contexts using quantitative corpus-based methods.

Literature
Baker, P. (2012). Acceptable bias? Using corpus linguistics methods with critical discourse analysis. Critical Discourse Studies, 9(3), 247–256. https://doi.org/10.1080/17405904.2012.688297

Jacobs, T., & Tschötschel, R. (2019). Topic models meet discourse analysis: A quantitative tool for a qualitative approach. International Journal of Social Research Methodology, 22(5), 469–485. https://doi.org/10.1080/13645579.2019.1576317

Manovich, L. (2020). Cultural analytics. The MIT Press.

Nordahl-Hansen, A., & Kvernbekk, T. (2020). Construct Validity in Scientific Representation: A Philosophical Tour. Nordisk tidsskrift for pedagogikk & kritikk, 6, 88–99. https://doi.org/10.23865/ntpk.v6.1704
 
Ondelli, S. (2018). Treat Texts as Data but Remember They Are Made of Words: Compiling and Pre-processing Corpora. I A. Tuzzi (Red.), Tracing the Life Cycle of Ideas in the Humanities and Social Sciences (s. 133–150). Springer International Publishing. https://doi.org/10.1007/978-3-319-97064-6_7

Target group/Participants
The course is especially relevant for early-stage PhD-students, but it is also relevant for later-stage students already working with corpus-based approaches or discourse analysis.

No prior experience with Python or statistics is required. 

Language    
English

Form
Lectures and hands-on workshops

ECTS-credits
3

Lecturers

Ulf Dalvad Berthelsen, udb@cc.au.dk
Yuri Bizzoni, yuri.bizzoni@cc.au.dk

Teaching assistant
Ea Lindhardt Toft, elt@cc.au.dk

Venue
Campus Aarhus    

12/11: 10.00-16.00 - Jens Chr. Skous Vej 7, 8000 Aarhus C. Building 1465, room 616
13/11: 9.00-16.00 - Åbogade 15, 8200 Aarhus N. Building 5524, room 137
14/11: 9.00-16.00 - Helsingforsgade 8 , 8200 Aarhus N. Building 5008, room 128H
15/11: 9.00-14.00 - Åbogade 15, 8200 Aarhus N. Building 5524, room 137

Course dates:

• 12 November 2024 10:00 - 16:00
• 13 November 2024 09:00 - 16:00
• 14 November 2024 09:00 - 16:00
• 15 November 2024 09:00 - 14:00