|
|
|
||
|
The usage of computer-aided analysis of textual sources has been a natural accompaniment of computer technology proliferation since the early 1950s. As computer software and hardware became widely accessible to even non-expert users, Digital Humanities (along with other analogical monikers) experienced rapid growth during the last 30 years. If we consider the ever-growing hardware capacity, digital shifts in all of the social sciences and humanities fields, and the all-encompassing interconnectivity of the internet age, it is only logical, that formerly niche-expertize has slowly turned into standard skill or even requirements for the research practice. The rapid development and spread of AI-assisted user and research performance only hastened and deepened the ever-growing pressure on the digitalization of academia. This course ameliorates this situation by offering low-threshold, entry-level access to knowledge and skillsets important for further and deeper exploration of the matter.
The course is open only for students of master's degree programmes. Last update: Hrubá Kateřina, Mgr. (28.01.2026)
|
|
||
|
Students will acquire fundamental knowledge, skills, and orientation in Digital Humanities. They become familiar with the most important concepts, operations, and subfields of DH. This course serves as an introductory class for the Certificate in Digital Humanities students and is therefore directly connected to the other parallel and following courses aimed at a detailed understanding of ML (NPFL 112, NPFL 142, NPFL 143). IT IS MANDATORY TO BE SIMULTANEOUSLY ENROLLED IN NPFL 112 IN THE WINTER SEMESTER. Last update: Kosová Klára, Mgr., Ph.D. (16.09.2025)
|
|
||
|
Compulsory attendance; minimum 50% points in part A), B) and C) each. A: 100-91 pts B: 90-81 pts C: 80-71 pts D: 70-61 pts E: 60-51 pts F(failed): 50 pts or less Last update: Kosová Klára, Mgr., Ph.D. (16.09.2025)
|
|
||
|
Recommended reading Accelerating Social and Behavioral Science Through Ontology Development and Use | National Academies (n.d.). Available at: https://www.nationalacademies.org/our-work/accelerating-social-and-behavioral-science-through-ontology-development-and-use (accessed 9 October 2023). Arnold T and Tilton L (2015) Humanities Data in R: Exploring Networks, Geospatial Data, Images, and Text. Quantitative Methods in the Humanities and Social Sciences. Cham: Springer International Publishing. Available at: https://link.springer.com/10.1007/978-3-319-20702-5 (accessed 9 October 2023). Greenwell BB& B (n.d.) Hands-On Machine Learning with R. Available at: https://bradleyboehmke.github.io/HOML/ (accessed 9 October 2023). Krippendorff KH (2018) Content Analysis: An Introduction to Its Methodology. Fourth edition. Los Angeles: SAGE Publications, Inc. Piotrowski M (2012) Natural Language Processing for Historical Texts. Synthesis Lectures on Human Language Technologies. Cham: Springer International Publishing. Available at: https://link.springer.com/10.1007/978-3-031-02146-6 (accessed 9 October 2023). R for Data Science (2e) (n.d.). Available at: https://r4ds.hadley.nz/ (accessed 9 October 2023). Ramírez AG, Mejía JM, Martin PV, et al. (2023) Digital Humanities, Corpus and Language Technology / Humanidades Digitales, Corpus y Tecnología Del Lenguaje. University of Groningen Press. Available at: https://books.ugp.rug.nl/index.php/ugp/catalog/book/128 (accessed 1 February 2024). Silge EH and J (n.d.) Supervised Machine Learning for Text Analysis in R. Available at: https://smltar.com/ (accessed 9 October 2023). Last update: Kosová Klára, Mgr., Ph.D. (16.09.2025)
|
|
||
|
This is a course for students of the Certificate in Digital Humanities, with twelve sessions, where physical presence is required. Students complete group tasks after each session and collaborate on a group project to produce a salient research design proposal by the end of the semester. MOODLE: https://dl2.cuni.cz/course/view.php?id=5749
Use of generative AI tools: The use and citation of generative AI tools (such as ChatGPT or MS Copilot) in seminar papers and other coursework must comply with the decrees of the IMS Director No. 7/2023 and 9/2023. Generative AI tools may be used unless explicitly prohibited by the instructor. However, they may not be used to generate substantial sections of the text or replace the student’s own intellectual contribution. The student remains fully responsible for any content generated with assistance of AI tools. Presenting AI-generated content, whether verbatim, rephrased, or only slightly modified, as one's own work constitutes plagiarism. Every submitted paper must include a transparent statement specifying which generative AI tools were used, in which stage of the work they were employed, and how they were used, or confirming that no generative AI tools were used. If this statement is missing or incomplete, the instructor is not permitted to accept the paper for evaluation. Unless the instructor explicitly prohibits the use of generative AI tools, the decision to use or not to use them rests fully with the student. The student has the right to request that the instructor does not use AI assistance for evaluating their work.
Last update: Kosová Klára, Mgr., Ph.D. (08.10.2025)
|
|
||
|
The final grade (100 points) comprises fulfilling three partial activities: A) midterm (15 pts) B) regular homework assignments (35 pts) C) groupwork research design (50pts) Last update: Kosová Klára, Mgr., Ph.D. (16.09.2025)
|
|
||
|
I. 1.10. - Introduction & computational logic How do computers perceive the world? What is data? How do we interact with computers? What is “programming”? Working groups selection II. 8.10. - Text from a computer perspective First module - what is data(sets), how can we produce data? Text from a computer perspective, operationalizing text, introduction into analysing text in DH (approaches and methods).
III. 15.10. - Qualitative coding Introduction to qualitative coding, attributing information to an analyzed piece of text. IV. 22.10. - Text analysis I. Second module: What is in the text? Information extraction Frequencies - fundamentals of quantitative methods as the basis of corpus linguistics Keyword extraction V. 29.10. - Text analysis II. Introduction to machine learning: supervised/unsupervised and an overview of methods. Named entities recognition VI. 5.11. - Text analysis III. Third Module: What kind of text is that? Text classification Introduction to sentiment analysis VII. 12.11. - Midterm Group project presentation VIII. 19.11. - Text analysis IV. Similarity analysis Semantic distances and clustering IX. 26.11. - Text analysis V. Topic modelling Introduction to LDA X. 3.12. - Data visualisation & special hands-on session Introduction to data visualisation and graphs Application in ggplot(2). XI. 10.12. - Network analysis Module 4: Social and semantic structures Introduction to network analysis and basics of Gephi. XII. 17.12. - Mapping & GIS Module 4: Geographic data Introduction into mapping, software, applications, coordinates, layers, and data formats. XIII. Research workshop Final presentations (date to be determined) Last update: Kosová Klára, Mgr., Ph.D. (16.09.2025)
|
|
||
|
The course is exclusively for the students enrolled in the Certificate in Digital Humanities program. IT IS MANDATORY TO BE SIMULTANEOUSLY ENROLLED IN NPFL 112 IN THE WINTER SEMESTER. Last update: Kosová Klára, Mgr., Ph.D. (16.09.2025)
|