Course Contents
How can emotions in literary texts be analyzed with the help of the computer? Can quantitative analyses be used to identify characteristics of literary genres? Does suspense literature show a particular tendency towards emotionality?
Sentiment analysis is a current topic of discussion in the Digital Humanities, with automated text analysis playing a particularly important role.
In this course, we will focus on a specific area of sentiment analysis by applying it to literary texts in different ways, with a focus on suspense literature, and look at manual and automated analysis of sentiment in literary texts.
Since the course is a "practical course", the focus will be on application examples with hands-on sessions and the implementation of a small group project.
Literature
Reading List (i.a.):
Carroll, Noël (2001): The Paradox of Suspense. In: Beyond Aesthetics: Philosophical Essays, 1st ed., 25470. Cambridge University Press. DOI 10.1017/CBO9780511605970.
Liu, Bing (2015): Sentiment analysis and opinion mining, San Rafael, Calif.: Morgan & Claypool. (Online access via ULB catalogue to 1st edition (2012))
Smuts, Aaron (2008): The Desire-Frustration Theory of Suspense The Journal of Aesthetics and Art Criticism, 66 (3): 281291.
Smuts, Aaron (2021): "The Paradox of Suspense", In: Edward N. Zalta (ed.), The Stanford Encyclopedia of Philosophy, https://plato.stanford.edu/archives/win2021/entries/paradox-suspense/.
Primary literature likely to be used, including the following English short stories:
Lewis, M.G. (1808): The Anaconda.
Polidori, J.W. (1819): The Vampyre.
Gaskell, J.W. (1852): The Old Nurse's Story.
Oliphant, M. (1881): The Open Door.
Conan Doyle, A. (1898): The Brazilian Cat.
Conan Doyle, A. (1913): How it happened.
Preconditions
Prior fundamental knowledge of programming in Python and the use of digital text analysis tools is advantageous and encouraged. Before the semester begins, please work through Evan Muzzall's (University of Stanford) workshop material, which can be found here: https://eastbayev.github.io/SSDS-TAML/intro.html
A notebook with internet access is required in some sessions.
Further Grading Information
Further information on the course and its organisation will be announced in the 1st session.
Online Offerings
moodle
How can emotions in literary texts be analyzed with the help of the computer? Can quantitative analyses be used to identify characteristics of literary genres? Does suspense literature show a particular tendency towards emotionality?
Sentiment analysis is a current topic of discussion in the Digital Humanities, with automated text analysis playing a particularly important role.
In this course, we will focus on a specific area of sentiment analysis by applying it to literary texts in different ways, with a focus on suspense literature, and look at manual and automated analysis of sentiment in literary texts.
Since the course is a "practical course", the focus will be on application examples with hands-on sessions and the implementation of a small group project.
Literature
Reading List (i.a.):
Carroll, Noël (2001): The Paradox of Suspense. In: Beyond Aesthetics: Philosophical Essays, 1st ed., 25470. Cambridge University Press. DOI 10.1017/CBO9780511605970.
Liu, Bing (2015): Sentiment analysis and opinion mining, San Rafael, Calif.: Morgan & Claypool. (Online access via ULB catalogue to 1st edition (2012))
Smuts, Aaron (2008): The Desire-Frustration Theory of Suspense The Journal of Aesthetics and Art Criticism, 66 (3): 281291.
Smuts, Aaron (2021): "The Paradox of Suspense", In: Edward N. Zalta (ed.), The Stanford Encyclopedia of Philosophy, https://plato.stanford.edu/archives/win2021/entries/paradox-suspense/.
Primary literature likely to be used, including the following English short stories:
Lewis, M.G. (1808): The Anaconda.
Polidori, J.W. (1819): The Vampyre.
Gaskell, J.W. (1852): The Old Nurse's Story.
Oliphant, M. (1881): The Open Door.
Conan Doyle, A. (1898): The Brazilian Cat.
Conan Doyle, A. (1913): How it happened.
Preconditions
Prior fundamental knowledge of programming in Python and the use of digital text analysis tools is advantageous and encouraged. Before the semester begins, please work through Evan Muzzall's (University of Stanford) workshop material, which can be found here: https://eastbayev.github.io/SSDS-TAML/intro.html
A notebook with internet access is required in some sessions.
Further Grading Information
Further information on the course and its organisation will be announced in the 1st session.
Online Offerings
moodle
- Lehrende: Svenja Guhr
Semester: ST 2023