Postgraduate Course: Cultural and Literary Text Analytics (ENLI11269)
|School||School of Literatures, Languages and Cultures
||College||College of Arts, Humanities and Social Sciences
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
||Availability||Available to all students
|Summary||During the Cultural and Literary Text Analytics course, students will learn from scratch the theory and practice of analysing cultural and literary text with code. The course is suitable for students who have no prior experience of text analytics, text mining or programming in Python. At the end of this course, students will not only know the theory and practice of text analytics methods but will have gained fundamental skills to prepare, search and critically analyse cultural and/or literary text, present the results of their analysis visually and discuss them verbally and in writing.
The Cultural and Literary Text Analytics course aims to teach students computational text analytics methods, how they have been applied in literary research, how they can be applied hands-on to analyse concrete datasets programmatically using visualisations and how their results should be interpreted critically in the context of their accuracy.
In this course students will be introduced to the computational analysis of literary text with respect to text evolution over time, comparisons of authors, genres and literature across domains, character relationships and progression, geography and text aesthetics/interestingness. The methods covered in this course include computational linguistic analysis, person and place name recognition, network analysis, topic analysis, sentiment analysis, deep semantic analysis as well as visualisation techniques to aid the presentation of results. This is a data- and research-driven course which uses cultural and literary data sources in hands-on Python coding exercises while presenting methods and topics within the context of state-of-the-art research in this field.
The course is delivered in a standard teaching format of 10 weekly interactive seminars which are made up of a lecture/discussion (one hour) and a tutorial (one hour). Each week, the lecture introduces one or more text analytics methods, their theory, motivation and application and is combined with a related discussion in light of essential reading. A weekly tutorial includes practical coding exercises in group work where students learn how to acquire, manipulate and analyse literary textual data and how to critically interpret their visualised results. This includes a tailored introduction to Python programming at the start of the course. Programming exercises will be conducted using the University of Edinburghs virtual programming environment (Edinburgh Noteable).
Students of this course are examined on a combination of class participation, coding notebooks and a final project (including a presentation of the project idea, a coding notebook and a critical original write-up of their work) which showcases the practical skills learned during the course applying at least one of the text analytics methods. This course is of particular interest to students who would like to focus their literary research project work on quantitative text analysis at scale, or who would like to complement their qualitative research with computational literary text analysis.
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| None
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Not being delivered|
On completion of this course, the student will be able to:
- Articulate a critical understanding of the main subject areas linked to the use of cultural and literary text analysis methods.
- Explain and apply key methods, technologies and formats used in cultural and literary text analysis to real data.
- Develop original and creative responses to data driven text analysis in course discussions, tutorials and the student project.
- Deliver, in verbal and written form, coherent, balanced arguments on the use of cultural and literary text data and the results of a computational analysis.
- Evaluate current issues related to computational text analysis methods.
Walsh, Melanie,2021. Introduction to Cultural Analytics & Python. https://doi.org/10.5281/zenodo.4411250.
Schöch, Christof, 2021. Do Sentences in Novels Get Shorter over the Course of the 19th-Century, In: The Dragonflys Gaze, 2021. URL: https://dragonfly.hypotheses.org/p=1152.
Meirelles, Isabel, 2019. Visualizing information, In: The Shape of Data in Digital Humanities.
Ardanuy, M.C. and Sporleder, C., 2014, April. Structure-based clustering of novels. In Proceedings of the 3rd Workshop on Computational Linguistics for Literature (CLFL) (pp. 31-39).
Thomas, L., 2020. Modeling Long Novels: Network Analysis and A Brief History of Seven Killings. In The Palgrave Handbook of Twentieth and Twenty-First Century Literature and Science (pp. 653-667). Palgrave Macmillan, Cham.
Janosov, M., 2022. A Network Map of The Witcher. arXiv preprint arXiv:2202.00235.
Agarwal, A., Corvalan, A., Jensen, J. and Rambow, O., 2012, June. Social network analysis of Alice in Wonderland. In Proceedings of the NAACL-HLT 2012 Workshop on computational linguistics for literature (pp. 88-96).
Dekker, N., Kuhn, T. and van Erp, M., 2019. Evaluating named entity recognition tools for extracting social networks from novels. PeerJ Computer Science, 5, p.e189.
Conroy, Melanie, 2021. Literary Geographies in Balzac and Proust. Elements in Digital Literary Studies. Cambridge: Cambridge University Press. doi:10.1017/9781108992923.
Moncla, Ludovic, Mauro Gaio, Thierry Joliveau, and Yves-François Le Lay, 2017. Automated geoparsing of Paris street names in 19th century novels. In: Proceedings of the 1st ACM SIGSPATIAL Workshop on Geospatial Humanities, pp. 1-8.
Loxley, J., Alex, B., Anderson, M., Hinrichs, U., Grover, C., Thomson, T., Harris-Birtill, D., Quigley, A. and Oberlander, J., 2018. Multiplicity embarrasses the eye: The digital mapping of literary Edinburgh. The Routledge Companion to Spatial History (Routledge companions), pp. 604-628.
Alex, Beatrice, Claire Grover, Richard Tobin, and Jon Oberlander, 2019. Geoparsing historical and contemporary literary text set in the City of Edinburgh." Language Resources and Evaluation 53, no. 4, pp. 651-675.
Mohr, J.W. and Bogdanov, P., 2013. Introduction¿Topic models: What they are and why they matter. Poetics, 41(6), pp. 545-569.
Underwood, T., 2012. Topic Modelling just made simple enough, https://tedunderwood.com/2012/04/07/topic-modeling-made-just-simple-enough/
Schmidt, B.M., 2015, October. Plot arceology: A vector-space model of narrative structure. In 2015 IEEE International Conference on Big Data (Big Data) (pp. 1667-1672). IEEE.
Reagan, A.J., Mitchell, L., Kiley, D., Danforth, C.M. and Dodds, P.S., 2016. The emotional arcs of stories are dominated by six basic shapes. EPJ Data Science, 5(1), pp.1-12.
Piper, A. and Portelance, E., 2016. How cultural capital works: Prizewinning novels, bestsellers, and the time of reading. Post45, 10.
Kim, E. and Klinger, R., 2018. A survey on sentiment and emotion analysis for computational literary studies. arXiv preprint arXiv:1808.03137.
Jacobs, A.M., 2019. Sentiment analysis for words and fiction characters from the perspective of computational (Neuro-) poetics. Frontiers in Robotics and AI, 6, p.53.
PM, K.R., 2021. Sentiment analysis, opinion mining and topic modelling of epics and novels using machine learning techniques. Materials Today: Proceedings.
Underwood, T., 2016. The Life Cycles of Genres, Cultural Analytics. https://culturalanalytics.org/article/11061-the-life-cycles-of-genres
Other selected articles from the Cultural Analytics journal.
|Graduate Attributes and Skills
|Keywords||literary text analytics,cultural text analytics,text as data,text mining
|Course organiser||Dr Beatrice Alex
Tel: (0131 6)50 2684
|Course secretary||Miss Kara McCormack
Tel: (0131 6)50 3030