Postgraduate Course: Artificial Intelligence and Storytelling (EFIE11504)
Course Outline
| School | Edinburgh Futures Institute |
College | College of Arts, Humanities and Social Sciences |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
Availability | Available to all students |
| SCQF Credits | 20 |
ECTS Credits | 10 |
| Summary | The course invites students to play with Artificial Intelligence (AI) in order to create and tell stories, using image and text. The AI technology is seen as a tool that can both generate new ideas and complement those of a person, while also acting as a potential bridge for collaboration between people.
Starting from no required technical background, the student will learn how AI, and especially Machine Learning, functions along with its strengths and limitations. With a combination of hands-on experience, workshops on creative storytelling, and invited lectures from experts in the diverse areas on AI and its application for creating stories, the course prepares students to engage creatively with AI, participation in interdisciplinary AI projects, or progression towards more technical study. |
| Course description |
The first week's opening lecture will introduce you to Artificial Intelligence (AI) and the various options it provides for Storytelling. This is followed by a creativity workshop, which aims to ease you into the overall theme of the course. The idea is that you will take the skills and ideas developed there with you into your project work. These projects primarily involve writing a story with the use of AI (no previous programming experience required).
Most self study time, as well as a significant part of the synchronous workshops, will have you working with a high level AI tool-set that has been custom made for the course (and which you can 'take home' when the course is over).
Select workshops will focus a bit more on some technical aspects of AI, helping you better understand how the tools you have been using work. At the same time, you will be invited to build AI solutions 'by hand', replicating the process Machine Learning algorithms go through. Later weeks will include collaborative activities using the tools you have been practising with in weeks prior, and testing the limits of their creative potential, while also exposing you to the dangers of their uncritical use.
Evaluation will be undertaken via two pieces of coursework, at 20% and 80%, both of which follow a similar structure, with 85% of the mark attached to story generation exercises. Using the provided AI tool-set (and in the second coursework, some external AI tool use), you will be tasked with directing the AI into producing a story that accomplishes certain feats. The rest 15% of each coursework involves technical tasks related to AI engineering, such as working with code repositories or introductory level programming, and critique of provided examples.
The last weeks will include invited lectures, providing you with guidance on further possibilities for storytelling with AI, each focussing on a different AI area or application.
Edinburgh Futures Institute (EFI) - Hybrid Course Delivery Information:
The Edinburgh Futures Institute delivers many of its courses in hybrid mode. This means that you may have some online students joining sessions for this course. To enable this, the course will use technologies to record and live-stream student and staff participation during their teaching and learning activities.
Students should be aware that:
- Classrooms used in this course will have additional technology in place: in some cases, students might not be able to sit in areas away from microphones or outside the field of view of all cameras.
- All presentations, and whole class discussions will be recorded (see the Lecture Recording and Virtual Classroom policies for more details).
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | |
| Prohibited Combinations | |
Other requirements | None |
Information for Visiting Students
| Pre-requisites | None |
| High Demand Course? |
Yes |
Course Delivery Information
|
| Academic year 2026/27, Available to all students (SV1)
|
Quota: 30 |
| Course Start |
Semester 2 |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
200
(
Lecture Hours 5,
Seminar/Tutorial Hours 1,
Supervised Practical/Workshop/Studio Hours 14,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
176 )
|
| Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
This course will be assessed by means of the following components:
1) Creative Story Writing Project with AI: Outlining a Story (20%)
- 85% of the overall assessment component mark will be derived from the Creative Story Writing Project with AI. This will be built around outlining a story with 3 acts. This assessment component focuses on having the student use all techniques demonstrated in the course, with most questions explicitly identifying which techniques to use.
- 15% of the overall assessment component mark will be derived from execution of technical tasks. For this assessment component, these will have very specific steps, with significant instructor support.
Learning Outcomes Assessed by Component: 1, 2, 3, 4
2) Creative Story Writing Project with AI / Execution of Technical Tasks (80%)
- 85% of the overall assessment component mark will be derived from the Creative Story Writing Project with AI. This will be built around writing a scene for a story with 3 acts. This assessment component allows for more flexibility in what techniques to use for each question, while also involving the need to creatively use combinations of techniques. For the second coursework, students may, if they wish, incorporate additional generative AI tools beyond those introduced in the course. This is intended to support self-directed exploration and creative experimentation. Any such tools should be used critically and integrated coherently into the overall project, and according to specification.
- 15% of the overall assessment component mark will be derived from the execution of technical tasks. For this assessment component, these will mostly have very specific steps, with significant instructor support, but also provide some more open ended challenges.
Learning Outcomes Assessed by Component: 1, 2, 3, 4 |
| Feedback |
Feedback on any formative assessment may be provided in various formats, for example, to include written, oral, video, face-to-face, whole class, or individual. The Course Organiser will decide which format is most appropriate in relation to the nature of the assessment.
Feedback on both formative and summative in-course assessed work will be provided in time to be of use in subsequent assessments within the course.
Feedback on the summative assessment(s) will be provided in written form via Learn, the University of Edinburgh's Virtual Learning Environment (VLE).
Formative Feedback Opportunity:
Formative feedback is ongoing feedback which monitors learning and is intended to improve performance in the same course, in future courses, and also beyond study.
Students will be provided with synchronous activities working alongside their instructor on the two pieces of assessment, during which formative feedback is provided. Students who are unable to attend any such sessions will be able to ask questions in an online forum which the course Lecturer will monitor and respond to.
For each of the coursework components, while that coursework is released, and especially during the two weeks before the submission deadline for the respective coursework, the students will be able to share their solutions so far with the teaching staff and receive an evaluation with constructive feedback and advise. Where this can be done without allowing for plagiarism, the communication will be open to the class on the course's forum. Specifically for the majority of questions that are evaluated on the generated text, students will be able to share the generated text but not the steps followed to produce it (commands, setup, or self-authored text).
Students will have access to technical support during the same timeline, helping them set up their environments and with executing commands for the coursework. |
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- Explain how contemporary AI and machine learning systems function, including their strengths, limitations, and creative affordances, in the context of storytelling.
- Use AI tools critically and creatively to produce narrative artefacts involving text and/or image.
- Analyse, critique, and communicate the role of AI in creative projects, including issues of authorship, bias, and responsibility.
- Develop foundational technical and analytical skills relevant to participating in or collaborating on AI-enabled creative projects.
|
Reading List
Essential Engagement:
Story Machines How Computers Have Become Creative Writers.
Sharples, Mike; Prez y Prez, Rafael, 1, Routledge, 2022
Note: Chapters 1 and 6
Into the woods a five-act journey into story / John Yorke.
Yorke, John (Television producer), author., New York, NY, The Overlook Press, 2015 - 2015
Note: Chapters 1, 2 and 3, pp 3-44
Recommended Engagement:
Story Machines How Computers Have Become Creative Writers.
Sharples, Mike; Prez y Prez, Rafael, 1, Routledge, 2022
What it is / Lynda Barry.
Barry, Lynda, 1956- author., Montreal, Canada, Drawn & Quarterly, 2017
Note: pp 138-173
Automatic Story Generation: Challenges and Attempts
Alabdulkarim, Amal ; Li, Siyan ; Peng, Xiangyu, arXiv.org, 2021-02-25
The creativity code : art and innovation in the age of AI
Du Sautoy, Marcus, First US edition., Cambridge, Massachusetts, The Belknap Press of Harvard University Press, 2019
The artist in the machine : the world of AI-powered creativity / Arthur I. Miller.
Miller, Arthur I., author., Cambridge, Massachusetts ;, The MIT Press, 2019
Note: Chapters 1 to 6; pp 5 - 44
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow.
Géron, Aurélien., 3rd ed., Sebastopol, O'Reilly Media, Incorporated, 2022
Note: Chapters 1 to 4, 10, 11; pp 3 -146, 257 - 318
Data Mining: Practical Machine Learning Tools and Techniques, Fourth Edition
Witten, Ian H ; Frank, Eibe ; Hall, Mark A ; Pal, Christopher J, Fourth Edition, Place of publication not identified, Elsevier Science and Technology Books, Inc, 2017
Note: Chapters 1 to 4; pp 3 - 160
Bayesian reasoning and machine learning / David Barber.
Barber, David, 1968-, Cambridge ;, Cambridge University Press, 2012
Note: Chapters 7, 15; pp. 127 - 162, 329 - 358
Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville.
Goodfellow, Ian, author., Bengio, Yoshua, author.; Courville, Aaron, author., Cambridge, Massachusetts, The MIT Press, 2016
Note: Chapter 1; pp 3 - 26
The elements of statistical learning : data mining, inference, and prediction
Hastie, T. J. (Trevor J.), 1953-, Tibshirani, Robert.; Friedman, J. H. (Jerome H.), Second edition., New York, Springer, 2009
Note: Chapter 1; pp 1-8 |
Additional Information
| Graduate Attributes and Skills |
Not entered |
| Keywords | Artificial Intelligence,Storytelling,Machine Learning,Creative AI,Generative Models |
Contacts
| Course organiser | Dr Pavlos Andreadis
Tel: (0131 6)50 8281
Email: Pavlos.Andreadis@ed.ac.uk |
Course secretary | Miss Zoe Hogg
Tel:
Email: Zoe.Hogg@ed.ac.uk |
|
|
University Homepage