Abstract
Overview
As part of the ‘Harnessing AI for Teaching and Learning Excellence at HKU’ conference next December, we would like to propose a hands-on experience with a software developed with a recent Teaching Development Grant (‘Writing Creatively: an AI-powered Multilingual Online Platform’). This software is named Motisse and provides support to write, with a focus on creative writing (short stories, personal diary, letters, poems etc.).
Today, most people use large language models like ChatGPT to get answers to questions or get work done for them. While this may increase productivity, it may also prevent younger users from developing crucial intellectual abilities. Our software adopts a different approach to help its users develop (writing) skills through tailored feedback and accompanied practice, so that they can write with pleasure and confidence.
Our product clearly departs from existing software – which addresses either one’s grammar like Grammarly or the structure of long documents like novels, like Scrivener. Although Motisse can help with one’s writing style and ability to organize text content, its innovativeness lies in tackling other more creative aspects of writing. It adapts to who the user is or wishes to be, and to their intended audience, provides suggestions to start a story, offers a range of instruments to detect and address clichés, fine-tune conveyed emotions, ‘show rather than tell’ etc. Importantly, it never rewrites in place of the user but highlights issues and provides (generic enough) suggestions by leveraging the power of the latest large language models. The underlying prompts have been extensively crafted: they integrate relevant linguistic and literary knowledge as well as precise directions to analyze a wide variety of texts in an in-depth and tailored manner.
The aim of the workshop is to provide a clear illustration of how generative AI – more specifically here large language models – can be leveraged to provide long-term learning opportunities and design products which may be of interest both for secondary/university students and a wider range of people interested in writing.
The PI of the TDG – Christophe Coupé – and a student from the BA(Humanities and Digital Technologies) – Mr. Syed Ali Mansoor, who developed the interface – will facilitate the workshop.
Learning Outcomes
The learning outcomes of the workshop are as follows:
- Apply instructions to use a GenAI-based software centered on creative writing
- Create an interesting text output leveraging the creative functionalities of the software
- Analyze how large language models can be queried for suggestions rather than precise answers
- Reflect on the use of Generative AI in teaching and learning
Workshop Plan
Participants will be invited to join the workshop with a short text of their choice.
The workshop will be organized as follows:
- 20 minutes to introduce the project and its philosophy, and to briefly explain how the software works
- 40 minutes to experiment with the software, try its different functions, and improve one’s short text, with individual facilitation and feedback from the organizers of the workshop
- 20 minutes to debrief and discuss both the software and how to use GenAI to design pedagogical activities
Presenter(s) / Author(s)
