Athina AI Research Agent
AI Agent that reads and summarizes research papers
Table of Contents
Do not index
Do not index
Original Paper
Original Paper: https://arxiv.org/abs/2306.01798
Abstract:
This study applies Activity Theory to investigate how English as a foreign language (EFL) students prompt generative artificial intelligence (AI) tools during short story writing. Sixty-seven Hong Kong secondary school students created generative-AI tools using open-source language models and wrote short stories with them. The study collected and analyzed the students' generative-AI tools, short stories, and written reflections on their conditions or purposes for prompting. The research identified three main themes regarding the purposes for which students prompt generative-AI tools during short story writing: a lack of awareness of purposes, overcoming writer's block, and developing, expanding, and improving the story. The study also identified common characteristics of students' activity systems, including the sophistication of their generative-AI tools, the quality of their stories, and their school's overall academic achievement level, for their prompting of generative-AI tools for the three purposes during short story writing. The study's findings suggest that teachers should be aware of students' purposes for prompting generative-AI tools to provide tailored instructions and scaffolded guidance. The findings may also help designers provide differentiated instructions for users at various levels of story development when using a generative-AI tool.
Summary Notes
How AI Helps EFL Students Improve Story Writing: Insights from Activity Theory
In today's digital era, artificial intelligence (AI) is transforming many aspects of life, including education.
For students learning English as a Foreign Language (EFL), AI tools like ChatGPT offer a unique support system for storytelling, helping them overcome language and experience barriers.
A detailed study using Activity Theory gives us a closer look at how these students use AI to enhance their story writing skills.
Understanding Activity Theory
Activity Theory (AT) serves as a powerful tool to analyze EFL students' use of AI in writing. It helps us understand the relationship between the learners, the AI tools, and the surrounding cultural and educational environment.
AT focuses on how community rules and the division of labor influence the achievement of goals, which is key to understanding the socio-cultural impacts on learning with AI.
Research Methods
The study focused on 67 EFL students from Hong Kong secondary schools, introducing them to AI writing tools through workshops. Data was gathered mainly through questionnaires and analyzed to identify common themes in how students used AI for storytelling.
Key Findings from the Study:
- Understanding of AI Tool Use: Some students were not fully aware of when and how to use AI effectively in their writing.
- Tackling Writer’s Block: AI tools proved to be a significant help for many students in generating ideas and overcoming creative blocks.
- Enhancing Story Development: A noticeable number of students used AI to either expand on their stories or improve their narratives, showing a deeper understanding of AI's capabilities.
Study Insights
The research revealed diverse ways EFL students use AI in storytelling, influenced by their understanding and the tools they use.
These findings stress the need for targeted teaching approaches to fully realize AI's educational benefits. They also highlight the importance of providing students with sufficient knowledge in language and technology to creatively use AI.
Analysis of Activity Systems
The study showed that students' ability to use AI tools effectively varied, which affected the quality of their stories.
For example, students who used AI to overcome writer’s block often produced better stories and demonstrated a more skilled use of the technology.
Implications and Future Directions
Applying Activity Theory to examine AI in EFL storytelling offers valuable insights into the socio-cultural factors affecting technology use in education.
Pedagogically, this suggests that customizing teaching to fit students' specific needs can significantly improve learning outcomes. These findings also help in designing better AI tools and teaching methods tailored to diverse learner needs.
Study Limitations
The study's limited sample size and data collection methods are its main constraints. Future research should include larger groups and diverse data gathering techniques to provide a fuller picture of AI's role in education, especially for language learning and creative writing.
Conclusion
Incorporating AI tools into EFL learning presents a promising path for enhancing storytelling skills. This study, through Activity Theory, uncovers the intricate ways students interact with AI in their writing process.
By aligning educational support with EFL learners' specific situations, educators can make the most out of AI in education, leading to innovative and effective learning experiences.
How Athina AI can help
Athina AI is a full-stack LLM observability and evaluation platform for LLM developers to monitor, evaluate and manage their models
Written by
