From Prompt to Dialogue: Blackboard AI Conversation Role-plays in Languages

Overview

Photo of Oscar Garcia Garcia Find out how Spanish Lecturer, Oscar Garcia Garcia, used role-play activities through Blackboard’s AI Conversation tool to support Intermediate and Advanced Spanish III classes, enhancing authentic conversational practice.

 

Objectives

• Facilitate interaction in Spanish in real-life contexts.
• Practise transferable skills such as negotiation and problem-solving.
• Reinforce and practise the content covered in class through activities.
• Trial the AI Conversation tool in Blackboard for language learning and share findings with colleagues teaching languages in the Department of Languages and Cultures (DLC).

Context

I wanted to trial Blackboard’s AI Conversation tool in two modules to provide students with a new interactive way to practice Spanish in the context of their course content. I chose the two Intermediate Spanish modules I convene, using role-plays based on day-to-day scenarios: a visit to the GP and a negotiation with a landlord/lady to rent a room. I trialled it in Advanced Spanish III with more complex conversations with a task identifying dialectal features and a debate on social media.

Implementation

The implementation of each activity started with identifying the most appropriate sessions in which to introduce it, ensuring alignment with the module content and appropriate timing. I designed each activity carefully, providing clear student instructions and a prompt for the AI with its role, with information on its level of Spanish and background (job, regional origin, age, personality). Before introducing it to my students, I conducted dry runs to test functionality and refine prompts where necessary. In class, I presented the activity and guided students so they could access it, complete it effectively, and understand how the AI Conversation tool works.

Students then completed each task. We did two activities in class: a doctor’s appointment role-play in Intermediate Spanish, and a task identifying dialectal features in Advanced Spanish III. Two other activities – a negotiation with a landlord/lady (Intermediate, scenario shown in the image below), and a debate about social media (Advanced III) – were set for homework.

After completing the two classroom activities, we discussed them; for instance, Intermediate Spanish students had to mention why the patient at the GP was feeling unwell and why they reached their conclusion.

I then proceeded to review their contributions to provide further feedback, draw conclusions, and redesign activities where necessary to improve their effectiveness for my use with future classes. For the two independently completed activities, the process was reversed: I first reviewed the students’ participation in the role plays and subsequently discussed them in class.

Screenshot of AI Conversation activity in Blackboard.

 

Impact

I believe the activities were successful as students engaged effectively with the AI Conversation tool and completed the tasks. The objectives were met, particularly in relation to practicing transferable skills such as negotiation and problem-solving, as well as reinforcing and consolidating classroom content and language skills. I also shared my findings at a departmental TEL event, where it was positively reviewed by colleagues, with a further session planned ti share more widely.

An unexpected outcome was that, although no reflections were required, some students still added brief comments on the usefulness of the activity and what they had learned, which has encouraged me to use the Reflection Question feature in the future in a more effective way.

Reflections

The activities were interactive, motivational and almost game-like, requiring students to solve problems individually or in small groups, or deal with everyday situations in real-life contexts using a language they were learning.They were well received by students and they were closely integrated with the course content. A key factor that made the activity successful was that I instructed the AI to use specific language levels: B1 for Intermediate Spanish and C1 for Advanced Spanish III, aligned with the levels of the respective modules students were studying. This allowed students to put into practice the topics and language, such as grammar and vocabulary, covered in class. I also completed the activity by previewing the chat several times to ensure it worked properly and the AI behaved as expected – I would advise doing this.

The two activities assigned as independent work beyond the classroom had a low completion rate. In the future, they could be carried out in class, or there should be a stronger emphasis on ensuring they are completed. I would also like to use the Reflection Question feature more effectively and clearly, as I consider it very useful for encouraging students to reflect on the activity and its objectives.

Follow up

Since these activities were carried out individually at different points during the academic year, I was able to refine the way I created prompts, making them increasingly concise. In the future, I would welcome the inclusion of voice recognition and pronunciation features within the tool, as these would provide significant benefits for language learning and the development of oral proficiency.


Further information

CQSD TEL guidance: AI Conversations

University of Derby: Enhancing student engagement with Blackboard’s AI Conversation Tool

 

ChatGPT: A conversational language study tool

ChatGPT: A conversational language study tool

 

By: Jackie Baines and Edward A. S. Ross, Department of Classics, School of Humanities, j.baines@reading.ac.uk and edward.ross@reading.ac.uk
classical Greek/Roman style columns on a classical ruin with a bright futuristic sky background
Photo by Yusuf Dündar on Unsplash

Overview

This project outlines the work undertaken in the Department of Classics to demystify generative artificial intelligence for ancient language staff and students over the 2023-2024 academic year.

Objectives

  • Codify and standardise methods for using conversational AI models (such as ChatGPT, Claude-2, and Google Bard) in ancient language classes.
  • Produce tested guiding phrase documents for students to copy and paste into conversational AI models so that their outputs are standardised to match course expectations.
  • Lead interactive testing sessions in all levels of ancient language classes (i.e. Latin and Ancient Greek) to test these documents and inform students about the ethical considerations for using generative AI.

Context

At the time when this project was instigated, there was a dramatic surge of generative AI development and use at a generally accessible level. This led to extreme anxiety among educators and students alike as to how these tools could impact the known models for teaching, learning, and assessment in classics and beyond. We sought to approach this issue ‘head on’ in order to contextualise the nature and value of generative AI tools for staff and students, dispelling any unwarranted preconceptions and informing them of necessary ethical considerations.

Implementation

  • Surveyed ancient language teaching staff about the necessary elements of their courses.
  • Led sessions with staff to develop the departmental AI guidelines and citation guide in Summer 2023.
  • Led AI ethics information sessions for all undergraduate and postgraduate students in the Department of Classics over the Autumn 2023 term.
  • Held survey sessions with all ancient language students studying Ancient Greek and Latin, gathering data on their views on generative AI before and after the information sessions, in Autumn 2023.
  • Hired three undergraduate research assistants to test guiding phrases on a variety of conversational AI tools to determine the effectiveness of the tools and guiding phrases for supporting various aspects of their ancient language learning.
  • Published the tested guiding phrases as a digital and physical pamphlet for staff and students to freely use in March 2024.
  • Recorded and published a series of tutorial videos on generative AI ethics and digital tools for Classics.
  • Carried out a follow-up survey in Spring 2024 with the same ancient language students that completed the Autumn 2023 survey to gauge the impact generative AI had on their studies over the 2023-2024 academic year.
  • Analysed and published survey data in two academic journal articles (one is currently in press) and on secure data repositories.

Impact

The initial intention for this project was to investigate how effective generative AI tools were for supporting ancient language teaching and learning, but our research and response from students led us to work more towards improving general AI literacy among humanities teachers and students. When we were giving our ethics presentations, teachers and students were shocked by the ethical considerations behind generative AI, especially the environmental and copyright implications, and as soon as they saw this and learned that their own work could be used to train these models, they were much more sceptical of using the tools. At the time of writing, the tutorial videos and guiding phrase pamphlet have been downloaded around 150 times each, and this continues to grow as we present our tutorials to future course groups.

Reflections

We found this work was successful in many ways, particularly through our collaboration with our undergraduate students. By working with our students, who are seeing large swaths of generative AI tools on a daily basis, we were able to get a wider perspective on the impact and use cases of these tools for ancient language teaching and learning. Any research into generative AI and teaching and learning should involve student-teacher collaboration. In some aspects, we were also interdisciplinary in our reach, making some presentations for the Modern Languages Department, but there is scope for many more interdisciplinary collaborations for this work. In the future, we intend to continue making ethics tutorials for ancient language students, and the materials developed during this TLEP-funded project will help us illustrate the current issues more effectively.

Links

Further reading

  • Ross, E. A. S., & Baines, J. (2024). Treading water: New data on the impact of AI ethics information sessions in classics and ancient language pedagogy. Journal of Classics Teaching25(50), 181–190. https://doi.org/10.1017/S2058631024000412