Chatbots in Blackboard – FAQs
1. How Does the Chatbot Work?
The chatbot in Blackboard works differently from a public chatbot like ChatGPT because it is designed to focus only on the course materials and data that it has access to, better ensuring its answers are relevant and accurate.
When someone asks the chatbot a question, it first goes through a pre-search phase. This is like a planning step where the chatbot figures out:
- What is the question (e.g., is it asking about course content, technical help, or something else?)?
- Where to look for the answer within the course materials
- What to do if the question is out of scope
Instead of searching the whole internet, the chatbot only looks at the information it’s connected to, like lecture notes, course quizzes, and other materials specific to the course. It will direct the student elsewhere if it can’t find the answer or the question isn’t about the course. This is provided through ‘hard coded’ escalation paths and would often, for example, mean re-directing to the Student Centre
The chatbot avoids making things up (so-called “hallucinations”) by focusing only on trusted course materials. It’s more thoughtful about giving accurate answers because it works within clear limits, unlike ChatGPT, which can answer more broadly across any topic.
This system helps students get the right information quickly while keeping the learning experience reliable and focused on their needs.
2. How accurate and reliable is the chatbot’s information?
All information used comes solely from the course. The assistant only answers information about the course content and course information using a combination of large language models to compile answers. So, if the course content is accurate then the chatbot responses should be too. Hallucinations are minimised by forcing the chatbot to only generate answers from the course content,
3. Can the chatbot understand and address complex or nuanced questions?
Chatbots are good at handling straightforward queries based on the course content. However, they may struggle with more complex or nuanced questions that require deep human insight. It’s important that students use the chatbot as a supplementary tool and not a replacement for human educators.
4. Will the chatbot reduce face-to-face interactions between students and educators?
Chatbots are good at handling straightforward queries based on the course content. However, they may struggle with more complex or nuanced questions that require deep human insight. It’s important that students use the chatbot as a supplementary tool and not a replacement for human educators.
5. Is there a risk of students and educators becoming overly dependent on the chatbot?
While chatbots can be incredibly helpful, it’s important to balance their use with traditional learning methods to ensure students develop critical thinking and problem-solving skills. Educators should encourage students to use the chatbot as a resource rather than a crutch.
6. How does the chatbot handle biases in its responses?
All responses come from course data; hence, they are as biased as the course data.It’s essential to balance their use with traditional learning methods to ensure students develop critical thinking and problem-solving skills. Educators should encourage students to use the chatbot as a resource rather than a crutch.
7. What measures are in place to ensure students use the chatbot ethically and do not plagiarise?
Clear guidelines on the ethical use of the chatbot should be provided to students. Educators can monitor the use of the chatbot and take necessary actions if instances of plagiarism are detected.
8. How often is the chatbot updated to maintain the accuracy of the information provided?
The chatbot undergoes regular weekly updates and continuous learning to remain accurate and relevant. Users’ feedback helps identify areas for improvement, which are then addressed in subsequent updates.
9. Can the chatbot handle sudden spikes in user queries during peak times?
The chatbot is designed to handle multiple queries simultaneously. However, during peak times, response times may vary. It’s important to manage user expectations and provide support through other channels when necessary.
Please email additional questions to:g.saunders@westminster.ac.uk
Chatbots can enhance learning by providing information and support, but their use should be balanced with traditional methods for a comprehensive educational experience.