Date
Publisher
arXiv
Designing Knowledge Management Systems (KMSs) for higher education requires addressing complex human-technology interactions, especially where staff turnover and changing roles create ongoing challenges for reusing knowledge. While advances in process mining and Generative AI enable new ways of designing features to support knowledge management, existing KMSs often overlook the realities of educators' workflows, leading to low adoption and limited impact. This paper presents findings from a two-year human-centred design study with 108 higher education teachers, focused on the iterative co-design and evaluation of GoldMind, a KMS supporting in-the-flow knowledge management during digital teaching tasks. Through three design-evaluation cycles, we examined how teachers interacted with the system and how their feedback informed successive refinements. Insights are synthesised across three themes: (1) Technology Lessons from user interaction data, (2) Design Considerations shaped by co-design and usability testing, and (3) Human Factors, including cognitive load and knowledge behaviours, analysed using Epistemic Network Analysis.
Study at a glance
- Question: How do educators interact with an iterative, teacher-centered knowledge management system designed for digital teaching tasks?
- Setting and data: A research-focused university, 2022 to 2024, involving 108 higher education teachers across faculties such as Medicine, Nursing and Health Sciences, and Information Technology.
- Method: Mixed methods across three iterative design cycles using co-design sessions, lab-based simulated teaching tasks, usability surveys, and interviews.
Why it matters
Higher education faces high staff turnover, yet existing knowledge management tools often overlook educators' real-world workflows. This creates persistent challenges for capturing institutional knowledge and causes low tool adoption.
Key findings
- In the final evaluation, teachers using GoldMind had a 60% lower failure rate and spent 44% less time searching for information compared to a baseline LLM chatbot.
- Across iterative evaluations, GoldMind reduced teachers' task completion duration and significantly reduced self-reported mental demand, effort, and frustration on cognitive load measures.
- Network analysis showed GoldMind's automated push recommendations prompted richer and more diverse knowledge exploration compared to the user-initiated querying observed with the baseline chatbot.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
