evidoria

← Back to browse

Good practice Imported

Facing a Failing Manual E-Ticketing System, Nigeria's National Open University Builds an AI Chatbot for Student Complaints

Nigeria · Abuja · See the Nigeria profile · See the Abuja profile

Evidence: Descriptive / self-reported Top 81% 33/100 · Ask Evidence Copilot about this practice

After a survey of NOUN's roughly 500,000 distance-learning students found routine delays in its manual complaint system, researchers built an AI chatbot for student support; among the 579 who responded (29% of those invited), 64% called it extremely helpful.

~500,000
NOUN enrolled students
29% (579 of 2,000)
Survey response rate
64% (370 of 579)
Respondents rating chatbot 'extremely helpful'
Facing a Failing Manual E-Ticketing System, Nigeria's National Open University Builds an AI Chatbot for Student Complaints

Details

Maturity
Pilot
Promoter
National Open University of Nigeria (NOUN) & Cardiff Metropolitan University
Period
2024-2025
Keywords
distance education, student support, chatbot, natural language processing

Context

The National Open University of Nigeria (NOUN) has about 500,000 enrolled students who rely on a ticketing system for academic and administrative complaints since most never set foot on a campus; researchers from NOUN and Cardiff Metropolitan University documented that the existing e-ticketing system was operated manually, producing delayed responses and, in many cases, inadequate resolutions.

Activities

The team built an AI chatbot using the open-source ChatterBot framework in Python, backed by SQLite and served through a Flask web interface, designed to answer routine student queries automatically and route complex cases onward.

Results

They evaluated it through an online survey sent to 2,000 NOUN students; 579 responded (a 29% response rate), and of those, 370 (64%) rated the chatbot 'extremely helpful' in resolving their issues and complaints.

Conclusions

The reliance on a self-selected 29% survey response is a real limitation: it measures self-reported satisfaction among students motivated enough to complete a questionnaire, not independently verified ticket-resolution times or attrition data, and the paper does not report a full production rollout beyond the evaluation.

Implementation
Indicative cost
Low (< €50k)
Time to results
Short (< 1 year)
Staffing & skills
NOUN and Cardiff Metropolitan University research team

Conditions for success

  • Built on open-source components (ChatterBot, Flask, SQLite) to keep implementation cost low for a distance-learning institution
  • Designed to route complex cases onward to human staff rather than attempting to resolve everything automatically

Common failure modes

  • Evaluated via a self-selected 29% survey response rate rather than verified resolution-time or attrition data; no full production rollout reported beyond the evaluation

Replication kit

Reusable artefacts from this practice — as published by their sources.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful