evidoria

← Back to browse

Good practice Imported

Botsify-Built AI Chatbot Answers Admissions Questions with 91% Accuracy — Princess Nourah Bint Abdulrahman University

Saudi Arabia · Riyadh · See the Saudi Arabia profile · See the Riyadh profile

Evidence: Observational / pre–post Top 95% 20/100 · Ask Evidence Copilot about this practice

Researchers at Princess Nourah Bint Abdulrahman University built a Botsify-based chatbot to answer prospective students' admissions questions around the clock, reaching 91% accuracy on a confusion-matrix test and a 76.6 usability score from 22 student testers.

91%
Chatbot response accuracy (confusion matrix)
76.6
Chatbot Usability Questionnaire (CUQ) score (2023)
22 of 42 users completed the CUQ
Survey respondents / initial users

Details

Maturity
Pilot
Promoter
Princess Nourah Bint Abdulrahman University
Period
2023
Keywords
higher education admissions, AI chatbot, student services

Context

Prospective-student inquiries about admissions, fees and programmes at Saudi universities have traditionally relied on phone and in-person counselling available only during office hours, creating bottlenecks as visitor volume grows.

Objectives

Researchers at Princess Nourah Bint Abdulrahman University's College of Computer and Information Sciences set out to build an intelligent chatbot on the Botsify platform that could automatically answer frequently asked admissions questions for prospective students around the clock.

Activities

Of 42 postgraduate students who accessed the chatbot, 22 completed the Chatbot Usability Questionnaire (CUQ), and the researchers ran a Confusion Matrix analysis of the chatbot's responses to assess accuracy.

Results

The chatbot achieved 91% accuracy on the Confusion Matrix analysis, and the 22 CUQ respondents returned an average usability score of 76.6, indicating reasonable user satisfaction.

Conclusions

The study, published in the International Journal of Information and Education Technology in September 2023, draws on a small pilot cohort of 42 initial users and 22 survey respondents, so results should be read as an early-stage proof of concept rather than evidence of impact at scale.

Implementation
Indicative cost
Low (< €50k)
Time to results
Short (< 1 year)
Staffing & skills
Researchers/developers at the College of Computer and Information Sciences building and configuring the Botsify-based chatbot, Student testers completing the Chatbot Usability Questionnaire

Conditions for success

  • A structured FAQ knowledge base covering admissions, fees and programme questions for the chatbot to draw on
  • Usability testing with real prospective/postgraduate students (CUQ) alongside technical accuracy testing (Confusion Matrix)

Common failure modes

  • The small pilot cohort (42 users, 22 survey respondents) limits confidence that results generalise at scale
  • No comparison against existing phone/in-person admissions counselling was reported

Commonly funded by

National / regional programmes Own resources / municipal budget

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

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.

Similar practices you may find useful