How can hybrid AI-based chatbot systems enhance automated student inquiry processing and lead qualification for English Language schools in Ireland currently dependent on third party enrolment intermediaries?

Rocha Berthely, Erika (2025) How can hybrid AI-based chatbot systems enhance automated student inquiry processing and lead qualification for English Language schools in Ireland currently dependent on third party enrolment intermediaries? Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (4MB) | Preview

Abstract

This research presents the design, implementation, and evaluation of a hybrid AI-based chatbot system developed in Python to support direct enrolment in ILEP-registered English language schools in Ireland. The system combines machine Natural Language Processing, intent classification using TF-IDF vectorisation (1000 features, ngram_range=(1,2)) and Logistic Regression with custom rule-based response generation, ensuring both intelligent language understanding and regulatory compliance.

During the research, the three-stage data augmentation strategy, combining institutional emails, public datasets, and ChatGPT-4 synthetic generation, produced a balanced dataset of 445 annotated messages across five intent categories. The complete system implementation included: a custom preprocessing pipeline with text normalisation, an intent classification module achieving 84.5% accuracy and perfect qualified lead detection (F1: 1.00), a template-based response engine with 100% compliance for immigration queries, and a functional interface deployed via Gradio.

The performance evaluation demonstrates the system's effectiveness for conversion optimisation and regulatory compliance, supporting Ireland's digital transformation goals in the education sector. These types of solutions are part of the trend of making AI greener, more accessible, and more explanatory, which is great for projects with limited resources or that need transparency.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jameel Syed, Muslim UNSPECIFIED
Subjects:	L Education > L Education (General) Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Ciara O'Brien
Date Deposited:	24 Jun 2026 11:37
Last Modified:	24 Jun 2026 11:37
URI:	https://norma.ncirl.ie/id/eprint/9403

Actions (login required)

View Item