University of Wollongong
Browse

A neural-net approach to user expertise modelling

Download (19.1 MB)
thesis
posted on 2024-11-11, 18:57 authored by Siu Cheong Leung
A neural network approach to low-level user modelling is described, in the context of text editing tasks using the Jove editor. Knowledge of a user's expertise is extracted automatically, based on their interaction with Jove over a two-week period. A multi-layered perceptron (MLP) classifier which uses rprop, or resilient backpropagation" learning and incorporate input data fuzzification is developed to classify users into one of five expertise levels. Classification into correct level is achieved in around 80% of cases, with misclassification being restricted to adjacent classes. The neuro-flizzy system is seen to outperform not only the binary classifier of Beale (1989), but also production rule and inductive expert systems developed especially for comparison purposes in this study.

History

Year

1996

Thesis type

  • Masters thesis

Faculty/School

Department of Computer Science

Language

English

Disclaimer

Unless otherwise indicated, the views expressed in this thesis are those of the author and do not necessarily represent the views of the University of Wollongong.

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC