Computer Science Home | People | Degrees | Papers | Research | Events | Other FCMS Subjects
Projects | Publications | Theses | Laboratories
Theses In Progress

Rob Akscyn
Improving the productivity of knowledge work

Khadija Bahiss
Serious game to provide social skills training for people with Asperger Syndrome/High-functioning Autism

Felipe Bravo Marquez
Adaptive domain-focused sentiment analysis for social media streams

Carole Chang
Augmented memory system on mobile devices for brain injury

Akram Darwish
Morphological analysis for automatic Arabic text classification

Stephen Eichler
Implementing Internet black hole and topology analysis with large numbers of vantage points

Reynaldo Giganto
Using a controlled language for requirements document and generation user CASE specifications

Cameron Grout
Desktop environments in virtual reality and the usability impacts of an adjusting workspace paradigm

Paul Hunkin
Distributed operating systems for resource-constrained devices

Mumraiz Kasi
Semantic data integration in a large-scale sensor networks

Simon Laing
Image selection on a design context: the development of a sysem for image retrieval in support of graphic design

Mi Li
Parallel stream data mining with Graphics Processing Unit (GPU)

Paora Mato
Te rorohiko me te reo Māori: What is the role of computer technology within a Māori language regeneration strategy?

Paul Monigatti
Large-scale mico-management of domestic electricity consumption

Bryce Nemhauser
Spatial Hypermedia as a Programming Environment

Colin Pilbrow
Visualisation of specification models

Antti Puurula
Document enrichment of Wikipedia articles through machine learning

Michael Rinck
Connecting information: detecting and tracing object evolution

Fouad Shiblaq
Localisation provision: Arabic speakers' preference on para-lingual website-layout

Joris Suppers
Smart grids, the internet of energy, and energy use efficiency

Alan Yu Shyang Tan
Metalearning and the full model selection problem

John Thompson
Architectures for the parallel processing of very large scale digital libraries

Claire Timpany
How the typographic relationships between access structure features (headings) improve within document search and retrieval tasks

Emmanuel Turner
Adaptive user interfaces for the semantic web

Nicholas Vanderschantz
Improving children's learning with ebooks and digital libraries

Michael Walmsley
Automatic creation of dynamic second language reading texts

Min-Hsien (Sam) Weng
Efficient OpenCL implementation for computational Whiley programs

Mark Will
Reducing latency in data transfers

Theses
Theses In Progress >> PhD Theses
 
Akram Darwish - Morphological analysis for automatic Arabic text classification

Date Completed: in progress

Text classification aims to automatically assign the text to a predefined category based on linguistic features. Text preprocessing should be performed with very special care before carrying out the text classification task (eg, document conversion, stop words removal, stemming, etc). After applying the preprocessing routines texts typically are represented as vectors with n elements that denote the number of features which are mostly the text words. My project aims to exploit the morpho-syntactic information that can be extracted from the Arabic text to investigate their effects on the accuracy of the classifier in automatic Arabic text classification in different aspects. A new conflation method will be adopted using machine learning approaches as a backbone of this project.

  2007 FCMS. The University of Waikato - Te Whare Wananga o Waikato