Skip to main content
 Luke Smallman

Luke Smallman

Research student, School of Mathematics

Room M/2.30, 21-23 Senghennydd Road, Cathays, Cardiff, CF24 4AG

I am a member of the statistics research group within Cardiff School of Mathematics. My area of expertise is dimension reduction, with applications to text mining. In particular, I have a focus on developing new methods for text data dimension reduction, and seeing them implemented on real data within Cardiff and Vale University Health Board and its Informatics department.

Research interests

My interests are primarily in the area of dimension reduction, with a particular focus on how it can be applied to enable better and faster text mining applications.


Over the last several years as a PhD student, I have tutored or led labs for the following modules within the School of Mathematics:

  • MA1500 - Introduction to Probability Theory
  • MA1501 - Statistical Inference
  • MA2501 - Programming and Statistics
  • MAT002 - Statistical Methods

I have also participated in the Maths Support service regularly, both in the drop-in sessions and providing one-on-one statistical support sessions.


Dimension reduction for text mining

Dimension reduction techniques from principal component analysis to sliced inverse regression and more have been very successfully applied to continuous data. My interests are in adapting and applying methods like these to work with the particular nature of text data in order to facilitate easier and computationally faster modelling and mining of text data. In particular, my PhD focuses on these methods and their applications to a healthcare dataset generously made available by Cardiff and Vale University Health Board

Funding source

Cardiff University School of Mathematics, and Cardiff and Vale University Health Board

Andreas Artemiou

Dr Andreas Artemiou

Deputy Director, Data Science Academy
Senior Lecturer in Statistics