Professor Irena Spasic

Professor Irena Spasic

Director of Research and Deputy Head of School

School of Computer Science and Informatics

I am a Professor in the School of Computer Science & Informatics at Cardiff University, where I am the Director of Research and a Deputy Head of School. I am a member of the Data & Knowledge Engineering group and the leader of the Text & Data Mining theme.

The main focus of my academic career has been to establish excellence in research related to text mining, which is the key to gaining knowledge for significant interventions and decision making in the context of big data. This makes it indispensible to other disciplines and has led to deep interdisciplinary collaboration which has been highly successful, leading to impact beyond computer science and informatics as well as developments in my home discipline. In particular, I have made contributions in areas of text classification, information extraction, term recognition and sentiment analysis.

I was awarded a PhD in 2004 for my work on the use of machine learning for terminological processing in biomedical literature. Prior to this post, I worked in the Manchester Institute of Biotechnology, an interfaculty initiative specifically designed to foster a scientific culture in which there are no barriers between the disciplines, thus ensuring that the widest possible range of expertise and techniques can be brought to bear on important bioscience problems. I joined Cardiff University in 2010 as a Lecturer. I have since developed active collaboration with the School of Healthcare Sciences (TRAK, KneeTex), the School of Social Sciences (crime and security) and, most recently, the School of English, Communication & Philosophy (CorCenCC).

CMT207: Information modelling and database systems (postgraduate)

Areas of scientific interest and research include:

  • Text mining: information extraction, term recognition, named entity recognition, sentiment analysis, text classification, information retrieval, language resources
  • Knowledge representation: development, application & standardisation of ontologies
  • Machine learning: feature engineering, case-based reasoning, naive Bayesian learning, support vector machines, genetic algorithms, genetic programming
  • Information management: data modelling, data mining, relational and XML databases, user interface development
  • Application areas: healthcare, life sciences, social sciences & social media

Research Supervision

  • Vigneshwaran Muralidaran (PhD, 2017-present): natural language processing, corpus linguistics
  • Steven Neale (PDRA, 2016-present): natural language processing, corpus linguistics, crowdsourcing
  • David Owen (RA/PhD, 2016-present): text mining, ontologies, health informatics
  • Lowri Williams (PhD, 2013-present): text mining, sentiment analysis, language resources
  • David Rogers (RA/PhD, 2012-present): text mining, sentiment analysis, social media
  • Bathilde Ambroise (PhD, 2012-2016, submitted): text mining, genomics, bioinformatics