I am a Senior Lecturer (Associate Professor) at Cardiff University and Social Computing research priority area lead in the School of Computer Science & Informatics’ Complex Systems research group. I have developed a reputation for data-driven, innovative, and interdisciplinary research that broadly contributes to the growing field of Data Science, working closely with the Cardiff School of Social Sciences and School of Engineering. I am an applied computer scientist with a principal focus on data and computational methods to improve understanding, operations and decision making outside of academia, while contributing to the academic fields of Social ComputingWeb Science and Cybersecurity.

These three fields are integrated within my research through the  analysis and understanding of Web-enabled human and software behaviour, with a particular interest in emerging and future risks posed to civil society, business (economies) and governments. I achieve this using computational methods such as machine learning and statistical data modelling, and interaction and behaviour mining, opinion mining and sentiment analysis to derive key features of interest.

My research outcomes, which include more than 50 academic articles – stemming from funded research projects worth over £7.2million, are organised and disseminated via the Social Data Science Lab, within which I am a director and the computational lead. The Lab’s core funding comes from a £450k ESRC grant and it forms part of the £64m ‘Big Data Network’. Core funding runs between 2017 and 2020, during which time the Lab will host 3 post-doctoral researchers and 9 PhD students, all studying topics related to Risk, Safety & Human/Cybersecurity.

ACM Keywords: Security and Protection; Human-centered computing; Modeling structured, textual and multimedia data; Data mining; Machine learning

Social Computing & Web Science

My contribution to Social Computing and Web Science has been developed through the creation of the ESRC/JISC-funded Collaborative Online Social Media Observatory (COSMOS) programme of research, which I pioneered with colleagues between 2012 and 2015. I was a co-founder of COSMOS and have captured more than £2.16 million over 13 projects to conduct research into online human and software behaviour and interaction, with the aim of developing new computational and statistical models and algorithms to measure emerging and future risks posed to public and economic security, safety and wellbeing.

COSMOS was recognised by the RCUK Global Uncertainties programme and investigated several research problems using data from online microblogs and social networks (e.g. Twitter), administrative sources (e.g. police crime data) and curated data sources (e.g. Office of National Statistics data). Examples include:

  • real-time and historical identification of social tension indicators;
  • understanding the propagation of antagonistic and offensive content;
  • spread of misinformation and rumour;
  • crime detection and prediction over time;
  • suicidal ideation and contagion.

Examples of the research outputs include:

  • Classifying and measuring propagation of human emotive reaction (particularly antagonistic and offensive sentiment) in online social networks (e.g. Twitter) following events of national interest;

Burnap, P. and Williams, M. (2015) ‘Cyber Hate Speech on Twitter: An Application of Machine Classification and Statistical Modeling for Policy and Decision Making’, Policy & Internet. Vol. 7:2 (available online here)

Burnap, P., Williams, M.L., Sloan, L., Rana, O., Housley, W., Edwards, A., Knight, V., Procter, R. and Voss, A. (2014), ‘Tweeting the Terror: Modelling the Social Media Reaction to the Woolwich Terrorist Attack’, Social Network Analysis and Mining. Vol 4:1 (available online here)

Burnap, P., Rana, O., Avis, N., Williams, M., Housley, W., Edwards, A., Morgan, J and Sloan, L. (2013) ‘Detecting Tension in Online Communities with Computational Twitter Analysis’, Technological Forecasting and Social Change. Vol 52 (available online here)

  • Detection of disruptive events (e.g. protests), misinformation (e.g. rumour), and crime, using streamed media (e.g. Twitter) – and how to formalize, summarize and share intelligence to minimize impact;

Alsaedi, N., Burnap, P. and Rana, O. (2015) ‘Identifying Disruptive Events from Social Media to Enhance Situational Awareness’, Proceedings of IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2015), presented at International Symposium on Foundations of Open Source Intelligence and Security Informatics (FOSINT 2015) (collocated event). Aug 26 – 27, Paris, France

Alsaedi, N., Burnap, P. and Rana, O. (2014) ‘A Combined Classification-Clustering Framework for Identifying Disruptive Events’, Proceedings of 7th ASE International Conference on Social Computing (SocialCom 2014), May 27-31, Stanford, CA, USA (available online here)

Burnap, P., Pauran, N., Rana, O and Bowen, P. (2014) ‘Towards Real-time Probabilistic Risk Assessment by Sensing Disruptive Events from Streamed News Feeds’, Proceedings of the 8th IEEE International Conference on Complex, Intelligent and Software Intensive Systems (CISIS 2014), July 2-4, Birmingham UK (available online here)

  • Classifying and measuring propagation of suicidal communication in online social networks (e.g. Twitter);

Colombo, G., Burnap, P., Hodorog, A. and Scourfield, J. (2015) ‘Analysing the connectivity and communication of suicidal users on Twitter’, Computer Communications (in press – available online here)

Burnap, P., Colombo, G. and Scourfield, J. (2015) ‘Machine Classification and Analysis of Suicide-Related Communication on Twitter’, Proceedings of the 26th ACM Conference on Hypertext and Social Media (Hypertext 2015), 1 – 4 Sep 2105, Cyprus (available online here)

I was the programme chair of ACM WebSci 2015, and have previously served on the programme committees for conferences and workshops such as WWW, ICWSM, SocialCom and SMSociety. I sit on the editoral board for the International Journal of Computational Science and Engineering.


In the area of Cybersecurity, I have been awarded more than £2.4 million in grant funding, including a significant £1.2million investment by EPSRC in exploratory interdisciplinary research in Cybersecurity. I am leading a work package on this project that studies the behavior and propagation of malicious software behavior in online social networks (linking to my work in Social Computing & Web Science).

Furthermore, I am working with an all-Wales team of collaborators studying risk identification and sensing malicious behavior in industry control systems (SCADA) with Airbus Group. This research received a £1.2million grant from Welsh Government, the largest sum ever invested in Cybersecurity research through this funding route.

I sit on the programme committee for key security conferences such as FiCloud, COMPSAC, SCADA-CSR, as well as regularly reviewing for ‘Computers & Security’. On several occasions I have spoken on the topic of Cyber Security and risk during programmes on BBC Radio Wales.

Examples of the research outputs include:

  • Classification and prediction of malicious software (malware) behaviour – and how to summarize and quantify risk metrics

Burnap, P., Javed, A., Rana, O.F. and Awan, M.S. (2015) ‘Real-time Classification of Malicious URLs on Twitter using Machine Activity Data’, Proceedings of IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2015), presented at International Symposium on Foundations of Open Source Intelligence and Security Informatics (FOSINT 2015) (collocated event). Aug 26 – 27, Paris, France (available online here)

Awan, M.S.K., Burnap, P. and Rana, O.F. (2015) ‘Estimating Risk Boundaries for Persistent and Stealthy Cyber-Attacks’, Proceedings of  ‘SafeConfig 2015: Automated Decision Making for Active Cyber Defense’. October 12-16, Denver, CO, US (available online here)

  • Theoretical and empirical frameworks for measuring and quantifying network security risk

Awan, M.S.K., Burnap, P., and Rana, O. ‘Identifying Cyber Risk Hotspots: A Framework for Measuring Temporal Variance in Computer Network Risk’, Computers & Security (in press)

Cherdantseva, Y., Burnap P., Blyth, A., Eden, P., Jones, K., Soulsby, H., Stoddart, K. (2016) ‘A Review of cyber security risk assessment methods for SCADA systems’, Computers & Security. Vol. 56, pp. 1-27. Available online here

Awan, M.S.K., Burnap, P. and Rana, O.F. (2015) ‘An Empirical Risk Management Framework for Monitoring Network Security’, Proceedings of 13th IEEE Conference on Autonomic and Secure Computing (DASC 2015). October 28-28, Liverpool, UK

  • Risk of IP/privacy/reputation loss due to information sharing and storage in distributed and cloud environments – policy and technology to reduce risk

Burnap, P.; Spasić, I,; Gray, W.A.; Hilton, J.; Rana, O.F.; and Elwyn, G. “Protecting Patient Privacy in Distributed Collaborative Healthcare Environments by Retaining Access Control of Shared Information”, in 14th International Conference on Collaboration Technologies and Systems (CTS), 2012. Springer Best Paper Runner Up

Burnap, P. (2010) “Advanced Access Control in support of Distributed Collaborative Working and De-perimeterization”. Doctoral Thesis.

  • Infrastructure for distributed, collaborative and secure risk and intelligence information sharing

Burnap, P et. al. (2012) “Open Dependency Modeling (O-DM): Constructing a Data Model to Manage Risk and Build Trust between Inter-Dependent Enterprises”, The Open Group. Reference C133. US ISBN 1-937218-19-5. Nov 2012. 

These examples all have an impact to varying degrees on civil society (e.g. community safety and public order), business (e.g. financial, reputation loss) and government (e.g. responding to public reactions, economics of cyber attacks, crime reduction targets)

Other Relevant Projects

I recently led the development of an international standard on dependency modelling and sharing risk information, published by The Open Group, which provides guidance on how to develop risk models that take account of various technical and human factors in a single model, and make dependencies between factors explicit. The O-DM standard defines how to construct a data model to manage risk and build trust on organizational dependencies between enterprises, or between operational divisions in a large organization. The data model produced using the standard can be be underpinned by computational Bayesian Networks to inform decision makers and risk managers which of these factors are most critical, and can calculate how risk factor impact changes over time given new information. Technology to support the standard was funded by the Technology Strategy Board and is available under license. Contact me for more details.