My research crosses a number of different disciplines. I was trained as a theoretical physicist, and completed my PhD on "Modelling and Generating Complex Emergent Behaviour". My thesis sought to understand a concept I termed high end complexity, where the contextuality of a system's responses to measurement and modelling mean that we struggle to understand its behavior using reductive modelling and other methods commonly employed by science. 

Since then I have worked in areas spanning Information Retrieval, Cognitive Science, Social Psychology, Educational Data Science, and Learning Analytics. It is lucky that the concept of AI in education is now of interest to so many people, or I could well have been unemployed and just bumming around the world by now (like I originally intended when I started my PhD). 

If you pay attention you can see some themes that emerge from my research, which has spanned many different fields, collaborations and topics of interest. 

I am interested in recruiting students and postdocs to work on any of the topics listed below. If you would like to come and work with me then send me an email with a 2 page proposal discussing what you are interested in doing... If it covers, combines or even extends any of the topics below then I am likely to be quite interested. If you do a good job synthesising concepts and writing a nice proposal then I will be even more intrigued... If that is the case then we can have some discussions where I help you to refine and polish your idea. This will help me to see if we are a good match for working together and help me to understand I will be able to help you with your research ambitions :) 

Data interoperability to support lifelong learning

• Kitto, K. (2024). Will a Skills Passport ever get me through the lifelong learning border?: Two critical challenges facing personalised user models for lifelong learning. In Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization (UMAP '24). Association for Computing Machinery, New York, NY, USA, 132–142. https://doi.org/10.1145/3627043.3659564
• Poquet, O., Kitto, K., Jovanovic, J., Siemens, G., Dawson, S., Markauskaite, L. (2021). Transitions through Lifelong Learning: Implications for Learning Analytics. Computers & Education: Artificial Intelligence. pp. 100039–100039, https://doi.org/10.1016/j.caeai.2021.100039
• Kitto, K., Sarathy, N., Gromov, A., Liu, M., Musial, K., Buckingham Shum, S. (2020). Towards Skills-based Curriculum Analytics: Can we automate the recognition of prior learning? In Proceedings of the Tenth International Conference on Learning Analytics & Knowledge (LAK '20). Association for Computing Machinery, New York, NY, USA, 171–180. https://doi.org/10.1145/3375462.3375526
• Kitto, K., Whitmer, J., Silvers, A., Webb, M., (2020). Creating data for learning analytics ecosystems. SoLAR position paper. Society for Learning Analytics (SoLAR). Available at: https://www.solaresearch.org/publications/position-papers/
• Kitto, K., Lupton, M. Bruza, P., Mallett, D., Banks, J., Dawson, S., Gašević, D., Buckingham Shum, S., Pardo, A., Siemens, G. (2020). Learning analytics beyond the LMS : enabling connected learning via open source analytics in “the wild”: final report. Dept of Education, Skills and Employment, Available at: https://ltr.edu.au/resources/ID14-3821_Kitto_Report_2020.pdf 

AI and Data literacy

• Kitto, K., Hicks, B., & Buckingham Shum, S. (2023). Using causal models to bridge the divide between big data and educational theory. British Journal of Educational Technology, 54:1095–1124 https://doi.org/10.1111/bjet.13321
• Kitto, K., Knight, S., (2019). Practical Ethics for Building Learning Analytics. British Journal of Educational Technology, 50(6), 2855-2870. https://doi.org/10.1111/bjet.12868
• Cetindamar Kozanoglu, D., Kitto, K., Wu, M., Zhang, Y., Abedin, B. & Knight, S. (2022), Explicating AI literacy of employees at digital workplaces, IEEE Transactions on Engineering Management, pp. 1-28. https://doi.org/10.1109/TEM.2021.3138503
• Hicks, B., Kitto, K., Payne, L., Buckingham Shum, S. (2022). Thinking with causal models: A visual formalism for collaboratively crafting assumptions. In LAK22: 12th International Learning Analytics and Knowledge Conference (LAK22). Association for Computing Machinery, New York, NY, USA, 250–259. https://doi.org/10.1145/3506860.3506899
• Kitto, K., Williams, C., Aldermann, L. (2019). Beyond Average: Contemporary statistical techniques for analysing student evaluations of teaching. Assessment and Evaluation in Higher Education. 44 (3), 338-360. https://doi.org/10.1080/02602938.2018.1506909
• Kitto, K., Buckingham Shum, S., Gibson, A. (2018). Embracing imperfection in learning analytics. In Proceedings of the 8th International Conference on Learning Analytics and Knowledge (LAK '18). ACM, New York, NY, USA, 451-460.  https://doi.org/10.1145/3170358.3170413   

Learner metacognition and self-reflection

• Buckingham Shum, S., Littlejohn, A., Kitto, K., Crick, R. (2022). Framing Professional Learning Analytics as Reframing Oneself. IEEE Transactions on Learning Technologies. 15(5), 634-649, https://doi.org/10.1109/TLT.2022.3190055
• Kay, J., Bartimore, K., Kitto, K., Kummerfeld, B., Liu, D., Reimann, P. (2022). Enhancing learning by Open Learner Model (OLM) driven data design, Computers and Education: Artificial Intelligence. 3, 100069, https://doi.org/10.1016/j.caeai.2022.100069
• Fernandez-Nieto, G., Echeverria, V., Buckingham Shum, S., Mangaroska, K., Kitto, K., Palominos, E., Axisa C., Martinez-Maldonado R. (2021). Storytelling with Learner Data: Guiding Student Reflection on Multimodal Team Data, IEEE Transactions on Learning Technologies. 14(5), 695-708, https://doi.org/10.1109/TLT.2021.3131842
• Liu, M., Kitto, K., & Buckingham Shum, S. B. (2021). Combining factor analysis with writing analytics for the formative assessment of written reflection. Computers in Human Behavior, 120, 106733. https://doi.org/10.1016/j.chb.2021.106733
• Kitto, K., Lupton, M., Davis, K., Waters, Z. (2017). Designing for Student Facing Learning Analytics, Australasian Journal of Educational Technology, 33(5), 152-168. https://doi.org/10.14742/ajet.3607
• Gibson, A., Kitto, K., Bruza, P. (2016). Towards the Discovery of Learner Metacognition From Reflective Writing. Journal of Learning Analytics, 3(2), 22-36. https://doi.org/10.18608/jla.2016.32.3

How to understand and change the behavior of complex and contextual systems (in general)

• Kitto, K., & Gibson, A., (2024). Places to Intervene in Complex Learning Systems. In Proceedings of the 14th Learning Analytics and Knowledge Conference (LAK '24). Association for Computing Machinery, New York, NY, USA, 929–935. https://doi.org/10.1145/3636555.3636938   
• Kitto, K., (2014). A Contextualised General Systems Theory, Systems, 2(4), 541-565. 
  https://doi.org/10.3390/systems2040541
• Kitto, K. (2008). High End Complexity, International Journal of General Systems, 37(6):689-714. https://doi.org/10.1080/03081070701524232

Quantum Cognition (one way to understand and model contextual cognitive systems)

• Widdows, D., Kitto, K., Cohen, T. (2021). Quantum Mathematics in Artificial Intelligence, Journal of Artificial Intelligence Research, 72, 1307-1341, https://doi.org/10.1613/jair.1.12702
• Aliakbarzadeh, M., Kitto, K. (2021). Is contextuality about the identity of random variables?. Foundations of Physics, 51(1), 1-13. https://doi.org/10.1007/s10701-021-00402-7
• Aliakbarzadeh, M., Kitto, K. (2018). Preparation and measurement in quantum memory models. Journal of Mathematical Psychology, 83, 24-34. https://doi.org/10.1016/j.jmp.2018.03.002  
• Bruza, P. D., Kitto, K., Ramm, B., Sitbon, L. (2015). A probabilistic framework for analysing the compositionality of conceptual combinations.  Journal of Mathematical Psychology, 67, 26-38. https://doi.org/10.1016/j.jmp.2015.06.002
• Nelson, D., Kitto, K., Galea, D., McEvoy, C., Bruza, P.D. (2013). How Activation, Entanglement, and Searching a Semantic Network Contribute to Event Memory, Memory & Cognition, 41(6):717-819. https://doi.org/10.3758/s13421-013-0312-y
• Kitto, K., Boschetti, F. (2013). Attitudes, Ideologies and Self-Organisation: Information Load Minimisation in Multi-Agent Decision Making. Advances in Complex Systems, 16:13500. https://doi.org/10.1142/S021952591350029X
• Bruza, P.D., Kitto, K., Nelson, D., McEvoy, C. (2009). Is there something quantum-like about the human mental lexicon?, Journal of Mathematical Psychology, 53:362-377. https://doi.org/10.1016/j.jmp.2009.04.004

I have had some successes in asking people to fund my work (I have also had lots of failures). 

In total, I have received over AUD$1.5M/NOK10M  in externally funded competitive projects and more than AUD$5M/NOK35M in internally funded competitive projects over the lifetime of my career. Here are some of my favorite projects...

Artificial intelligence in education: Democratising policy 

Australian Research Council (DP240100602) 2024-2027, AU$500K (NOK3.28M)

Kalervo Gulso, Greg Thompson, Marcia McKenzie, Sam Sellar, Kirsty Kitto, Simon Knight, José-Miguel Bello y Villarino.

SUMMARY: The rapid introduction of AI into education is occurring with inadequate policy support. Additionally, there is a lack of stakeholder input into decisions about the use of AI in education. Utilising social science and data science approaches, this project aims to democratise policy about AI in education by building tools to monitor policies, and developing collaborative policy making methods. The expected outcomes include publicly available policy resources to anticipate, and respond to, the role of AI in education, and participatory frameworks for policy making. The benefits include informed stakeholder engagement, and concrete policy recommendations that are globally relevant and adaptable to the Australian context.

Governing AI, education and equity together

James Martin Institute for Public Policy, 2024 AU$87K (NOK570K)

USyd: Kalervo Gulson, Teresa Swist, Jose-Miguel Bello Villarino UTS: Leslie Loble, Kirsty Kitto, Simon Knight 

SUMMARY: AI is proposed as a solution to address inequality related to the UN SDG #4 Quality Education. However, AI can also reinforce educational disadvantages. Policy makers need ways to ensure the use of AI addresses digital learning equity to enhance educational opportunities for students (by addressing differential access, usage, and outcomes). This project aims to develop collective policy making approaches across multiple scales in the NSW Department of Education to ensure that the opportunities/benefits of using AI to address educational disadvantage are realised, and to avoid embedding harms for vulnerable populations.

Enabling connected learning via open source analytics in the wild: learning analytics beyond the LMS 

Australian Office for Learning and Teaching (OLT) - Innovation and Development Scheme (ID14-3821) 2015-2017 AU$320K (NOK2.1M)

Kirsty Kitto (Lead Investigator), Mandy Lupton, John Banks, Dann Mallet, Peter Bruza, Shane Dawson, Dragan Gašević, Simon Buckingham Shum, Abelardo Pardo, George Siemens 

SUMMARY: This project developed the Connected Learning Analytics Toolkit, which uses the Experience API (xAPI) educational data specification enable students to sign up for tracking of their participation in specific learning activities using standard social media (e.g. Twitter, Youtube, Wordpress, Facebook, Trello, Github). Contextualised dashboards (e.g. SNA and Content Analysis) allow both students and instructors to learn about the data traces they leave and to develop better self-regulated learning practices. 

Generalized quantum models of complexity with application to cognitive systems

Kirsty Kitto (Lead Investigator, Australian Postdoctoral Fellowship), Peter Bruza 

Australian Research Council (DP1094974) 2010-2012 AU$270K (NOK1.77M)

SUMMARY: This project developed new methods for modelling complexity, with a particular focus upon contextual behaviour in cognitive systems. The probabilistic structure of quantum theory was used to represent an underlying cognitive state with reference a specific ‘measurement’ context. Agents in a social context, framing effects, word associations, memory and priming were all modelled using the approaches developed in this project.

Quantum Theory of Context Representation for Information Access and Retrieval 

Marie Curie International Research Staff Exchange Scheme (IRSES), QONTEXT (N° 247590) 2010-2013 EU208K+AU$15K (NOK2.5M) 

Massimo Melucci, Dawei Song, Di Buccio, Di Nunzio, Wang, Zhang, Piwowarski, Frommholz, Lalmas, S. Aerts, Hou, Liu, Yu, Sun, Dai, Song, Wang, Bruza, Kitto, Sitbon, Nie

SUMMARY: This staff exchange scheme facilitated the international collaboration of over 20 researchers and PhD students. The project developed a wide variety of new approaches to modelling context in information retrieval, generally with a focus upon modelling the cognitive processes of information seekers.