In the talk, I use the careers of father-son duo Pan Shi’en 潘世恩 and Pan Zengying 潘曾瑩, who both held the elite jinshi degree, and had long and illustrious careers in the Qing government. Pan Shi’En is the gentleman in the portrait with the great beard.
There were some good questions from the audience after the talk, and some good conversations around the conference afterwards. People were interested in the Qing dataset, and the successful collaboration with scholars in a different field. Many people had different ideas for sourcing career path or other state data. As might be expected for a technical conference, people also picked up on the technical challenges: the idea of mining from logs of states, rather than events; other existing work such as the Composite State Machine Miner; possible improvements to the types of nets used as models; and connections to goal selection and other topics in AI.
Lastly, the paper received the Out of the Box Paper award for the main research track of the conference, and it was lovely to get this formal recognition from the community. I think there’s a lot of interesting followups from this research, with Qing career data, with other historical or sociological data sources, and with the technical problems of concurrent roles and mining models from states. Thanks to the Lee-Campbell Group at HKUST, the QUT Centre for Data Science and the QUT IS School helping fund the trip and present this work at the major process mining conference.
van Eck, M.L., Sidorova, N., van der Aalst, W.M.P (2016). Composite state machine miner: Discovering and exploring multi-perspective processes. BPM2016.
Burke, A., Leemans, S.J.J, Wynn, M.T., and Campbell, C.D. (2023). ‘State Snapshot Process Discovery on Career Paths of Qing Dynasty Civil Servants’. ICPM2023.
Chen, B., Campbell, C.D., Ren, Y. and Lee, J. (2020). ‘Big Data for the Study of Qing Officialdom: The China Government Employee Database-Qing (CGED-Q),’ Journal of Chinese History, vol. 4, no. 2, pp. 431–460, Jul. 2020.