This project proposes to study the evolution of topics at CHI, the largest conference venue in Human-Computer Interaction (HCI), using the topic evolution analysis framework proposed in [1]. With this method, topics are encoded into embeddings and topic evolution is analyzed via the geometrical motion of these topic embeddings.
| Academic Advisor | Dr. Jonas Oppenlaender |
| Topics | Meta-research, NLP |
| Degree | Master’s or a research project |
Technologies and Required Knowledge
- Python
- Data Science (basic scripting, data processing and data cleaning)
- NLP (in particular encoders for creating embeddings)
- Machine Learning (in particular support vector machines)
Related Work
1. Shengzhi Huang, Wei Lu, Qikai Cheng, Yong Huang, Fan Yi, Liang Zhu; A framework for demonstrating, forecasting, and explaining topic evolution by analyzing geometrical motion of topic embeddings. Quantitative Science Studies 2025; doi: https://doi.org/10.1162/qss_a_00344
2. Jonas Oppenlaender and Joonas Hämäläinen. 2023. Mapping the Challenges of HCI: An Application and Evaluation of ChatGPT for Mining Insights at Scale. http://arxiv.org/abs/2306.05036
3. Yong Liu, Jorge Goncalves, Denzil Ferreira, Bei Xiao, Simo Hosio, and Vassilis Kostakos. 2014. CHI 1994-2013: mapping two decades of intellectual progress through co-word analysis. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ’14). Association for Computing Machinery, New York, NY, USA, 3553–3562. https://doi.org/10.1145/2556288.2556969