Ph.D. Student
School of Computer and Communication Sciences
École Polytechnique Fédérale de Lausanne (EPFL)
Postal Address
BC 145 (Bâtiment BC)
Station 14, CH-1015 Lausanne, Switzerland
Tel: +41 21 69 3127
Email: ekaterina dot svikhnushina at epfl dot ch
Research Interests
Human-Computer Interaction, User Experience Research, Natural Language Processing, Dialogue Generation, Discourse Analysis, Data Mining, Machine Learning, Human Computation
About My Research
My research lies at the intersection of HCI and AI fields with a specific focus on open-domain conversational agents, also known as chatbots. I follow a user-centered approach to understand which qualities are essential for such agents to deliver compelling user experience and how to evaluate them. In my work, I pay particular attention to theoretical conceptualization, experimental design, and evaluation. While my research mainly concerns the applications in computational linguistics, it is largely inspired by findings in psychology, psycholinguistics, and social sciences, which prompts many exciting interdisciplinary projects.
Education
- Ph.D. in Computer Science. École Polytechnique Fédérale de Lausanne (EPFL). September 2017 – Present
- M.Sc. and B.Sc. in Applied Mathematics and Physics. Moscow Institute of Physics and Technology, State University (MIPT). 2012 – 2018
Publications
- Ekaterina Svikhnushina, Marcel Schellenberg, Anna K Niedbala, Iva Barišić, and Jeremy N Miles. 2023. Expectation vs Reality in Users’ Willingness to Delegate to Digital Assistants. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA 2023). [access]
- Ekaterina Svikhnushina, Anastasiia Filippova, and Pearl Pu. 2022. iEval: Interactive Evaluation Framework for Open-Domain Empathetic Chatbots. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2022). [access]
- Ekaterina Svikhnushina, Iuliana Voinea, Anuradha Welivita, and Pearl Pu. 2022. A Taxonomy of Empathetic Questions in Social Dialogs. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2952–2973, Dublin, Ireland. Association for Computational Linguistics. [access]
- Ekaterina Svikhnushina and Pearl Pu. 2022. PEACE: a Model of Key Social and Emotional Qualities of Conversational Chatbots. In ACM Transactions on Interactive Intelligent Systems (April 2022). DOI: https://doi.org/10.1145/3531064 [access]
- Ekaterina Svikhnushina, Alexandru Placinta and Pearl Pu. User Expectations of Conversational Chatbots Based on Online Reviews. In Proceedings of the 2021 ACM Designing Interactive Systems Conference (DIS ’21). DOI: https://doi.org/10.1145/3461778.3462125 [access]
- Ekaterina Svikhnushina and Pearl Pu. Key Qualities of Conversational Chatbots – the PEACE Model. In 26th International Conference on Intelligent User Interfaces (IUI ’21). DOI: https://doi.org/10.1145/3397481.3450643 [access][video]
- Yubo Xie, Ekaterina Svikhnushina and Pearl Pu. A Multi-Turn Emotionally Engaging Dialog Model. In Companion Proceedings of the 25th International Conference on Intelligent User Interfaces: 2nd workshop on user-aware conversational agents (user2agent), 2020. [access]