Hyo Jin (Gina) Do
Research Scientist
Cambridge, MA, USA
Updates
I am excited to announce that I am now a Research Scientist at IBM Research!
Jan 9, 2023
I successfully defended my PhD!
Dec 12, 2022
Our paper about imperfect interventions and repair in a conversational agent got accepted to CSCW'23! Kudos to everyone who helped this project!
Oct 1, 2022
Excited to share that I am doing my summer internship at IBM Research in Cambridge, MA.
May 23, 2022
Our paper about the communication strategies of a conversational agent got accepted to CSCW'22! Big shout-out to my amazing collaborators!
Mar 30, 2022
I am a research scientist at IBM Research in Cambridge, MA, USA. I received my PhD in Computer Science at the University of Illinois Urbana-Champaign advised by Prof. Brian P. Bailey and co-advised by Prof. Karrie Karahalios. My research interests lie at the intersection of human-computer interaction (HCI) and artificial intelligence (AI), particularly in designing AI systems to improve user experience and mitigate biases.
Conversational Agents Facilitating Group Chat Discussions
Communication Strategies of a Conversational Agent
We evaluated five communication strategies that a conversational agent can use when promoting participation of under-contributing members in a small group synchronous chat discussion. Through an online study, we found that the agent sending messages specifying an individual through a private channel is the most preferred and effective way to deliver facilitation messages. [Do et al. 2022]
Imperfect Interventions and Resilience in a Conversational Agent
Two types of errors can occur when a conversational agent detects under-contributing members in a group chat discussion: 1) false positives happen when the agent falsely identifies a member as under-contributing, and 2) false negatives occur when the agent misses an under-contributing member. We designed a conversational repair strategy for the agent that sends a follow-up message to correct errors. We showed how different errors and the repair strategy affect user acceptance of the agent and group dynamics. [Do et al. 2023]
A Conversational Interface for Sexual Harassment Prevention Training
We designed a conversational interface that tells a vignette of sexual harassment from a first-person perspective. From a mixed-methods study, we found that learners experiencing the interface felt less overwhelmed with the content, more engaged with the situation, and more comfortable discussing the topic compared to reading the same contents online. [Do et al. 2021]
Hyo Jin Do, Ha-Kyung Kong, Pooja Tetali, Karrie Karahalios, Brian P Bailey, "Inform, Explain, or Control: Techniques to Adjust End-User Performance Expectations for a Conversational Agent Facilitating Group Chat Discussions", To Appear in the Proceedings of the ACM on Human-Computer Interaction (PACM HCI), CSCW, ACM, November, 2023.
Hyo Jin Do, Ha-Kyung Kong, Pooja Tetali, Jaewook Lee, Brian P Bailey, "To Err is AI: Imperfect Interventions and Repair in a Conversational Agent Facilitating Group Chat Discussions", Proceedings of the ACM on Human-Computer Interaction (PACM HCI), CSCW, ACM, November, 2023.
Hyo Jin Do, Ha-Kyung Kong, Jaewook Lee, Brian P Bailey, "How Should the Agent Communicate to the Group? Communication Strategies of a Conversational Agent in Group Chat Discussions", Proceedings of the ACM on Human-Computer Interaction (PACM HCI), CSCW, Taipei (Taiwan), ACM, November, 2022.
Hyo Jin Do, Seon Hye Yang, Boogyoung Choi, Wai-Tat Fu, Brian P Bailey, "Do You Have Time for a Quick Chat? Designing a Conversational Interface for Sexual Harassment Training", Proceedings of the 26th Annual Meeting of the Intelligent User Interfaces Community (IUI), TX (USA), ACM, April, 2021.
Wai-Tat Fu, Mingkun Gao, Hyo Jin Do, "Computational Methods for Socio-Computer Interaction", Computational Interaction (Chapter 16), Oxford University Press, 2018.
Mingkun Gao, Hyo Jin Do, Wai-Tat Fu, “Burst Your Bubble! An Intelligent System for Improving Awareness of Diverse Social Opinions”, Proceedings of the 23rd Annual Meeting of the Intelligent User Interfaces Community (IUI), Tokyo (Japan), ACM, March, 2018.
Hyo Jin Do, “Intelligent Interface for Seeing the World Through Different Lenses”, Proceedings of the 22nd Annual Meeting of the Intelligent User Interfaces Community (IUI), Cyprus, ACM, March, 2017.
Mingkun Gao, Hyo Jin Do, Wai-Tat Fu, “An Intelligent Interface for Organizing Online Opinions on Controversial Topics”, Proceedings of the 22nd Annual Meeting of the Intelligent User Interfaces Community (IUI), Cyprus, ACM, March, 2017.
Hyo Jin Do, Wai-Tat Fu, “Empathic Virtual Assistant for Healthcare Information with Positive Emotional Experience”, Presented at the International Conference on Healthcare Informatics (ICHI), Chicago, IL (USA), IEEE, October, 2016.
Hyo Jin Do, “Korean Twitter Emotion Classification and Application”, Master’s thesis, Korea Advanced Institute of Science and Technology (KAIST), 2016
Hyo Jin Do, Chae-Gyun Lim, and Ho-Jin Choi, “Analyzing Emotions in Twitter During a Crisis: A Case Study of the 2015 Middle East Respiratory Syndrome Outbreak in Korea”, Proceedings of the 3rd International Conference on Big Data and Smart Computing (BigComp), Hong Kong (China), IEEE, January, 2016.
Hyo Jin Do and Ho-Jin Choi, “Korean Twitter Emotion Classification Using Automatically Built Emotion Lexicons and Fine-grained Features”, Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (PACLIC), Shanghai (China), October, 2015.