Publications

A Humanoid Robot Dialogue System Architecture Targeting Patient Interview Tasks

Published in ROMAN '24, 2024

The project focuses on enhancing humanoid robots' performance in conducting patient interviews by developing a dialogue system architecture. Humanoid robots offer a unique advantage in utilizing verbal and behavioral cues during interviews. However, the human-like appearance can create expectations of human-level performance, leading to interaction quality degradation if not met. The project introduces a dialogue system architecture that includes a nested inner real-time control loop to enhance the robot's responsiveness based on the concept of "stance." This architecture also expands the dialogue state to monitor task progress and human engagement. Experiments with the proposed architecture demonstrate improved performance in terms of response timeliness and user impressions during patient interviews.

Recommended citation: Yifan SHEN*, Dingdong Liu, Yejin Bang, Ho Shu Chan, Rita Frieske, Hoo Choun CHUNG, Jay Patrick Monton Nieles, Tianjia ZHANG, Trung Kien Pham, Wai Yi Rosita CHENG, YINI FANG, Qifeng Chen, Pascale FUNG, Xiaojuan Ma, Bertram Emil Shi
Download Paper

Exploring Scaffolding Techniques for Agent-Administered Brief Cognitive Screening in Hospital Settings

Published in DIS '24 Companion, 2024

This study explores effective scaffolding strategies used by clinicians to assist in cognitive screening of hospitalized older patients, highlighting six key strategies identified through empirical research on the Abbreviated Mental Test (AMT) process, with implications for designing conversational agents in this context.

Recommended citation: Dingdong Liu, Sensen Gao, Zixin Chen, Yifan Shen, Chuhan Shi, Bertram E. Shi, and Xiaojuan Ma. 2024. Exploring Scaffolding Techniques for Agent-Administered Brief Cognitive Screening in Hospital Settings. In Companion Publication of the 2024 ACM Designing Interactive Systems Conference (DIS '24 Companion). Association for Computing Machinery, New York, NY, USA, 185-189. https://doi.org/10.1145/3656156.3663697
Download Paper | Download Slides

CoArgue : Fostering Lurkers’ Contribution to Collective Arguments in Community-based QA Platforms

Published in CHI' 23, 2023

This research investigates obstacles hindering lurkers from contributing to collective arguments in Community-Based Question Answering (CQA) platforms, leading to the development of CoArgue, a tool designed to enhance lurkers' motivation and ability to participate in discussions by extracting and summarizing augmentative elements from question threads, resulting in a more engaging and productive experience compared to a Quora-like baseline, as demonstrated in a within-subject study involving 24 participants.

Recommended citation: Chengzhong Liu, Shixu Zhou, Dingdong Liu, Junze Li, Zeyu Huang, and Xiaojuan Ma. 2023. CoArgue_: Fostering Lurkers' Contribution to Collective Arguments in Community-based QA Platforms. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 271, 1-17. https://doi.org/10.1145/3544548.3580932
Download Paper

PlanHelper: Supporting Activity Plan Construction with Answer Posts in Community-based QA Platforms

Published in CSCW '22, 2022

This study addresses challenges in using answer posts from Community-based Question Answering (CQA) platforms for constructing Activity Plans (AP). By proposing an answer-post processing pipeline and developing PlanHelper, users were found to be significantly more satisfied with informational support and more engaged when creating AP compared to a Quora-like baseline in a within-subject study involving 24 participants. The research also includes an analysis of user behaviors with PlanHelper and provides design considerations for similar supporting tools.

Recommended citation: Chengzhong Liu, Zeyu Huang, Dingdong Liu, Shixu Zhou, Zhenhui Peng, and Xiaojuan Ma. 2022. PlanHelper: Supporting Activity Plan Construction with Answer Posts in Community-based QA Platforms. Proc. ACM Hum.-Comput. Interact. 6, CSCW2, Article 454 (November 2022), 26 pages. https://doi.org/10.1145/3555555
Download Paper

Exploring the Effects of Self-Mockery to Improve Task-Oriented Chatbot’s Social Intelligence

Published in DIS' 22, 2022

This study explores the impact of self-mockery humor on a customer service chatbot's Social Intelligence (SI) by proposing a pipeline for incorporating situated self-mockery in different interaction stages. Through a within-subject experiment involving 28 participants, the self-mockery chatbot was found to be significantly funnier, more satisfactory, and to perform better in certain aspects of SI compared to a chatbot without self-mockery utterances. The study also discusses individual factors influencing the perceived helpfulness of self-mockery on SI and provides design considerations based on the findings.

Recommended citation: Chengzhong Liu, Shixu Zhou, Yuanhao Zhang, Dingdong Liu, Zhenhui Peng, and Xiaojuan Ma. 2022. Exploring the Effects of Self-Mockery to Improve Task-Oriented Chatbot's Social Intelligence. In Proceedings of the 2022 ACM Designing Interactive Systems Conference (DIS '22). Association for Computing Machinery, New York, NY, USA, 1315-1329. https://doi.org/10.1145/3532106.3533461
Download Paper