Kaixin’s research focuses on using physiological signals to quantify confirmation bias during information retrieval activities.
In today’s information-filled world, we rely heavily on information retrieval systems like Google to get the information we need. However, these systems often use algorithms and elements that prioritise catching our attention over presenting balanced viewpoints. This can lead to misinformation, manipulation, and the reinforcement of existing beliefs. Confirmation Bias, where people tend to favour information that aligns with their current beliefs, plays a significant role in this process. Studies show confirmation bias influences information reception, especially in health and politics. People tend to spend more time on information that supports their views and may even read opposing views with a critical attitude to disagree rather than accept. Existing solutions, such as training our brains or optimising search engines, have limitations. Technical solutions that prevent biased thinking and provide awareness are crucial. Kaixin’s research proposes using physiological data, such as skin conductance, heart rate, and gaze movement, to objectively measure and quantify confirmation bias during information retrieval activities. Her approach aims to overcome the limitations of subjective surveys and qualitative research. The main research questions focus on whether physiological data can discriminate information processing activities and detect as well as measure the level of confirmation bias in the information retrieval process.
Kaixin is a scholarship recipient of the ARC Centre for Automated Decision-Making and Society (ADM+S) is supervised by Prof. Falk Scholer, Dr. Damiano Spina, Prof. Flora Salim and Dr. Danula Hettiachchi.
Visit Kaixin’s personal website to learn more about her research.
References
2023
Examining the Impact of Uncontrolled Variables on Physiological Signals in User Studies for Information Processing Activities
Physiological signals can potentially be applied as objective measures to understand the behavior and engagement of users interacting with information access systems. However, the signals are highly sensitive, and many controls are required in laboratory user studies. To investigate the extent to which controlled or uncontrolled (i.e., confounding) variables such as task sequence or duration influence the observed signals, we conducted a pilot study where each participant completed four types of information-processing activities (READ, LISTEN, SPEAK, and WRITE). Meanwhile, we collected data on blood volume pulse, electrodermal activity, and pupil responses. We then used machine learning approaches as a mechanism to examine the influence of controlled and uncontrolled variables that commonly arise in user studies. Task duration was found to have a substantial effect on the model performance, suggesting it represents individual differences rather than giving insight into the target variables. This work contributes to our understanding of such variables in using physiological signals in information retrieval user studies.
@inproceedings{Ji2023-aq,title={Examining the Impact of Uncontrolled Variables on Physiological
Signals in User Studies for Information Processing Activities},booktitle={Proceedings of the 46th International {ACM} {SIGIR} Conference
on Research and Development in Information Retrieval},author={Ji, Kaixin and Spina, Damiano and Hettiachchi, Danula and Salim, Flora D and Scholer, Falk},publisher={ACM},series={SIGIR '23},year={2023},doi={10.1145/3539618.3591981},}
Towards Detecting Tonic Information Processing Activities with Physiological Data
In Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable Computing (UbiComp/ISWC ’23 Adjunct), 2023
Characterizing Information Processing Activities (IPAs) such as reading, listening, speaking, and writing, with physiological signals captured by wearable sensors can broaden the understanding of how people produce and consume information. However, sensors are highly sensitive to external conditions that are not trivial to control – not even in lab user studies. We conducted a pilot study (N = 7) to assess the robustness and sensitivity of physiological signals across four IPAs (READ, LISTEN, SPEAK, and WRITE) using multiple sensors. The collected signals include Electrodermal Activities, Blood Volume Pulse, gaze, and head motion. We observed consistent trends across participants, and ten features with statistically significant differences across the four IPAs. Our results provide preliminary quantitative evidence of differences in physiological responses when users encounter IPAs, revealing the necessity to inspect the signals separately according to the IPAs. The next step of this study moves into a specific context, information retrieval, and the IPAs are considered as the interaction modalities with the search system, for instance, submitting the search query by speaking or typing.
@inproceedings{Ji2023-td,author={Ji, Kaixin and Spina, Damiano and Hettiachchi, Danula and Scholer, Falk and Salim, Flora D.},title={Towards Detecting Tonic Information Processing Activities with Physiological Data},year={2023},isbn={9798400702006},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3594739.3610679},doi={10.1145/3594739.3610679},booktitle={Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing \& the 2023 ACM International Symposium on Wearable Computing},pages={1–5},numpages={5},location={Cancun, Mexico},series={UbiComp/ISWC '23 Adjunct},}