005: CHIIR 2025 resource paper: g-Rel-READER Dataset

007: ETRA 2025 research paper: Real-Time Attention Capture in Visual Search

Jayawardena, G., Jayawardana, Y., Abeysinghe, Y., Mahanama, B., Jayarathna, S., & Gwizdka, J. (2025). A Real-Time Approach to Capture Ambient and Focal Attention in Visual Search. Proceedings of the 2025 Symposium on Eye Tracking Research and Applications, 1–7. https://doi.org/10.1145/3715669.3723111 [https://doi.org/10.1145/3715669.3723111] Conversation in this podcast is generated by AI Notebooklm.google from the full text of the paper. (C) is held by paper authors. Illutration was generated by ChatGPT. Music intro created by a human (C) Jacek Gwizdka. https://jacekg.ischool.utexas.edu/ https://ixlab.ischool.utexas.edu/

006: CHIIR 2025 research paper: Pupillometric Analysis of Cognitive Load in Relation to Relevance and Confirmation Bias

Shi, L., Jayawardena, G., & Gwizdka, J. (2025). Pupillometric Analysis of Cognitive Load in Relation to Relevance and Confirmation Bias. Proceedings of the 2025 ACM SIGIR Conference on Human Information Interaction and Retrieval, 219–230. https://doi.org/10.1145/3698204.3716458 [https://doi.org/10.1145/3698204.3716458] Conversation in this podcast is generated by AI Notebooklm.google from the full text of the paper. (C) is held by paper authors. Illutration was generated by ChatGPT.

005: CHIIR 2025 resource paper: g-Rel-READER Dataset

Gwizdka, J., & Cole, M. (2025). g-Rel-READER: A Dataset for Relevance and Reading Evaluation through Advanced Data from Eye-tracking and EEG Recordings. Proceedings of the 2025 ACM SIGIR Conference on Human Information Interaction and Retrieval, 377–381. https://doi.org/10.1145/3698204.3716474 [https://doi.org/10.1145/3698204.3716474] Conversation in this podcast is generated by AI Notebooklm.google from the full text of the paper. (C) is held by paper authors.

004-True or false? Reading COVID-19 news headlines

IX LAB RESEARCH - 004 This episode introduces 2023 paper presented at the ACM SIGIR Conference on Human Information Interaction and Retrieval. This research was conducted by PhD students Li Shi, Nilavra Bhattacharya and Anubrata Das under supervision of Dr. Jacek Gwizdka and Dr. Matt Lease.  Shi, L., Bhattacharya, N., Das, A., & Gwizdka, J. (2023). True or false? Cognitive load when reading COVID-19 news headlines: an eye-tracking study. Proceedings of the 2023 Conference on Human Information Interaction and Retrieval, 107–116. https://doi.org/10.1145/3576840.3578290 [https://doi.org/10.1145/3576840.3578290] SUMMARY This podcast discussion summarizes a study using eye-tracking to examine how people process online information. The research reveals position bias, where information presented first receives disproportionate attention. Pupil dilation indicated increased cognitive effort when encountering information contradicting personal beliefs or presenting incorrect evidence, especially when aligning with pre-existing biases. Interestingly, belief changes didn't significantly impact cognitive load. The study highlights how our brains prioritize information confirming existing beliefs, even if inaccurate, emphasizing the need for critical thinking and awareness of cognitive biases. IX Lab website: https://ixlab.us/ [https://ixlab.us/] Dr. Jacek Gwizdka website: https://jacekg.ischool.utexas.edu/ [https://jacekg.ischool.utexas.edu/] The audio for this conversation has been generated by AI using: https://notebooklm.google/ Music intro created by a human (C) Jacek Gwizdka

003-From brain waves to words: Using AI to convert brain signals to text

IX LAB RESEARCH - 003 This episode discusses the 2024 paper: Mishra, A., Shukla, S., Torres, J., Gwizdka, J., & Roychowdhury, S. (2024). Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs) (No. arXiv:2410.07507). arXiv. https://doi.org/10.48550/arXiv.2410.07507 [https://doi.org/10.48550/arXiv.2410.07507] This research is conducted under Dr. Abhijit Mishra as the main Principal Investigator with students Shreya Shukla and Jose Torres and contributions from Dr. Jacek Gwizdka and Dr. Shounak Roychowdhury. SUMMARY Researchers at the University of Texas at Austin are developing technology to translate brainwaves into text using electroencephalography (EEG) and large language models (LLMs). The system employs a three-stage process: training an EEG encoder to extract features, fine-tuning LLMs on multimodal data (images and text), and further refining the LLMs with EEG embeddings for text generation. Experiments using a public EEG dataset demonstrate the effectiveness of this approach, surpassing chance performance and showing promise for future applications in assistive technologies and neuroscience. While the technology shows promising results, it's still in its early stages and faces challenges such as noise in EEG data, limited spatial resolution of EEG, and ethical concerns about privacy and bias. Potential applications include assistive technology for communication impairments and advances in healthcare and education. IX Lab website: https://ixlab.us/ [https://ixlab.us/] Dr. Jacek Gwizdka website: https://jacekg.ischool.utexas.edu/ [https://jacekg.ischool.utexas.edu/] The audio for this conversation has been generated by AI using: https://notebooklm.google/ Music intro created by a human (C) Jacek Gwizdka