[{"file_date_updated":"2025-09-16T07:47:45Z","citation":{"bibtex":"@article{Johnson_2025, title={Higher Stakes, Healthier Trust? An Application-Grounded Approach to Assessing Healthy Trust in High-Stakes Human-AI Collaboration}, author={Johnson, David S.}, year={2025} }","ama":"Johnson DS. Higher Stakes, Healthier Trust? An Application-Grounded Approach to Assessing Healthy Trust in High-Stakes Human-AI Collaboration. Published online 2025.","mla":"Johnson, David S. <i>Higher Stakes, Healthier Trust? An Application-Grounded Approach to Assessing Healthy Trust in High-Stakes Human-AI Collaboration</i>. 2025.","chicago":"Johnson, David S. “Higher Stakes, Healthier Trust? An Application-Grounded Approach to Assessing Healthy Trust in High-Stakes Human-AI Collaboration,” 2025.","short":"D.S. Johnson, (2025).","ieee":"D. S. Johnson, “Higher Stakes, Healthier Trust? An Application-Grounded Approach to Assessing Healthy Trust in High-Stakes Human-AI Collaboration.” 2025.","apa":"Johnson, D. S. (2025). <i>Higher Stakes, Healthier Trust? An Application-Grounded Approach to Assessing Healthy Trust in High-Stakes Human-AI Collaboration</i>."},"abstract":[{"lang":"eng","text":"Human-AI collaboration is increasingly promoted to improve high-stakes decision-making, yet its benefits have not been fully realized. Application-grounded evaluations are needed to better evaluate methods for improving collaboration but often require domain experts, making studies costly and limiting their generalizability. Current evaluation methods are constrained by limited public datasets and reliance on proxy tasks. To address these challenges, we propose an application-grounded framework for large-scale, online evaluations of vision-based decision-making tasks. The framework introduces Blockies, a parametric approach for generating datasets of simulated diagnostic tasks, offering control over the traits and biases in the data used to train real-world models. These tasks are designed to be easy to learn but difficult to master, enabling participation by non-experts. The framework also incorporates storytelling and monetary incentives to manipulate perceived task stakes. An initial empirical study demonstrated that the high-stakes condition significantly reduced healthy distrust of AI, despite longer decision-making times. These findings underscore the importance of perceived stakes in fostering healthy distrust and demonstrate the framework's potential for scalable evaluation of high-stakes Human-AI collaboration. "}],"project":[{"name":"TRR 318 - Teilprojekt IRG BI","_id":"1204"}],"file":[{"date_created":"2025-09-16T07:47:45Z","creator":"johnson","success":1,"content_type":"application/pdf","file_id":"61296","date_updated":"2025-09-16T07:47:45Z","relation":"main_file","access_level":"closed","file_size":1715871,"file_name":"2503.03529v1.pdf"}],"date_created":"2025-09-16T07:41:37Z","type":"preprint","department":[{"_id":"660"}],"year":"2025","title":"Higher Stakes, Healthier Trust? An Application-Grounded Approach to Assessing Healthy Trust in High-Stakes Human-AI Collaboration","status":"public","author":[{"first_name":"David S.","last_name":"Johnson","full_name":"Johnson, David S."}],"date_updated":"2025-09-16T07:48:33Z","has_accepted_license":"1","_id":"61294","language":[{"iso":"eng"}],"user_id":"97208","ddc":["000"]},{"ddc":["000"],"user_id":"97208","volume":16,"page":"518-536","_id":"61290","publisher":"Institute of Electrical and Electronics Engineers (IEEE)","has_accepted_license":"1","status":"public","project":[{"_id":"110","name":"TRR 318 - Project Area A"},{"_id":"1204","name":"TRR 318 - Teilprojekt IRG BI"},{"_id":"1200","name":"TRR 318 - Teilprojekt A6 - Inklusive Ko-Konstruktion sozialer Signale des Verstehens"}],"file_date_updated":"2025-09-16T07:34:27Z","citation":{"chicago":"Johnson, David, Olya Hakobyan, Jonas Paletschek, and Hanna Drimalla. “Explainable AI for Audio and Visual Affective Computing: A Scoping Review.” <i>IEEE Transactions on Affective Computing</i> 16, no. 2 (2024): 518–36. <a href=\"https://doi.org/10.1109/taffc.2024.3505269\">https://doi.org/10.1109/taffc.2024.3505269</a>.","short":"D. Johnson, O. Hakobyan, J. Paletschek, H. Drimalla, IEEE Transactions on Affective Computing 16 (2024) 518–536.","apa":"Johnson, D., Hakobyan, O., Paletschek, J., &#38; Drimalla, H. (2024). Explainable AI for Audio and Visual Affective Computing: A Scoping Review. <i>IEEE Transactions on Affective Computing</i>, <i>16</i>(2), 518–536. <a href=\"https://doi.org/10.1109/taffc.2024.3505269\">https://doi.org/10.1109/taffc.2024.3505269</a>","ieee":"D. Johnson, O. Hakobyan, J. Paletschek, and H. Drimalla, “Explainable AI for Audio and Visual Affective Computing: A Scoping Review,” <i>IEEE Transactions on Affective Computing</i>, vol. 16, no. 2, pp. 518–536, 2024, doi: <a href=\"https://doi.org/10.1109/taffc.2024.3505269\">10.1109/taffc.2024.3505269</a>.","ama":"Johnson D, Hakobyan O, Paletschek J, Drimalla H. Explainable AI for Audio and Visual Affective Computing: A Scoping Review. <i>IEEE Transactions on Affective Computing</i>. 2024;16(2):518-536. doi:<a href=\"https://doi.org/10.1109/taffc.2024.3505269\">10.1109/taffc.2024.3505269</a>","bibtex":"@article{Johnson_Hakobyan_Paletschek_Drimalla_2024, title={Explainable AI for Audio and Visual Affective Computing: A Scoping Review}, volume={16}, DOI={<a href=\"https://doi.org/10.1109/taffc.2024.3505269\">10.1109/taffc.2024.3505269</a>}, number={2}, journal={IEEE Transactions on Affective Computing}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Johnson, David and Hakobyan, Olya and Paletschek, Jonas and Drimalla, Hanna}, year={2024}, pages={518–536} }","mla":"Johnson, David, et al. “Explainable AI for Audio and Visual Affective Computing: A Scoping Review.” <i>IEEE Transactions on Affective Computing</i>, vol. 16, no. 2, Institute of Electrical and Electronics Engineers (IEEE), 2024, pp. 518–36, doi:<a href=\"https://doi.org/10.1109/taffc.2024.3505269\">10.1109/taffc.2024.3505269</a>."},"doi":"10.1109/taffc.2024.3505269","language":[{"iso":"eng"}],"date_updated":"2025-09-16T08:02:23Z","publication_status":"published","intvolume":"        16","article_type":"review","year":"2024","title":"Explainable AI for Audio and Visual Affective Computing: A Scoping Review","publication_identifier":{"issn":["1949-3045","2371-9850"]},"author":[{"id":"97208","full_name":"Johnson, David","last_name":"Johnson","first_name":"David"},{"last_name":"Hakobyan","first_name":"Olya","full_name":"Hakobyan, Olya"},{"last_name":"Paletschek","first_name":"Jonas","full_name":"Paletschek, Jonas","id":"98941"},{"first_name":"Hanna","last_name":"Drimalla","full_name":"Drimalla, Hanna"}],"type":"journal_article","department":[{"_id":"660"}],"file":[{"success":1,"content_type":"application/pdf","file_id":"61291","date_updated":"2025-09-16T07:34:27Z","relation":"main_file","access_level":"closed","file_size":3252812,"file_name":"Explainable_AI_for_Audio_and_Visual_Affective_Computing_A_Scoping_Review.pdf","date_created":"2025-09-16T07:34:27Z","creator":"johnson"}],"date_created":"2025-09-16T07:24:07Z","abstract":[{"lang":"eng","text":"ffective computing often relies on audiovisual data to identify affective states from non-verbal signals, such as facial expressions and vocal cues. Since automatic affect recognition can be used in sensitive applications, such as healthcare and education, it is crucial to understand how models arrive at their decisions. Interpretability of machine learning models is the goal of the emerging research area of Explainable AI (explainable AI (XAI)). This scoping review aims to survey the field of audiovisual affective machine learning to identify how XAI is applied in this domain. We first provide an overview of XAI concepts relevant to affective computing. Next, following the recommended PRISMA guidelines, we perform a literature search in the ACM, IEEE, Web of Science and PubMed databases. After systematically reviewing 1190 articles, a final set of 65 papers is included in our analysis. We quantitatively summarize the scope, methods and evaluation of the XAI techniques used in the identified papers. Our findings show encouraging developments for using XAI to explain models in audiovisual affective computing, yet only a limited set of methods are used in the reviewed works. Following a critical discussion, we provide recommendations for incorporating interpretability in future work for affective machine learnin"}],"issue":"2","publication":"IEEE Transactions on Affective Computing"}]