Mitigating Viewer Impact From Disturbing Imagery Using AI Filters: A User-Study
Abstract
Exposure to disturbing imagery can significantly impact individuals, especially professionals who encounter such content as part of their work. This article presents a user study, involving 107 participants, predominantly journalists and human rights investigators, that explores the capability of Artificial Intelligence (AI)-based image filters to potentially mitigate the emotional impact of viewing such disturbing content. We tested five different filter styles, both traditional (Blurring and Partial Blurring) and AI-based (Drawing, Colored Drawing, and Painting), and measured their effectiveness in terms of conveying image information while reducing emotional distress. Our main findings suggest that the AI-based Drawing style filter demonstrates the best performance, offering a promising solution for reducing negative feelings (−30.38%) while preserving the interpretability of the image (97.19%). Overall, this article contributes to the development of a more ethically considerate and effective visual environment for professionals routinely engaging with potentially disturbing imagery.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Some studies evaluating technological interventions such as image modification through blurring and filters found positive effects like reduced negative feelings while retaining operational efficiency.
“On one hand some studies (13–15), evaluating technological interventions such as image modification through blurring and filters, found positive effects like reduced negative feelings while retaining operational efficiency.”
From Longitudinal comparison of psychological outcomes of professional content moderators engaged in resilience training program (2025) · cites this paper as [15]
Cites
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 1× · see citing works
“The rapid advancements of Artificial Intelligence (AI) in recent years have enabled its integration into numerous fields with a wide range of applications (Bobadilla et al., 2013; Creswell et al., 2018; Taigman et al., 2014; Tan et al., 2020).”
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542 · see citing works
Image Style Transfer Using Convolutional Neural Networks
Gatys, L. A., Ecker, A. S., & Bethge, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.265 · Cited by 6,025 · see citing works
Generative Adversarial Networks: An Overview
Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., & Bharath, A. A. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2765202 · Cited by 4,540 · see citing works
Bobadilla, J., Ortega, F., Hernando, A., & Gutiérrez, A. (2013) · Knowledge-Based Systems · doi:10.1016/j.knosys.2013.03.012 · Cited by 3,167 · see citing works
Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
(2020) · doi:10.1145/3313831 · Cited by 1,951 · see citing works
Neural Style Transfer: A Review
Jing, Y., Yang, Y., Feng, Z., Ye, J., Yu, Y., & Song, M. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2019.2921336 · Cited by 894 · see citing works
Relationship between color and emotion: A study of college students.
Kaya, N., & Epps, H. H. (2004) · College student journal · Cited by 588 · see citing works
StyTr 2 : Image Style Transfer with Transformers
Deng, Y., Tang, F., Dong, W., Ma, C., Pan, X., Wang, L., & Xu, C. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01104 · Cited by 442 · see citing works
The Psychological Well-Being of Content Moderators
Steiger, M., Bharucha, T. J., Venkatagiri, S., Riedl, M. J., & Lease, M. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445092 · Cited by 168 · cited 1× · see citing works
“Furthermore, psychological traumas on content moderators are highlighted in several studies (Arsht & Etcovitch, 2018; Steiger et al., 2021).”
Witnessing images of extreme violence: a psychological study of journalists in the newsroom
Feinstein, A., Audet, B., & Waknine, E. (2014) · JRSM Open · doi:10.1177/2054270414533323 · Cited by 112 · see citing works
A Meta-Analysis of the Efficacy of Trigger Warnings, Content Warnings, and Content Notes
Bridgland, V. M. E., Jones, P. J., & Bellet, B. W. (2023) · Clinical Psychological Science · doi:10.1177/21677026231186625 · Cited by 77 · see citing works
Das, A., Dang, B., & Lease, M. (2020) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v8i1.7461 · Cited by 37 · see citing works
Preparing Future Journalists for Trauma on the Job
Hill, D., Luther, C. A., & Slocum, P. (2020) · Journalism & Mass Communication Educator · doi:10.1177/1077695819900735 · Cited by 30 · see citing works
Testing Stylistic Interventions to Reduce Emotional Impact of Content Moderation Workers
Karunakaran, S., & Ramakrishan, R. (2019) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v7i1.5270 · Cited by 28 · see citing works
Dirty Data: Content Moderation, Regulatory Outsourcing, and The Cleaners
Parks, L. (2019) · Film Quarterly · doi:10.1525/fq.2019.73.1.11 · Cited by 28 · see citing works
Content Moderators’ Strategies for Coping with the Stress of Moderating Content Online
Spence, R., Harrison, A., Bradbury, P., Bleakley, P., Martellozzo, E., & DeMarco, J. (2023) · Journal of Online Trust and Safety · doi:10.54501/jots.v1i5.91 · Cited by 25 · see citing works
Bridgland, V. M. E., & Takarangi, M. K. T. (2021) · Behavior Therapy · doi:10.1016/j.beth.2021.10.005 · Cited by 23 · see citing works
Bridgland, V. M. E., Bellet, B. W., & Takarangi, M. K. T. (2022) · Clinical Psychological Science · doi:10.1177/21677026221097618 · Cited by 23 · see citing works
Progressive Attentional Manifold Alignment for Arbitrary Style Transfer
Luo, X., Han, Z., & Yang, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26293-7_9 · Cited by 20 · see citing works
Danger, trauma, and verification: eyewitnesses and the journalists who view their material
Zeng, Y. (2018) · Media Asia · doi:10.1080/01296612.2017.1533279 · Cited by 8 · see citing works
Simister, E. T., Bridgland, V. M. E., Williamson, P., & Takarangi, M. K. T. (2023) · Media Psychology · doi:10.1080/15213269.2023.2211774 · Cited by 8 · see citing works
Safer Viewing: A Study of Secondary Trauma Mitigation Techniques in Open Source Investigations.
Baker, E., Stover, E., Haar, R. J., Lampros, A., & Koenig, A. (2020) · PubMed Central · Cited by 8 · see citing works
Leveraging Large-scale Multimedia Datasets to Refine Content Moderation Models
Sarridis, I., Koutlis, C., Papadopoulou, O., & Papadopoulos, S. (2022) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm55396.2022.00029 · Cited by 6 · see citing works
Self-citationA Web-Based Service for Disturbing Image Detection
Zampoglou, M., Papadopoulos, S., Kompatsiaris, I. Y., & Spangenberg, J. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-51814-5_37 · Cited by 4 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
A Systematic Review of User Attitudes Toward GenAI: Influencing Factors and Industry Perspectives
Chen, J., Wei, X., Xie, Q., Hu, A., Qiao, Y., Wan, R., & Liu, Y. (2025) · Journal of Intelligence · doi:10.3390/jintelligence13070078 · Cited by 36 · see citing works
Disturbing Image Detection Using LMM-Elicited Emotion Embeddings
Tzelepi, M., & Mezaris, V. (2024) · IEEE International Conference on Image Processing Workshops (ICIPW) · doi:10.1109/icipcw64161.2024.10769133 · Cited by 6 · see citing works
Framing the digital self: development and validation of the social media AI filter scale
Kuşci, İ., Bakır, V., & Arpacı, İ. (2026) · Online Information Review · doi:10.1108/oir-02-2025-0115 · Cited by 5 · see citing works
Savio, M. T., Balammal, A., de Villa, J. C., Perez, J., Huang, X., & Guevara, R. L. (2025) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2025.1666543 · Cited by 1 · see citing works
"Gross!": Personalized Video Content Moderation Using Generative Image Overlays for Aversive Videos
Choi, Y., Kim, D., Jun, Y., Kim, H., & Park, E. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746058.3758458 · Cited by 1 · see citing works
Nicholas, A., & Ennis, G. (2026) · Journal of Workplace Behavioral Health · doi:10.1080/15555240.2026.2621352 · Cited by 1 · see citing works
Zlatar, A., & Divers, A. (2025) · doi:10.1093/9780198945215.003.0168
An, S., Wu, Y., Zhang, Z., Li, Y., Jiang, M., Zhang, J., & Li, Q. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790993
- Authors
- Sarridis, I., Spangenberg, J., Papadopoulou, O., & Papadopoulos, S.
- Affiliations
- Centre for Research and Technology Hellas (GR)
- Deutsche Welle (DE)
- Corresponding author
- Sarridis, Ioannis
- Venue
- International Journal of Human–Computer Interaction
- Publisher
- Informa UK Limited
- Published
- 2024-03-13
- Volume
- 41
- Issue
- 2
- Pages
- 1234-1245
- ISSN
- 1044-7318 (ISSN-L)
- 1532-7590
- OpenAlex
- W4392761621
- Cited by
- 8
- References
- 25
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 1
- FWCI
- 1.95
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- International Journal of Human-Computer Interaction (publishedVersion)
- Funders
- MediaVerse (957252)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Aesthetic Perception and Analysis
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- image blurring, image stylization, journalists, image interpretability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
