From Eww to Woo: Detection of Mental Health Disturbing Images in Social Media
Keywords: Mental Health, Social Media, Harmful
Abstract: Exposure to distressing images on social media, such as gore and other graphic content, can lead to significant mental health issues and disturbances. This paper introduces a novel dataset specifically curated to include such harmful images, aiming to facilitate the development of machine learning models capable of detecting and filtering these types of content. By training on this dataset, the proposed models demonstrate the ability to accurately identify and flag disturbing images, thereby contributing to the mitigation of mental health risks associated with prolonged exposure to harmful visual content on social media platforms. The proposed dataset is benchmarked on various state of the art models with the accuracy 70.15\%. This work represents a critical step towards creating safer online environments and protecting users' mental well-being.
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 3921
Loading