Content moderation assistance through image caption generation

The rapid growth in digital media creation has led to an increased challenge in content moderation. Manual and automated moderation are susceptible to risks associated with a slower response time and false positives arising from unpredictable user inputs respectively. Image caption generation has be...

Full description

Saved in:
Bibliographic Details
Main Author: Liam Kearns
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Intelligent Systems with Applications
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667305325000158
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078834707136512
author Liam Kearns
author_facet Liam Kearns
author_sort Liam Kearns
collection DOAJ
description The rapid growth in digital media creation has led to an increased challenge in content moderation. Manual and automated moderation are susceptible to risks associated with a slower response time and false positives arising from unpredictable user inputs respectively. Image caption generation has been suggested as a viable content moderation tool, but there is a lack of real world deployment in this context. In this work, a collaborative approach is taken, where a machine learning model is used to assist human moderators in the approval and rejection of media within a scavenger hunt game. The proposed model is trained on the Flickr30k and MS Coco datasets to generate captions for images. The results demonstrate a 13% reduction in review times, indicating that human–machine collaboration contributes to mitigating the risk of unsustainable review backlog growth. Furthermore, fine-tuning the model led to a 28% reduction in review times when compared to the untuned model. Notably, this paper contributes to knowledge by demonstrating caption generation as a viable content moderation tool in addition to its sensitivity to accurate captions, whereby false positives risk a deterioration in moderator response time.
format Article
id doaj-art-fa76e18ad9ed4816b9ab2e708c188877
institution DOAJ
issn 2667-3053
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Intelligent Systems with Applications
spelling doaj-art-fa76e18ad9ed4816b9ab2e708c1888772025-08-20T02:45:27ZengElsevierIntelligent Systems with Applications2667-30532025-03-012520048910.1016/j.iswa.2025.200489Content moderation assistance through image caption generationLiam Kearns0AuraQ, 33 Graham Rd, Malvern, WR14 2HU, Worcestershire, UKThe rapid growth in digital media creation has led to an increased challenge in content moderation. Manual and automated moderation are susceptible to risks associated with a slower response time and false positives arising from unpredictable user inputs respectively. Image caption generation has been suggested as a viable content moderation tool, but there is a lack of real world deployment in this context. In this work, a collaborative approach is taken, where a machine learning model is used to assist human moderators in the approval and rejection of media within a scavenger hunt game. The proposed model is trained on the Flickr30k and MS Coco datasets to generate captions for images. The results demonstrate a 13% reduction in review times, indicating that human–machine collaboration contributes to mitigating the risk of unsustainable review backlog growth. Furthermore, fine-tuning the model led to a 28% reduction in review times when compared to the untuned model. Notably, this paper contributes to knowledge by demonstrating caption generation as a viable content moderation tool in addition to its sensitivity to accurate captions, whereby false positives risk a deterioration in moderator response time.http://www.sciencedirect.com/science/article/pii/S2667305325000158Content moderationCaption generationComputer visionMachine learning
spellingShingle Liam Kearns
Content moderation assistance through image caption generation
Intelligent Systems with Applications
Content moderation
Caption generation
Computer vision
Machine learning
title Content moderation assistance through image caption generation
title_full Content moderation assistance through image caption generation
title_fullStr Content moderation assistance through image caption generation
title_full_unstemmed Content moderation assistance through image caption generation
title_short Content moderation assistance through image caption generation
title_sort content moderation assistance through image caption generation
topic Content moderation
Caption generation
Computer vision
Machine learning
url http://www.sciencedirect.com/science/article/pii/S2667305325000158
work_keys_str_mv AT liamkearns contentmoderationassistancethroughimagecaptiongeneration