Neural Networks Based Automatic Content Moderation on Social Media
Date
2020
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Tartu Ülikool
Abstract
Millions of users produce and consume billions of content on social media. Therefore, humanreviewed
content moderation is not achievable in such volume. Automating content moderation
is a scalable solution for social media platforms. In this thesis work, we propose a neural networks
based automatic content moderation pipeline. Our solution consists of two main parts:
the first part that classifies the content into granular content classes and a second part that automatically
obfuscates the part of the image that might be inappropriate for the target audience.
The proposed solution is cost-efficient in terms of human labour. Our classification network
is trained with automatically labelled data using noise-robust techniques. Our automatic obfuscation
algorithm uses the information obtained from the classification network and does not
require additional annotation or supplementary training. This obfuscation algorithm presents a
novel-use case to the state-of-the-art.
Description
Keywords
Computer vision, Image recognition, Pattern recognition, Convolutional neural networks, Deep learning, Automated content moderation, arvutinägemine, pildituvastus, mustrituvastus, konvolutsioonilised närvivõrgud, sügav õppimine, automatiseeritud sisu modereerimine