Streamline Content Moderation Operations
Human-based content moderation alone cannot scale to meet safety, regulatory, and operational needs, which leads to a poor user experience, high moderation costs, and brand risk. Content moderation powered by machine learning (ML) can help organizations moderate large and complex volumes of user-generated content (UGC) and reclaim up to 95% of the time that their teams spend moderating content manually.
Amazon content moderation services and solutions provide automation and artificial intelligence (AI) capabilities to implement a reliable content moderation solution without requiring ML expertise. Use these services to protect users from harmful exposure while reducing content moderation costs and safeguarding your organization from risk, liability, and brand damage.
Benefits
Improve safety for users and brands
Protect users and brands from unwanted content exposure and associations by proactively reviewing every content piece.
How? Review images and videos against a wide variety of pre-defined categories, or from your own list of prohibited terms, to moderate media at scale with Amazon Rekognition. Extend your moderation capabilities to audio files with Amazon Transcribe. Derive and understand valuable insights and sentiment with Amazon Comprehend.
Streamline content moderation operations
Eliminate the need to build new tools or managing infrastructure with pre-trained and customizable Amazon Rekognition moderation models and workflows.
How? Convert speech in videos to text with Amazon Transcribe and check it for use of profanities or hate speech. Moderate text across languages with neural machine technology in Amazon Translate. Extend text analysis with the natural language processing (NLP) capabilities in Amazon Comprehend. Integrate with Amazon Augmented AI (Amazon A2I) to provide human review for any ML workflow.
Increase reliability and lower costs
Create reliable, scalable, and repeatable cloud-based content moderation workflows without upfront commitments or expensive licenses.
How? Start with any of the AWS content moderation AI services under the AWS Free Tier and scale as needed.
Customer stories
-
CoStar Group
-
Dena
-
Dream11
-
Mobisocial
-
SmugMug
-
ZOZO
-
CoStar Group
-
CoStar is a leader in commercial real estate information, analytics, technology, and news, with one of the most comprehensive data platforms on the market, processing more than 150,000 images that are uploaded to its platform daily.
Read success story“For CoStar, it is imperative that images uploaded to our platform comply with the terms of our end user agreement and do not contain inappropriate content, so that we can ensure an inclusive, safe, and data-driven user community. Amazon Rekognition's Content Moderation API enabled us to easily build a solution to automatically analyze all uploaded images, allowing us to efficiently deliver high-value products to our customers. Amazon Rekognition offers a suite pre-trained computer vision APIs, which along with content moderation, text detection, and object detection, help us further improve our product offerings by making the images we receive more discoverable and our community more inclusive. Amazon Rekognition allows us to move quickly and add AI smarts to our systems with its pre-trained models, helping us stay focused on delivering unique solutions to the real estate sector.”
Mark Osborn, Principal Software Engineer, CoStar Group
-
Dena
-
DeNA, one of Japan's leading mobile gaming and internet services companies with major business areas in mobile games, sports, live streaming, healthcare, and automotive, now offers a live audio distribution app called Voice Pococha.
"When evaluating a speech-to-text service, we focused on finding a service that could create a safe community for our users by automatically redacting banned words. These banned words are typically slang and not recognized by standard speech-to-text services. With Amazon Transcribe and its custom vocabulary feature, banned terminology can be identified and redacted. Looking forward, our team is excited to grow the Voice Pococha community with the support of services like Amazon Transcribe and the Amazon Web Services (AWS) team."
Takuto Noguchi, Product Owner, and Takehiro Nakamori (Tech Lead), Live Streaming Business Unit, Strategy Office, DeNA
-
Dream11
-
Dream11 allows users to post videos and pictures and share images in group chats. The company uses Amazon Rekognition to automate the media analysis of thousands of assets each day as part of its content moderation process to protect and deliver engaging experiences to its 100 million users.
Learn more“Every decision we make is backed by data and technology, considering various metrics to continually add ‘wow factors’ that help retain customers. AWS promotes a user-first culture, with intuitive cloud-native services that help us launch things fast without any dependencies. The various AWS technology offerings help us develop our prototypes and make them live very quickly, even at a massive scale. This gives us a competitive edge in the market, where speed is essential.”
Praveen Jain, Vice President of Engineering, Dream11
-
Mobisocial
-
Mobisocial is a leading mobile software company, focused on building social networking and gaming applications. The company develops Omlet Arcade, a global community where tens of millions of mobile gaming live-streamers and e-sports players gather to share gameplay media.
“To ensure that our gaming community is a safe environment to socialize and share entertaining content, we used machine learning to identify content that doesn’t comply with our community standards. We created a workflow, leveraging Amazon Rekognition, to flag uploaded image and video content that contains non-compliant content. Amazon Rekognition’s content moderation API helps us achieve the accuracy and scale to manage a community of millions of gaming creators worldwide. Since implementing Amazon Rekognition, we’ve reduced the amount of content manually reviewed by our operations team by 95%, while freeing up engineering resources to focus on our core business. We’re looking forward to the latest Rekognition content moderation model update, which will improve accuracy and add new classes for moderation.”
Zehong, Senior Architect, Mobisocial
-
SmugMug
-
SmugMug operates two very large online photo platforms, SmugMug and Flickr, enabling more than 100M members to safely store, search, share, and sell tens of billions of photos. Flickr is the world's largest photographer-focused community, empowering photographers around the world to find their inspiration, connect with each other, and share their passion with the world.
“As a large, global platform, unwanted content is extremely risky to the health of our community and can alienate photographers. We use Amazon Rekognition’s content moderation feature to find and properly flag unwanted content, enabling a safe and welcoming experience for our community. At Flickr’s huge scale, doing this without Amazon Rekognition is nearly impossible. Now, thanks to content moderation with Amazon Rekognition, our platform can automatically discover and highlight amazing photography that more closely matches our members’ expectations, enabling our mission to inspire, connect, and share.”
Don MacAskill, Cofounder, CEO & Chief Geek, SmugMug
-
ZOZO
-
ZOZO, Inc. owns and operates ZOZOTOWN, Japan's largest fashion ecommerce, and WEAR, a SNS for sharing stylings and outfits, and more various services for fashion lovers.
"A large number of images are posted on WEAR from our users every day, and it was necessary to check every image to ensure that it complied with the service guidelines. We built a solution based on Amazon Rekognition Content Moderation API that automatically inspects to analyze the content that users post and store in Amazon S3. Amazon Rekognition has helped us cut down the manual content review process by up to 40% by automatically analyzing images. We were also able to reduce escalating reviews to supervisors that would have slowed down content operations when a person could not determine if an image was appropriate or not."
Yu Shigetani, Engineer, Brand Solution Development Division, ZOZO, Inc.
Use cases
Social media
Protect users from exposure to inappropriate content on content sharing platforms, such as dating apps and creativity networks.
Gaming
Prevent hate speech, profanity, bullying, and other behaviors that lower the safety and engagement in your gaming spaces.
Ecommerce
Keep illegal or controversial items and listings off your digital shelves to protect your marketplace and its users.
Finance and healthcare
Identify and protect sensitive personal identifiable or health information (PII, PHI) to meet internal standards and practices (S&P), comply with external regulation, and increase digital security for your users.
Education
Moderate the contributions from students and educators to help build a safe, inclusive, and fulfilling learning experience.
Advertising
Protect brands against unwanted associations to meet compliance. Also achieve brand objectives that lead to revenue growth, such as brand elevation and likability.
Featured Solution on AWS
Discover Purpose-Built Services, AWS Solutions, Partner Solutions, and Guidance to rapidly address your business and technical use cases.
Guidance for Content Moderation on AWS
This Guidance helps you implement a serverless architecture to efficiently moderate the increasing influx of user-contributed content and sensitive information. This content and information can come from a broad range of industries including gaming, social media, e-commerce, and regulated environments, such as healthcare and financial services.
How to get started
Contact us for more information on machine learning solutions for content moderation
Contact the AWS Partner Network, to work with our global technology and consulting partners
The AWS Professional Services organization is a global team of experts that can help you realize your desired business outcomes when using the AWS cloud
Choose an AWS Solution
AWS Solutions Reference Architectures are a collection of architecture diagrams, created by AWS. They provide prescriptive guidance for applications, as well as other instructions for replicating the workload in your AWS account.
Guidance for Content Moderation on AWS
This Guidance is a serverless architecture to efficiently obtain a broader understanding of your media libraries, analyze and extract valuable metadata, to moderate the increasing influx of user-generated content and sensitive information across industries.
This solution helps brand-conscious customers understand the most popular topics being actively discussed by ingesting digital assets and performing near real-time inferences and analytics.
The AWS Content Analysis solution helps you to obtain a broader understanding of your media libraries, analyze and extract valuable metadata.
Learn more »
AWS Solutions Implementations help you solve common problems and build faster using the AWS platform. All AWS Solutions Implementations are vetted by AWS architects and are designed to be operationally effective, reliable, secure, and cost efficient. Every AWS Solutions Implementation comes with detailed architecture, a deployment guide, and instructions for both automated and manual deployment.
AWS Media2Cloud SolutionIngest your content and move video assets and its metadata to the cloud with AWS Media2Coud solution.
Do it yourself
Getting started is free and easy. Amazon offers several flexible approaches you can use to implement content moderation workflows successfully and at a low cost.
Thousands of images and videos free per month for 12 months with the AWS Free Tier.
2 million characters free per month with the AWS Free Tier.
60 minutes free per month for 12 months with the AWS Free Tier.
50,000 units of text, for each of the nine APIs per month, and five jobs, up to 1MB each for 12 months with the AWS Free Tier.
500 objects free for the first 12 months with the AWS Free Tier.
