TINT is a simple, DIY platform that helps brands find, curate, and display their most effective customer-generated content from social media on marketing channels such as websites, mobile apps, and event displays. Businesses can link their Twitter, YouTube, Pinterest, Instagram, Facebook, and RSS feeds to their TINT accounts
The social media aggregator uses machine learning to automate the curation process and recommend content that is likely to resonate well with their clients’ audience. TINT analyzes every post on the platform, extracting valuable information to learn what customers are posting about clients’ brand.
Content curation and recommendation
HUE by TINT, is a scalable content discovery engine that help TINT clients uncover great visual content with machine learning. HUE uses natural language processing, image recognition, deep learning, and audience insights to instantly pair brands with highly engaging content, eliminating the need for manual curation and guesswork.
How it works
The TINT content curation engine also relies on Amazon Comprehend, a machine learning service from AWS, to make its platform more accurate and ensure that the identified social media content resonates with clients’ campaigns. Amazon Comprehend is a natural language process (NLP) service that uses machine learning to understand the meaning in text and identify potentially hidden relationships and trends. TINT uses Amazon Comprehend to provide sentiment analysis for both English and Spanish text (positive, negative, neutral, or mixed), and to examine and identify common themes in the content. For sources that do not provide language identification (such as Facebook), Amazon Comprehend also helps to detect the language of the text. All the information is used by HUE to better understand what their customers like to see.
“Our business is focused on delivering the best marketing content possible for the brands that depend on us,” said Ryo Chiba, Chief Technology Officer of TINT. “Using Amazon Comprehend, we were able to significantly increase the quality and accuracy of our platform’s content analytics capabilities, which identifies the right content for the most impactful marketing campaigns. Amazon Comprehend allows us to focus on our core product and not worry about the heavy lifting associated with building our own machine learning models.”
To reduce the reliance on manual tagging, TINT turned to Amazon Rekognition, a deep-learning-powered image recognition service. Amazon Rekognition Image identifies thousands of objects such as vehicles, pets, and furniture, as well as scenes within an image, such as a sunset or a beach. It also enables customers to detect explicit and suggestive content, so that they can filter out inappropriate images based on their requirements.
After HUE has analyzed the images, it uses machine learning to understand users’ moderation behavior and tracks what the users like or dislike. Using this data, HUE builds a library of content that is catered to clients’ content preferences and surface recommended content.
Client success story
Loews Hotels launched #TravelForReal, which took user-generated content and used it to build an entire campaign that spanned digital and print. Guests shared Instagram photography from their stay at Loews properties. After tagging the images, the brand featured select user-generated content across various advertising and promotional channels. In so doing, the Loews was able to scale their content efficiently, and engage their audience at a more personal level.
“It was a huge search to find the right images for each communication, and many people were involved when it came to pinpointing the perfect guest photo for a hotel ad or a brand ad,” says Piper Stevens, Loews senior director of Brand Loyalty and Marketing Communications. Using the advanced moderation feature and content filters, Loews is able to narrow down searches to find that 0.1% of high quality content, without having to scroll through hundreds of pages of posts. Leveraging the targeting functionality, Loews is able to curate guest images that have a distinctive look and feel that corresponds to a destination, such as filling the lobby screens in Miami with iconic South Beach imagery, and billboards in Hollywood with pictures of poolside visitors enjoying the LA summers.
Conclusion
Amazon Comprehend removes the complexity of building text analysis capabilities into your applications by making powerful and accurate natural language processing available with a simple API. You don’t need textual analysis expertise to take advantage of the insights that Amazon Comprehend produces. Amazon Comprehend enables TINT to analyze millions of documents efficiently, to find and aggregate the best social media content for their customers.
About the Author
Binny Peh is a Sr. Product Marketing Manager for AWS machine learning solutions. In her spare time, she indulges in too much television and is an aspiring foodie. Binny’s glass is always half-full, and she believes in the power of positive thinking.