AWS Machine Learning Blog

ClearView Social uses Amazon Comprehend to measure the impact of social sharing

ClearView Social enables a company’s employees to share approved content on LinkedIn, Twitter, and other social networks with a single click. It then broadcasts the content to those social networks at peak times, and tracks the resulting engagement with a leaderboard and an analytics dashboard.

According to Bill Boulden, CTO of ClearView Social, a key differentiator of the ClearView Social platform is that it allows customers to calculate and track return on investment (ROI) from social sharing. Companies that use ClearView Social have realized as much as a 20x increase in ROI, based on earned media value.

In the past, it was hard to measure the value of social engagement. The formula for calculating the value of social shares relied on users manually tagging content consistently and accurately. But content wasn’t always accurately tagged, or wasn’t tagged at all.

To eliminate the reliance on manual tagging, ClearView Social turned to Amazon Comprehend, a natural language processing (NLP) service that uses machine learning to find insights and relationships in text. The Amazon Comprehend entity detection feature returns a list of named entities, such as people, places, and locations.

“We use Amazon Comprehend to read an article and extract topics, which are automatically tagged using machine learning. This automatic tagging helps customers easily estimate the market value of their engagement according to the current bid prices from the Google AdWords API,” explains Boulden.

How it works: ClearView Social and Amazon Comprehend

As an example, let’s take a post from the AWS AI blog,  AWS DeepLens Extensions: Build Your Own Project. First, we store the unstructured data from the post in an Amazon S3 bucket. The ClearView Social platform analyzes the data from the bucket.

Using Amazon Comprehend’s entity recognition API, the text is scanned and automatically tagged as relevant entities are identified. In this example, Amazon Comprehend immediately identifies two entities: Alexa and It also recognizes that in the context of this blog post, Go is an entity that refers to the Amazon Go store. The Amazon Comprehend key phrase extraction API also recognizes that, for instance, robotics is a type of entity that is important to this post.

Employees can use email to immediately share the post on social networks. The ClearView Social platform logs the entity tags to calculate the reach of social sharing and the success metrics for engagement.

“Amazon Comprehend tags entities with the highest confidence and enables us to make more accurate earned media estimates to really determine ROI from social. We used to see earned media value as a very rough estimate, but not anymore,” says Boulden.

ClearView Social plans to explore other Amazon Comprehend features, including sentiment analysis, which determines the overall sentiment expressed in text—positive, negative, neutral, or mixed.

To get started with Amazon Comprehend, see these posts:

Build a social media dashboard using Amazon Comprehend and BI services

Amazon Comprehend – Continuously Trained Natural Language Processing


About the author

Cynthya Peranandam is a Principal Marketing Manager for AWS artificial intelligence solutions, helping customers use deep learning to provide business value. In her spare time she likes to run and listen to music.