By Apoorv Saxena, Product Manager, Cloud AI
From documents to blog posts, emails to social media updates, there’s never been more ways to connect via the written word. For businesses, this can present both a challenge and an opportunity. With such a proliferation of communication channels, how do businesses stay responsive? More importantly, how can they derive useful insights from all of their content?
That’s where Google Cloud Natural Language API comes in. Cloud Natural Language enables businesses to extract critical information from their written data. And today we’re launching two new features that can help businesses further organize their content and better understand how their users feel.
Here’s a little more on what these new features can do.
Through predefined content classification, Cloud Natural Language can now automatically sort documents and content into more than 700 different categories, including Arts & Entertainment, Hobbies & Leisure, Law & Government, News, Health, and more. This makes it ideal for industries like media and publishing who’ve traditionally had to manually sort, label and categorize content. Through machine learning with Cloud Natural Language, these companies can now automatically parse the meaning of their articles and content to organize
them more efficiently.
To showcase the granularity of content classification, we analyzed top stories from the The New York Times API with Cloud Natural Language. This lobster salad recipe was categorized not only as “Cooking & Recipes” but also as “Meat & Seafood.” You can read more examples on our machine learning blog.
Hearst, one of the largest mass media publishers in the world, uses Cloud Natural Language Processing in their content management system to automatically tag entities in articles and will be using categories such as sports, entertainment, technology and more. Natural language processing adds an intelligence layer to their newsrooms, that will allow editors to understand what their audience is reading and how their content is being used. For example, Hearst now has granular visibility into how specific entities (people, places and things) trend across all their properties including daily newspapers such as the San Francisco Chronicle. This insight will help editors keep a finger on the pulse of their readers and better inform them when deciding what or who to cover in the news.
“In the newsroom, precision and speed are critical to engaging our readers. Google Cloud Natural Language is unmatched in its accuracy for content classification. At Hearst, we publish several thousand articles a day across 30+ properties and, with natural language processing, we’re able to quickly gain insight into what content is being published and how it resonates with our audiences.”
— Naveed Ahmad, Senior Director of Data, Hearst
Content classification is available in beta for all Cloud Natural Language users.
Sentiment analysis is one of Cloud Natural Language’s most popular features. Now, it offers more granularity with entity sentiment analysis. Rather than analyze the sentiment of a sentence or block of text, users can now parse the sentiment of places or things.
Leveraging Entity Sentiment Analysis, Motorola analyzes customer sentiment about its products across multiple sources such as Twitter, online community forums, and customer service emails. The insight helps Motorola quickly turn feedback into actionable results and increase customer satisfaction. Motorola uses Cloud Natural Language alongside its in-house natural language algorithms to get richer, more granular understanding of its customers to better serve them. Cloud Natural Language also offered a short learning curve and was easily integrated within its existing framework, without any downtime.
Entity sentiment analysis is now generally available for all Cloud Natural Language users.
These new features will help even more businesses use machine learning to get the most from their data. For more information, visit our website or sign up for a trial at no charge.