Google says it’s implementing AI and machine learning techniques to improve story suggestions in Google Search. In a blog post this morning, the tech giant announced that users in the U.S. in English (with more languages and locations to come in the next few months) who search for a news topic will now see an article carousel at the top of the results page. When there are multiple stories related to a search, each will be organized by relevance and quality in a way that accounts for a diversity of perspectives.
“People come to Search for all types of information to help them form a better understanding of the world and the topics they care about most,” wrote Google Search product manager Duncan Osborn. “We’ve continued to bring new improvements to Search to help people better orient themselves around a topic and easily explore related ideas, so they can more quickly go from having a question in mind to developing deeper understanding … Our research has shown that clustering results into clearly-defined stories is critical in helping people easily navigate the results and identify the best content for their needs.”
Osborn says that as of today, Google Search structures story results with better context. For example, if a person searches for “NASA news,” they might see results grouped under the distinct news stories “NASA adds five companies to moon bid” and “NASA detects water vapor on Jupiter’s moon Europa,” along with additional results under “Also in the news.”
Powering this experience is a new story-understanding technology that graphs the people, places, and things involved in a news story and then draws connections between them. Distinct groups of news articles are informed by natural language understanding architectures like Bidirectional Encoder Representations from Transformers (BERT), which Google recently deployed to Search to help improve its understanding of the intent behind users’ search queries.
Alongside these improvements, Google says it’s now featuring key information like notable quotes and related opinion pieces in the top stories carousel within Search. It’s an attempt to provide a “more well-rounded” preview of a news piece’s tone and tenor, according to Osborn, and a part of a longer-term effort to expand the types of journalistic contributions users encounter in Search.
“We hope these updates help people engage with the most relevant information and build a deeper understanding of the world around them,” said Osborn.
This week’s enhancements to Search come over a year after Google completely revamped Google News, using information it knows about users to suggest things that might interest them. It saw the launch of the For You section, which serves up tidbits specifically for people based on what Google thinks they’ll like, with a starting point of five picks that mix big stories and local news. In addition, a new visual layout format called Newscasts rolled out, which uses machine learning to “understand” a range of content from across videos and articles on a single given topic, as well as Full Coverage, which shows stories reported from multiple sources and includes local coverage, videos, FAQs, social media commentary, and a timeline of events.