Artificial Intelligence

Leveraging AI to advance the power of facts

Artificial intelligence at The Associated Press

The Associated Press was one of the first news organizations to leverage artificial intelligence and automation to bolster its core news report. Today, we use machine learning along key points in our value chain, including gathering, producing and distributing the news. Explore this page to learn more about the history of artificial intelligence at The Associated Press, our strategy around the technology and how we currently use it today.

Newsgathering

AP deploys a variety of news gathering tools to enable our journalists to break news and dig deeper. This involves working with startup partners to scan and analyze social media feeds with natural-language processing and building our own internal tool to verify social and user-generated content faster.

News production

Our objective in production is to streamline workflows to enable our journalists to concentrate on higher-order work. This ranges from the automatic transcription of video to experimenting with the automatic-generation of video shot-lists and story summaries. We also currently automate stories in both sports and corporate earnings.

News distribution

In distribution, we aim to make it easier for our customers to access our content and put it into production faster. As part of this, we are working to optimize content via image recognition, creating the first editorially-driven computer vision taxonomy for the industry. This tagging system will not only save hundreds of hours in production but help surface content more easily.

Startup partners

AP works with a variety of startup partners to infuse external innovation into the organization and help to bring our artificial intelligence projects to life. This allows us to experiment at low costs with emerging tech and support the entrepreneurial news ecosystem at the same time. In addition to working with various startups, we also build partnerships to help extend the reach of our journalism and our work with AI. Some key examples include Social Starts, Matter Ventures and NYC Media Lab.

US local newsrooms

The AP distributed a scorecard to U.S. local news operations to understand AI technologies and applications that are currently being used and how AI might augment news and business functions. Based on the scorecard results, AP wrote a report and designed an online course to share best practices and techniques on AI with local newsrooms. The initiative's third phase will be a consultancy program with 15 news operations.

Event detection

We deploy a tool from SAM, a Canadian social media solutions company, to detect newsworthy events based on natural language processing (NLP) of text-based chatter on Twitter and other social media venues. SAM alerts expose more breaking news events sooner than human journalists could track on their own through manual monitoring of social media.

Automated stories

Since 2014, we have automated text stories from structured sets of data using natural language generation (NLG). We began with corporate earnings stories for all publicly traded companies in the United States, increasing our output by a factor of 10 and increasing the liquidity of the companies we covered. We have since applied similar technology to over a dozen sports previews and game recaps globally.

Real-time transcriptions

Software developed by Trint and employing machine learning is enabling us to transcribe videos in real time, slashing the time previously spent creating transcripts for broadcast video. We are now working to marry this technology with live video streams and also integrate automatic translation to multiple languages.

AP story summaries

We are exploring how summarization technology can help us automatically generate different versions of text stories to serve a variety of digital uses. Our current project creates short summaries of longer text articles and delivers them to editors for review, streamlining a process that was previously all manual.

Image recognition

Image recognition software can improve the keywords on AP photos, including the millions of photos in our archive, and improve our system for finding and recommending images to editors. We have tested whether these tools can help keep graphic content out of our image feeds or help identify athletes by jersey numbers. This will create the first editorially-defined taxonomy for the news industry.

Automated shotlists

We're applying computer vision technology from Vidrovr to videos to identify major political and celebrity figures and to accurately time-stamp soundbites. This is helping us streamline the previous process of manually examining our video news feeds to create text “shotlists” for our customers to use as a guide to the content of our news video.

Leveraging AI to advance the power of facts