Panel Orientation: Platform News Products (June 2020)

Published: June 1, 2020

The purpose of this document is to provide participants of our News Ranking Review Panels with information on each platform news product being reviewed by the project. NewsQ selected eight news products to examine and from which to collect data:

This review has focused mainly on documentation available from news product pages. We aim to update this orientation as more information becomes available; suggestions are welcome.

How to Use This Document

The following document provides overviews for each news product, mostly from the perspective of the goals expressed by platform owners themselves, with background for each product (vis-a-vis news); its process; and, how it works.

Four aspects have been selected for our overviews to support conversations related to news ranking and recommendations systems online:

  • Technological Interface: Is the product oriented to desktop or mobile?
  • Content Recommendation: Do articles appearing within the news product appear due to algorithmic processing alone, or is there human curation?
  • Content Guidelines: Do the news products offer rationales related to the content recommendation, including mission statements for the products or a description of their content-related processes?
  • Customized COVID-19 Policy: Has the product developed a specific policy related to COVID-19 content?

Each product overview starts with an information box to allow for quick scanning, like the one below:

Interface Orientation: [✓] Desktop [✗] Not Mobile
Content Recommendation: [✓] Algorithmic [✓] Human
Content Guidelines: [✓]Exists
Customized COVID-19 Policy: [✓] Present

A check mark ✓ indicates that the news product incorporates the stated dimension. When there is an ✗, the product does not focus on this feature or have this feature in a way that we have been able to find related documentation.

At the bottom of each section, we include links to archived versions of the documents from which we summarized our overview.

Note: The information in the respective overviews relate to each news product only and, unless otherwise specified, does not refer to other products or services by each platform.

Alphabet: Google News

Interface Orientation: [✓]Desktop [✓]Mobile
Content Recommendation: [✓]Algorithmic [*]Human (Special Coverage)
Content Guidelines: [✓]Exists
Customized COVID-19 Policy:[✓]Present

Background. Google News primarily uses algorithms to select and rank news content. These algorithms choose what all users see in the Top Stories and Full Coverage sections, and they personalize content for each user in sections like For You and Favorites.

Members of the Google News staff are able to add temporary topics for special circumstances, like events or elections. They also choose news topics and publications to highlight in the Newsstand tab of the Google News App.

According to the platform, the essential purpose of the product is “to help everyone understand the world by connecting people with high quality news from a variety of perspectives.”

Google News states it aims to “help you make sense of the news” by:

  • “using technology to connect you to information,”
  • “providing Access to content and multiple perspectives,”
  • “elevating trustworthy information,” 
  • “fighting misrepresentative and deceptive practice.”

Google News also says it aims to “help sustain a healthy news ecosystem” by:

  • “building and strengthening audiences for high-quality news”;
  • “collaborating with the news industry to drive innovation.”

Ranking Factors and Process

Screenshot of Google News categories on desktop (29 May 2020)

Google News offers a number of general news categories that are available for every user. The content available in Top Stories is chosen algorithmically and only varies depending on language and regional settings. 

Content is also personalized in the Discover and For You sections based on user-specified interest about topics, location, and publishers. Depending on account settings, Google News can suggest content based on user activity. 

Google News describes its ranking process as one in which its algorithms weigh a host of factors. It identifies its primary factors as:

  • relevance,
  • interests,
  • location,
  • prominence,
  • authoritativeness,
  • freshness, and
  • usability.

Ranking in Google News is determined by the following factors

  • relevance (Relevance to search terms),
  • location (Google uses location to help find content relevant to a user’s area, such as Local stories),
  • prominence (Noteworthy news events as signaled by trending articles or stories, as well as coverage being prominently featured by publishers),
  • authoritativeness (Authoritativeness signals are designed to help surface pages that “demonstrate expertise, authoritativeness and trustworthiness on a given topic”), and
  • freshness (Freshness refers to when the article was published and when it is more useful to have up-to-date content over an older article).

In addition to the factors above, the For You tab is ranked based on: 

  • usability (usability assesses page load times, how easy it is to view content on the site, if the site is formatted for different devices, etc.);
  • interests (depending on account settings, individual interests may help determine results in sections such as Discover or For You in Google News).

Google News emphasizes that it “elevates news from authoritative sources” and that it “requires publishers to be transparent and accountable in order to be represented in news results.” Google News also states that it “uses technology to sort massive amounts of content to connect you with important, relevant, and useful news.” [Emphasis added].

Content Labels

Google News uses labels to help classify and sort information. Publishers are advised to apply labels to their entire site as well as different parts of their site. Labels are also algorithmically applied to a publisher’s site.

The labels that publishers can apply themselves are: 

  • Opinion,
  • Satire,
  • User-generated,
  • Press release, and
  • Blog

Information found in this section is adapted from the following documents: How Google News stories are selected, Building news experiences, How news works on Google, Presenting news in helpful ways, Ranking within Google News, What does each label mean?

Alphabet: YouTube

Interface Orientation: [✓]Desktop [✓]Mobile
Content Recommendation: [✓]Algorithmic
Content Guidelines: [✓]Exists
Customized COVID-19 Policy: [✓]Present

Background. YouTube is a video sharing site that was acquired by Google in 2006 and is regarded as the second-largest search engine in the world, after Google Search itself. News on the site can be viewed as a video carousel, or “shelf,” that includes Breaking News, Top News and, currently, COVID-19 News

YouTube defines its values based on “Four Essential Freedoms”: 

  1. Freedom of Expression: “We believe people should be able to speak freely, share opinions, foster open dialogue, and that creative freedom leads to new voices, formats and possibilities.”
  2. Freedom of Information: “We believe everyone should have easy, open access to information and that video is a powerful force for education, building understanding, and documenting world events, big and small.”
  3. Freedom of Opportunity: “We believe everyone should have a chance to be discovered, build a business and succeed on their own terms, and that people—not gatekeepers—decide what’s popular.”
  4. Freedom to Belong: “We believe everyone should be able to find communities of support, break down barriers, transcend borders and come together around shared interests and passions.”

Ranking Factors & Process

YouTube’s Breaking News section uses an algorithm to display curated content to all users. This process is the same as the Top Stories section of Google News. News from the Latest tab of the YouTube app for TV features personalized algorithmically chosen content using the same process as the Discover and For You section of Google News. While YouTube does not provide explicit information about its algorithms’ ranking factors and process, it does provide some information on what kinds of content violate its policies. 

YouTube’s “news shelf. A news shelf is a video carousel that groups videos together running left to right.

YouTube COVID-19 “news shelf” example (26 May 2020).

Breaking News. During breaking news events, a news shelf with videos related to that event may appear on the homepage. This shelf can be deleted by the user and will not appear if a user is under 18. 

Top News. For users who search for news-related content, a Top News shelf may appear with videos from news sources that follow Google’s content policy.

COVID-19. The COVID-19 shelf includes news stories from “authoritative sources” and “local health authorities.” 

Information Panels. Context around the news may also be displayed on YouTube in the form of “information panels” which are snippets of text that appear alongside search results related to specific topics that are frequently subject to misinformation. The panel may also appear with a link to a third-party partner’s website for more information. 

Screenshot of an Information Panel related to COVID-19 from May 26, 2020.
  • Health information & COVID-19. Searches related to COVID-19 may appear alongside panels with information from “authoritative” sources such as the WHO, the CDC, and certain health ministries.
  • Publisher context. For channels from publicly or government-funded news sources, a panel may appear with publisher information related to funding sources as well as a link to their Wikipedia page. 
Screenshot of “publisher context” information box at the bottom of a news video (26 May 2020).

Policies and Safety section. Content that violates any of the Community Guidelines can be flagged by users to be reviewed by YouTube staff.

These include: 

  • nudity or sexual content;
  • harmful or dangerous content;
  • hateful content;
  • violent or graphic content,
  • harassment and cyberbullying;
  • spam, misleading metadata, and scams;
  • threats;
  • copyright;
  • privacy;
  • impersonation; and
  • child safety.

Information found in this section is adapted from the following documents: YouTube Essentials, YouTube About, Meet the seven most popular search engines in the world, Presenting news in helpful ways, Policy and Safety, Breaking news and Top news on YouTube, Info panel giving topical context, Health information panels, Information panel providing publisher content, Content Policies.

Apple News

Interface Orientation: [✓]Desktop [✓]Mobile
Content Recommendation: [✓]Algorithmic [✓]Human
Content Guidelines: [✓]Exists
Customized COVID-19 Policy: [✗]Unable to find

Background. Apple News is an algorithmically and human-determined ranking and recommendation system for news content. It can be accessed via desktop app at or as the “Apple News” mobile app. The homepage presents Top Stories in the Today section. Scrolling through Apple’s Today section, past Top Stories, takes users past a number of other sections (e.g., Politics, Business) that either populate by default or that the user selected to follow. Each section displays previews for a certain number of stories as the user scrolls past.

At the bottom of the app, there are three main sections: Today, News+ (which allows users to dive deeper into certain publications), and Following (which allows users to follow certain topics or beats).

Content on the service is also curated by topic. A set number of sections show up by default; other sections allow users to find news in areas they have explicitly selected to follow in the app (See the Apple News+ description).

Screenshot from Apple News Top stories, Trending Stories and For You (29 May 2020).

Ranking Factors and Process

Apple editorial staff chooses five stories to be featured in the Top Stories section of Apple News. The team reportedly selects from a pool of between 100 and 200 pitches per day. The Apple editorial team also curates a selection of featured stories. 

Algorithms are used to select content for the Trending Stories section. News content is also personalized using algorithms when users follow, unfollow, or block categories. 

Information found in this section is adapted from the following documents: Apple News, View news stories chosen just for you on iPhone, Auditing News Curation Systems: A Case Study Examining Algorithmic and Editorial Logic in Apple News, Apple News’s Radical Approach: Humans Over Machines.

Facebook News (News Tab and Today In)

Interface Orientation: [*]Limited Desktop [✓]Mobile
Content Recommendation: [✓]Algorithmic [✓]Human
Content Guidelines: [✓]Exists
Customized COVID-19 Policy: [✓]Present

Background. Facebook News is currently available in the United States on the Facebook app. The feature is integrated into the app as a separate tab from the newsfeed, and users can control the news sections that appear in the app. News content for the app is chosen both algorithmically and by a small team of staff journalists. 

Image from Facebook News site (accessed May 29, 2020).

News Sections currently include: 

  • Daily Features,
  • Today In,
  • Suggested for You,
  • Science & Tech,
  • Health,
  • Business,
  • Entertainment,
  • Sports,
  • Spotlight: Coronavirus (COVID-19).

Spotlight: Coronavirus. During the coronavirus pandemic, Facebook News has been curating content related to COVID-19 as a part of its Spotlight section. This section can also be controlled by users. 

Today In. Facebook’s Today In section is designed to connect people with local news, updates, weather, events, and other news. See the full list of cities compatible with this feature. 

Selection of news pages and publishers

Facebook News chooses publishers that produce coverage across four main categories

  • General News (Outlets that publish across a range of topics);
  • Topical News (Outlets that specialize in coverage areas, e.g., business);
  • Diverse News (Outlets focused on five racial/ethnic groups as defined by the US Census: Black/African-American; Latino/Hispanic; Asian; American Indian and Alaska Native; and Native Hawaiian and Other Pacific Islander);
  • Local News (Local outlets that meet Facebook’s integrity criteria).

For a publisher to be considered in the above categories their news page must first meet criteria to be included in the News Page Index. These criteria include: 

  • reporting on current events or timely information,
  • citations or links to factual sources,
  • pages that primarily publish content that is neither aggregated nor user-generated. 

Publishers must also be determined to be above a readership threshold; this number is defined differently across the four news categories.

Publishers must meet integrity standards which look at factors such as:

  • misinformation;
  • community standards violations (e.g., hate speech);
  • clickbait, engagement bait, and scraped content.

Ranking Factors & Process

Algorithmically Curated Content. Facebook algorithmically personalizes Facebook News with similar signals that dictate the main Facebook feed. These include past interests, topics, and publishers as well as engagement with news pages. Users can also access algorithmically curated local news by changing their location settings. 

Human Curated Content. Facebook is working with a team of journalists with experience working in a variety of newsrooms who are responsible for choosing the daily top stories according to developed guidelines. 

According to Facebook, topics are chosen based on: 

  • prevalence,
  • interest,
  • impact, and
  • diversity.

They state that they choose stories based on: 

  • facts,
  • diverse voices,
  • original reporting,
  • on-the-record sourcing,
  • timeliness,
  • depth and context,
  • fairness,
  • local reporting.

COVID-19 Info Center. The same team of journalists is also responsible for curating news content on the COVID-19 info center page following the same guidelines detailed above. In addition, they are responsible for featuring content that provides context around the pandemic as well as community information for both the info center and Facebook News. 

Information found in this section is adapted from the following documents: Facebook FAQFacebook’s Today In Expands US CitiesToday In AvailabilityHow Facebook News WorksNews Page IndexHow News Feed WorksCOVID-19 Info Center.

Microsoft: Bing News

Interface Orientation: [✓]Desktop [✓]Mobile
Content Recommendation: [✓]Algorithmic [✓]Human
Content Guidelines:[✓]Exists
Customized COVID-19 Policy: [✗]Unable to find

Background. Bing News is a Microsoft product that uses an algorithmically-determined ranking and recommendation system for news content. It can be accessed via web at or in the news section of the “Microsoft Bing Search” mobile app. The homepage presents Top Stories. Content on the service is also curated by topic by choosing interests to follow such as news, sports, and weather. Bing news is divided into categories which can be seen in the sidebar of the site page, including: For you, Top Stories, Sports, U.S. Local, World, Science, Technology, Entertainment, Politics, and Business.

To be eligible as a news source in Bing News, publishers must meet certain requirements and adhere to best practices as outlined by the PubHub Guidelines

Non-news sites are automatically disqualified from inclusion as well as sites that do not publish with regular frequency and those that do not meet certain grammar standards. These are defined in the PubHub Guidelines as follows:

  • “Non-news sites designed primarily to market products or services”;
  • “Sites with a primary purpose of unauthorized news or content aggregation”;
  • “Sites that do not publish with some level of frequency”;
  • “Sites publishing content that does not adhere to basic standards of grammar, punctuation, sentence structure, spelling, and word usage.”

Bing’s PubHub Guidelines also identify the following journalistic best practices which sites must adhere to if they are to be included as a news source: 

A) Accountability and transparency. Sites must provide easily identifiable and accessible ownership and contact information, including:

  • publisher name,
  • physical address,
  • email address, and
  • phone number

B) Content rights and responsibility. Sites are responsible for the content on their site and must have legal rights to publish.

C) Attribution and representation. Sites must provide information about authorship, source attribution, and must clearly label content. These guidelines include:

  • “Clear, verifiable authorship,”
  • “Bylines must primarily use the full names of writers,”
  • “Sources must be provided for facts, quotes, and opinions,”
  • “Headlines and link text must accurately represent the connected content,”
  • “Site content consistently reflects the stated purpose and theme of the site,”
  • “Commentary, opinion, and reviews must be clearly labeled.”

Ranking Factors & Process

Content is algorithmically curated based on many factors including:

  • source authority,
  • newsworthiness,
  • originality,
  • relevance.

Bing News can be personalized for each user based on their settings which include:

  • language,
  • country or region,
  • location.
Desktop version of Bing News settings (29 May 2020).

The desktop version of Bing News allows users to further personalize the news experience by choosing personal interests to follow.

News interests search bar on the desktop version of Bing News (29 May 2020).

Content Labeling. Bing News categorizes news content to identify “traditional news reporting” from other content like analysis and opinion. Labels are both provided by publishers (according to standards set by The Trust Project) or by Bing which scans the article:

  • Analysis (“Based on factual reporting, though it may incorporate the expertise of the author and offer interpretations and conclusions”);
  • Backgrounder (“Provides context, definition, and detail on a news topic”);
  • Fact check (“Checks a specific statement or set of statements asserted as fact”);
  • In-depth (“Provides a deep look at a news-related topic and takes 10 minutes or more to read”);
  • Live update (“Receives continuous updates while an event is developing”);
  • Local source (“Publisher is based at or near the location of the story”);
  • Most-cited (“Article being linked to the most within a collection of news articles”);
  • Opinion (“Advocates for ideas and draws conclusions based on the author’s interpretation of facts and data”);
  • Review (“An assessment or critique of a service, product, or creative endeavor”);
  • Satire (“Humorous/satirical article not intended to be understood as factual”).

Information found in this section is adapted from the following documents: Bing News PubHub, How Bing labels news articles, About interests on Bing.

Microsoft: Microsoft News

Interface Orientation: [✓]Desktop [✗]Not Mobile
Content Recommendation: [✓]Algorithmic [✓]Human
Content Guidelines: [✓]Exists
Customized COVID-19 Policy: [✗]Not found

Background. Microsoft News is a human and machine-determined ranking and recommendation system which curates content for, The Edge browser start page, the Microsoft News app, and more. It can be accessed via web at or as the “Microsoft News” mobile app.

The Edge start page presents Headlines and content on the service is curated by topic. A set number of sections show up by default; other sections allow users to find news in areas they have explicitly selected to follow in the app; because it allows for individual sign-in, the products may reflect personal interest given their statement that “user choice and personalization are essential to the experience.”  

Rather than a mission statement, one can find a Microsoft News belief statement that includes: 

  • “A free, well-funded press plays a critical role in society”;
  • “In delivering unparalleled breadth and depth of high-quality journalism”;
  • “That trustworthy and diverse perspectives matter”;
  • “In the power of combining human and machine curation”;
  • “User choice and personalization are essential to the experience.”

Microsoft News Editorial Standards also states the following 6 core commitments as fundamental to their curation practices: 

  • truth,
  • transparency,
  • integrity,
  • independence,
  • privacy,
  • quality.

Ranking Factors & Process

Microsoft News content is curated by hundreds of editors in combination with algorithms that personalize based on user preferences. Microsoft News publishes content from 1200 publishers that meet specific editorial requirements such as: 

  • adherence to strict editorial guidelines,
  • legally obtained information, and
  • proper sourcing.

Microsoft News states that it labels content in an effort to clearly flag to readers when a news article contains advertising or opinions. According to Microsoft’s policy, any content that has been commissioned “by or for clients” will be properly labeled to ensure a clear delineation from their editorial content. 

Content that contains the following will be filtered from the available content where possible: 

  • vulgar language;
  • language or images meant to shock the audience;
  • discriminatory language;
  • inappropriate depictions of sexual activity;
  • nudity or eroticism;
  • gratuitous reference to or images of drug paraphernalia;
  • images depicting consumption of alcohol or smoking;
  • coverage of bestiality;
  • detailed descriptions and gratuitous images of murders and violent crimes, or the identity of crime victims unless the victims publicly identifies themselves;
  • excessive blood in images;
  • images of dead bodies or body bags;
  • religious representation that may cause offense;
  • images gratuitously highlighting deformity or “medical voyeurism”;
  • descriptions of suicide methods;
  • images that depict animals in distress.

The programming model also attempts to represent diversity as defined by “the appreciation of differences in age, gender, ethnicity, religion, disability, sexual orientation, education, socio-economic background and national origin.” 

Recently, Microsoft announced that AI would replace the work of Microsoft externally contracted news producers; according to the Seattle Times, the following are examples of the work that the human contractors performed:

  • identifying trending news stories from dozens of publishing partners;
  • helping to optimize the content by rewriting headlines;
  • adding better accompanying photographs or slide show to stories;
  • planning content;
  • maintaining the editorial calendars of partner news websites and assigning content to them.

Information found in this section is adapted from the following documents: Microsoft News – Editorial Standards.

Twitter Explore – News

Interface Orientation: [✓]Desktop [✓]Mobile
Content Recommendation: [✓]Algorithmic [*]Limited Human (Twitter Moments)
Content Guidelines: [*]Limited documentation
Customized COVID-19 Policy: [✓]Present

Screenshot of the Twitter News app (29 May 2020).

Background. Twitter’s Explore Tab and News Tab is an algorithmically determined ranking and recommendation system for news content. It can be accessed via web at Explore ( or on the Twitter mobile app. Twitter publishes little information on its Explore tab in general, and on its News tab in particular. 

To reach a news section, the user has to navigate to the Explore section on desktop or the search icon on the Twitter app. The main section that then appears is For You. Then the user can navigate to five other sections: Trending, News, Sports, Fun, or Entertainment.  

Twitter has also added a COVID-19 section to its mobile and desktop apps. The COVID-19 section involves human curation under guidelines and principles outlined for Twitter Moments and described below. 

The company outlines safety principles when posting to Twitter, and to its approach regarding Safety on Twitter. The principles are described as follows: 

  • Twitter stands for freedom of expression for everyone“;
  • We do not take sides. We show sides. Every side.“;
  • We treat everyone equally: the same Twitter Rules apply to all“;
  • You have the right to express yourself on Twitter if you adhere to these rules.”

Ranking Factors & Process 

Human Curation with Twitter Moments. The Twitter curation team uses Twitter Moments to highlight “remarkable” content that appeals to a broad audience. These Moments may run in parallel with large world events, and when a topic is particularly controversial, the team will choose topics that are big stories in mainstream media or trending heavily on Twitter.

Moments may also be curated by individuals or Twitter partners who must also meet curatorial standards. 

The policy highlights three main factors that influence curation choices on Twitter Moments

  • bias (“Twitter curators should not advance their own viewpoints, but rather reflect the discussion as it appears on our platform.”);
  • accuracy (“When dealing with news or newsworthy content, we want to highlight quality Tweets that represent accurate information.”);
  • standards (“Profanity, violence, nudity, and other types of potentially sensitive content should be avoided except where it is necessary to tell a newsworthy story.”) .

Misleading Information Policy. Decisions about adding labels and warnings for “misleading information” such as synthetic tweets and manipulated media — as well as potential removal of those tweets — are assessed using the following questions

  • “Are the media synthetic or manipulated?” 
  • “Are the media shared in a deceptive manner?”
  • “Is the content likely to impact public safety or cause serious harm?”

Labels contain links to either Twitter-curated content pages (see Twitter Moments above) or to external sources with additional information giving context around the tweet content. During the COVID-19 pandemic, tweets containing potentially harmful content will also have these labels. 

Twitter takes action when tweets fall into three categories: 

Excerpt from Twitter blog post, “Updating our Approach to Misleading Information” (accessed 29 May 2020).
  1. Misleading information — “statements or assertions that have been confirmed to be false or misleading by subject-matter experts, such as public health authorities.”
  2. Disputed claims — “statements or assertions in which the accuracy, truthfulness, or credibility of the claim is contested or unknown.”
  3. Unverified claims — “information (which could be true or false) that is unconfirmed at the time it is shared.”

There is little information about the process that Twitter uses to identify tweets that fall into these categories. Twitter does state that the platform in part relies on “trusted partners” to help with this and that the process is continuing to be developed. 

COVID-19 and Twitter. Twitter is using a blend of automated and human processes to address the spread of harmful messages related to COVID-19. Automated processes surface content that is likely to cause harm, and human teams manually review reports of content that need additional context. See Twitter’s definition of what constitutes harmful messaging. 

From COVID-19 event page (25 May 2020).

Twitter has also set up a dedicated COVID-19 event page with “credible” COVID-19 information. This feature appears for all users at the top of Twitter’s Home timeline.

Information found in this section is adapted from the following documents: Twitter ExploreSafety on TwitterTwitter Moments guidelines and principlesUpdating our approach to misleading informationBuilding rules in public: Our approach to synthetic & manipulated mediaAn update on our continuity strategy during COVID-19,Coronavirus: Staying safe and informed on TwitterStepping up our work to protect the public conversation around Covid-19.

Yahoo News

Interface Orientation: [✓]Desktop [✗]No Mobile
Content Recommendation: [✓]Algorithmic [✓]Human
Content Guidelines: [✗]Unable to find
Customized COVID-19 Policy: [✗]Unable to find

Background. Content on Yahoo News is both human curated and algorithmically-determined. It can be accessed at The site has a number of default sections including: 

  • News Home,
  • Coronavirus*,
  • US,
  • World,
  • Politics,
  • 2020 Election*,
  • Health,
  • Science,
  • Originals.

*The asterisks indicate temporary sections.

The Originals section includes a dropdown menu with subsections: 

Screenshot of Originals dropdown menu (25 May 2020).

Researchers were unable to find any information related to Yahoo’s ranking and recommendation processes. 

Information found in this section is adapted from the homepage of Yahoo News: NewsQ researchers were unable to find public-facing information about ranking factors and process for the platform to date. We will update this section when possible.

Thanks to members of the Google News Initiative and Facebook for providing feedback on aspects of this orientation.

As stated above, this version of the review has focused mainly on documentation available from news product pages. We aim to update this orientation as more information becomes available; suggestions are welcome at hello [at] newsq [dot] net.