Readerscope: Turning Articles Into Actionable Insights
2019 Finalist

Readerscope: Turning Articles Into Actionable Insights

The New York Times

New York, United States

Category Best Use of Data Analytics

Media associated with this campaign

Overview of this campaign

All brands seek relevance, and NYT offers a unique lens for understanding what matters to the world. What our audience reads reveals what matters.

Despite having this valuable data, we weren’t able to use it to drive the business. Advertising clients are desperate for new angles of insight into their consumers, but we could only access stats about a single URL or article.

Previous data classifications (keywords, sections) were driven by what a publisher thinks are relevant categories. Readerscope’s topic model uses natural language processing to group articles that are alike. Indexing algorithms further connect these topics and articles to the most relevant audiences and locations.

Readerscope was built to:

  • Develop a topic model that accurately describes what articles are about, using natural language processing. For instance, Readerscope doesn’t say “CEOs mostly read the Technology section.”  It lets us break down technology into discrete sup-topics like cybersecurity, consumer devices and Silicon Valley investments

  • Show the differences in topics, articles and geographies among our audience segments. Who follows articles on the latest blockbusters more - millennials or new parents?

  • Design a widely usable interface so the entire ad department can query this data and use it throughout the sales cycle from RFP response to ideation to media targeting

  • Allow for client customization and the ability to ingest first-party client data, so we can see Readerscope insights for a segment they care about

All of this is in service of having a widely-available, unique tool to drive creative ideation and smart media strategies by showing more about what resonates with a specific audience.

 


Results for this campaign

Readerscope has driven commercial results in a number of ways:

First, it generates insights that surprise our clients and showcase the depth of Times data, one of our key assets. The topic clustering surfaces what topics occur frequently in our coverage - for instance, a distinction between sports scandals, sports business news and sporting event results. It also links that to audience: younger men tend to read more about the scandals, older men the scores.

Second, these insights are actionable for clients. As one of many examples, a pharmaceutical company wanted to align with Times content, but was unsure where to target ads. Readerscope revealed that “wellness seekers” (their primary audience) read health articles, but also significant amounts of science and home coverage. This guided the client to a diverse and performative set of placements.

Importantly, Readerscope is scaled. Every member of our 450+ advertising department is able to access the tool and derive insights, bringing this real data to all of our clients and elevating our conversations.

Finally, it is a launchpad. We are now building a proprietary targeting capability that will target media against articles classified in a given topic, enabling advertisers to target a topic like “sports scandals”. And, we are engaging with more and more clients to ingest their first-party segments to provide meaningful intelligence about their consumer base using Readerscope.

 


Contact

To contact a company representative about this campaign, click here for the INMA Member Directory