Discovery and Exploration

Out of the box, Discovery provides a pre-enriched collection of 2 months of internet news content

Share this post:

Key points:

  • Aggregate content from sources across the web and make sense of unstructured data.
  • Watson can quickly provide answers to inquiries about current news.
  • Create four Watson Discovery News API queries in under 5 minutes.

Learn more about Discovery Service

It used to be easy – pick up a newspaper with your morning coffee and stay up-to-date on the day’s news. In the cognitive era, where hundreds of thousands of news articles are generated every day, developers and data analysts are up against a fire hose of unstructured content.

Aggregating content from numerous sources across the web is a challenge and even with your news all in one place, it’s daunting to make sense of all that unstructured data. Traditional keyword search only get you so far, differentiating “Apple” the technology company from “apple” the fruit for instance. And even with a list of relevant articles, searching through all of them to find patterns and trends takes teams of people and lots of time.

IBM Watson® is an avid “reader” of web articles and offers an API that can quickly provide answers to inquiries about current news. For instance, if you’re curious about artificial intelligence (AI), ask industry-specific questions like:

  • What are the latest news articles about the artificial intelligence industry?
  • Who are the most commonly mentioned people in news articles about artificial intelligence?
  • What are the newest company acquisitions in the field of artificial intelligence?

Watson already has the answers and each question can be answered with a single query to the Watson Discovery News API. Watch a video demo of how to create four queries in under 5 minutes.

Out of the box, Discovery Service provides a pre-enriched collection of the past 60 days of news content on the internet. Already enriched with Watson natural language understanding (NLU) technology, articles have been categorized, analyzed for sentiment and syntax, and the major entities, concepts, and relationships have been identified. These structured NLU enrichments are useful to understand the context and meaning of unstructured text and can be used to fine-tune your queries.

Ask Watson for news articles on a defined topic, in a defined date range, and with a specific type of entity in their title (or more). Explore the metrics of the world’s news to seek insights like the most common concepts mentioned in articles on a certain topic. Filter out news articles so Watson only returns results from respected and established news sources. Whether you’re interested in financial news, sports headlines, or the latest political happenings, Watson Discovery News API will return valuable and enlightening results.

And our news content is just one possible data set to explore. Discovery Service has a “bring your own data” capability where you can easily upload your own set of documents and explore them in the same way. Upload your latest tweets or company’s product reviews and uncover trends and patterns in what your customers are saying.

Learn more about Discovery Service

Associate Offering Manager - Watson Platform

More stories
June 21, 2018

How AI is helping Autodesk transform their procurement processes

Autodesk is developing Autodesk Contract Explorer (ACE), using Watson Compare & Comply. Compare & Comply is trained on contract structure and language – and it contextually understands PDFs, the documents of business.

Continue reading

June 15, 2018

IBM Watson Studio named winner for best innovation in deep learning

We're thrilled to share that IBM Watson Studio was named winner for the "Best innovation in Deep Learning" at the world-renowned, independently-judged AIconics awards in London this week. IBM won the award for "being a pioneer in deep learning, helping to drive machine learning applications towards the true potential of AI."

Continue reading

June 8, 2018

How to prepare and clean data through quick operations, data profiles and visualization

IBM Watson Studio and Watson Knowledge Catalog include Data Refinery for self-service data preparation. Data Refinery puts data pre-processing and feature engineering in the hands of data scientists, enabling faster data insights.

Continue reading