In the supersaturated media world, it is extremely difficult for news and media organisations to discover, track, sort and distribute content efficiently and effectively. Given the volume of content and the wide range of channels where we consume and share news, it has become more important for news and media companies to come up with innovative ways of curating, categorizing and distributing content.

  • Discover – Stay ahead of the curve on breaking news and popular articles

  • Tag – Tag and classify articles and content

  • Distribute – Find the best audience for your content, keep track of media contacts, their changing preferences, interests and popularity

Enrich your content discovery process while reducing the time spent on inefficient manual tasks.


Effectively managing online content is becoming increasingly difficult.


Text Analysis allows more intelligent and automatic discovery, tagging and distribution of content.

Find the needle in the haystack


Use Cases

Content Discovery

  • Stay ahead of the curve. Discover and distribute the most up to date and popular content available.
  • Automatically gather content from news sites, blogs, RSS feeds and social channels.


  • Automatically categorize, cluster and tag articles, press releases and news stories.
  • Move away from relying purely on key-word search.
  • Extract what matters in a piece of text and block out the noise.
  • Extract concepts from articles to get the full picture.
  • Identify and extract entities in text (mentions of people, places and things).

Smart Signature

  • Find the optimal targets for your content.
  • Automatically profile journalists and content creators based on their interests and writing styles from previous publications.
  • Identify content influencers for specific topics, industries and interests.

Process Improvement

  • Streamline the research process.
  • Automate mundane tasks like tagging, summarization and extraction.
  • Summarize articles, docs and URL’s into consumable snapshots.
  • Extract text and media (videos, images) from webpages.


The features listed below outline the API functions that are most commonly used in News and Media use cases.

Article Extraction

Cut down on research and discovery time and focus on what matters to you most. Remove all clutter and extract the main text and media from an article or URL.


Automatically classify your text and tag it according to IPTC NewsCode standards. There are over 500 industry standard categories to choose from.


Speed up the research and discovery process by automatically summarizing any piece of text into consumable chunks for a snapshot view of an article or document.

Entity Extraction

Extract entities (people, locations, organizations) or values (URLS, emails, phone numbers, currency amounts and percentages) which may be of interest.

Concept Extraction

Enhance the accuracy of your discovery process by identifying an authors intent with word sense disambiguation; does apple refer to the fruit or the company.

Batch Processing

Automatically process and analyze large numbers of documents, URL’s or articles all at once.