skip to Main Content

Topics and Entities

Filter the news and detect unseen patterns by using IPTC Media Topics and named entities.

About the metadata

We have teamed up with a UK-based tech company that combines state-of-the-art natural language processing with a comprehensive knowledgebase of real-life facts to help extract topics and named entities from news articles in real-time.

The topics and entities are delivered as metatags along with the corresponding articles in your Opoint news feed. The data can be added to both Firehose and StoredSearch feeds.

Topics

The International Press Telecommunications Council (IPTC) was established in 1965, and its primary focus is to develop and promote industry standards for the exchange of news data.

We have chosen the IPTC Media Topics as our default taxonomy. It is a constantly updated taxonomy of over 1,200 terms developed specifically for the categorisation of media content, and it is updated at least once a year.

Topic tags include:

  • Label – the name of the IPTC Media Topic
  • Media Topic ID – the unique IPTC Media Code
  • Score – the overall confidence that article revolves around the topic.

Entities

We analyse the entire article to identify all persons, locations, and organisations. The process includes advanced disambiguation to avoid delivering duplicate entities.

Entity tags include:

  • Entity type – person, location, or organisation
  • Entity – name of person, location, or organisation
  • Wikidata ID – a link to additional information about the entity (when possible).

Code sample

- topics_and_entities:  {
     - topics: [
          - {
               label: "economy, business and finance > economy",
               mediatopic_id: "20000344",
               score: 0.6528
            },
          - {
               label: "economy, business and finance > economic sector > financial and business service > banking",
               mediatopic_id: "20000274",
               score: 0.5842
            },
          - {
               label: "science and technology > social sciences > economics",
               mediatopic_id: "20000745",
               score: 0.5563
            }
     ],
     - entities: {
          - location: [
               - {
                    entity: "United States",
                    wikidata_id: "Q30"
                 },
               - {
                    entity: "Japan",
                    wikidata_id: "Q17"
                 },
               - {
                    entity: "London",
                    wikidata_id: "Q84"
                 }
          ],
          - organization: [
               - {
                    entity: "Bank of England",
                    wikidata_id: "Q183231",
                 },
               - {
                    entity: "Bloomberg",
                    wikidata_id: "Q13977",
                 }
          ],
          - person: [
               - {
                    entity: "Jerome Powell",
                    wikidata_id: "Q6182718",
                 },
               - {
                    entity: "Andrew Bailey",
                    wikidata_id: "Q4756258"
                 },
               - {
                    entity: "Haruhiko Kuroda",
                    wikidata_id: "Q5244721"
                 }
          ]
     }
}

“Knowing that hundreds of thousands of users around the world depend on the content provided by Opoint Technology, we put all our efforts into maintaining a high quality, stable deliveries and the best customer support in the market.”

Jon Anders Tangnes, COO at Opoint Technology

Back To Top