News API release notes
AYLIEN News API allows you to search, source and understand news content from across the web in real time. Using Machine Learning and NLP-driven technology, News API users can stay ahead of the curve by collecting relevant content and extracting what’s important to them.
Search (Fig 1.)
Our powerful search and filtering capabilities allow users to source and collect what news matters most to them. Users can build their queries on a variety of data points:
- Entities (people, places, products, organizations, etc.)
- Categories (industry-specific taxonomies)
- Time (down to minute level, and up to 60 days of historical data)
- Outlets (news sources and blogs)
- Authors (journalists and influencers)
- Writer Sentiment (positive, negative or neutral opinion)
- Title level
- Body level (Entity and Aspect-level on the way)
- Language (English, Spanish, Portuguese, Italian, French and German, with more to come)
Our users can build complex search queries to query the news like they would a database, giving them tailored streams of news and content.
- Related Stories and Coverages
- Clustering to remove or group duplicates and near duplicates
Enrichments (Fig 2.)
We go beyond just sourcing news. We extract the key data points from news making them usable and providing an enriched data source that can be used to power intelligent news aggregators, content-driven apps or news dashboards.
- Entities mentioned
- Categories the content is grouped in
- Sentiment Analysis of the writer’s opinion
- Language Detection
- Automated article summaries
- Automatically generated for each story
These key data points are extracted in a matter of seconds from the time the article is published giving you fast access to the key data points in the world’s news content.
Insights (Fig 3.)
By looking at the massive amounts of content that we collect and analyze in aggregate, we also provide some further important insights that cannot be obtained by looking at news articles individually.
- Social performance:
- We continuously monitor social media to find and count mentions of each story, and profile the performance over time to give users and understanding of the popularity of the story
- Sentiment and category breakdown:
- We leverage the data points we extract form every story to let users answer questions like; What % of articles are talking about what category? or What % of articles are positive, negative or neutral?
- Volume over time:
- We provide historical data up to 60 days allowed which allows our users know, how many stories match a query in a given time window
- Word clouds:
- Our word cloud capabilities let users get a snapshot of what the most used keywords or entities are for a given time period?
- Informative histograms can be easily created to provide snapshots about a query, an author, outlet or even vertical
We currently monitor thousands of sources from across the world. We’ll be adding more sources during the beta period. Given the amount of noise out there, our focus is on quality over quantity and providing access to high quality trusted sources.
While the product is still technically in beta it is fully functional and production ready. We are rolling it out in a tiered beta in order to scale the number of sources we’re monitoring and this is reflected in the Beta pricing.
Integrating with the API is simple, and in addition to our extensive and interactive documentation, we’re providing code snippets for most popular programming languages to help developers get up and running faster. Results are provided in a well-structured JSON format, and we plan to release SDKs shortly after the beta launch which will make the process even easier.
We charge a monthly base subscription fee of $49. From then on the pricing is based on the number of stories you collect and analyze, with the first 10,000 stories included in your subscription fee. The more stories you collect the less you pay per story.