AYLIEN Announces Text Analysis API, a Suite of NLP, Information Retrieval, and Machine Learning APIs to Extract Insights from Documents

Date: 17/2/2014

DUBLIN, February 17, 2014- AYLIEN, Inc., a Dublin-based technology firm backed by SOS Ventures, this week announced the availability of its Text Analysis API, a suite of eight Natural Language Processing, Information Retrieval and Machine Learning APIs that enable developers and news organizations to extract meaningful insights from nearly any document.

“The concept of the Semantic Web is crucial to the evolution of the web in general, but existing technology hasn’t kept up with that vision,” founder Parsa Ghaffari said.” In order to build the platform of the future, we need to build the technology to support that platform. It starts with giving developers and news organizations the tools they need to build platforms that adapt to the needs of their users. The Text Analysis API is the first step in building a web in which machines communicate with each other in meaningful ways.”


AYLIEN’s Text Analysis API offers distinct advantages over existing solutions, most notably with automatic hashtag suggestions for social media platforms. The package consists of eight APIs, each with unique capabilities:

  • Article Extraction: strips HTML documents of ads, navigation elements, and other extraneous information, leaving only text and embedded content such as video and images.extract
  • Article Summarization: extracts key sentences from a document and combines them to form a clear, concise summary.extract
  • Classification: classifies a document according to IPTC NewsCode standards, using a database of more than 500 categories.extract
  • Entity Extraction: extracts entities such as people, location, and organizations, and values such as URLs, emails, phone numbers, currency amounts and percentages mentioned in a document.extract
  • Concept Extraction: extracts concepts from a document, linking them to both relevant DBPedia and Linked Data entries, and semantic types such as DBPedia and schema.org types.extract
  • Language Detection: detects the language of a document from a database of 62 languages, presenting the information in ISO 639-1 format.extract
  • Sentiment Analysis: detects sentiment in a document, either in positive or negative terms, or in terms of subjectivity or objectivity.extract
  • Hashtag Suggestion: automatically suggests relevant hashtags for stories shared on social media platforms for greater discoverability.extract

The Text Analysis API delivers highly relevant information at record speed, surfacing new information almost immediately after it appears on, for example, Wikipedia. Classification adheres to a universal standard, eliminating miscommunication between platforms. Using the API consists merely of creating a Mashape account and subscribing to the API through its homepage. Pricing is aggressive, and does not require long-term contracts. A plan is available to students, educators, and researchers free of charge for the first six months.

Learn More

A demo of the Text Analysis API is available here, and an overview and FAQ section is available on our page. A press kit is available for download here.

Parsa Ghaffari, Founder
503 Regus, Harcourt Road, Dublin 2, Ireland

Press kit

Including company logo, team photos and product screenshots.


Learn more

To learn more about us, please visit:


For all press and media enquiries, please contact us: