Begun as a research project from the Royal Melbourne Institute of Technology and the University of Technology Dresden, WebKnox is an ontology-driven fact extraction engine built to provide direct, fast, and complete answers to questions on any topic a user can think of. To answer a question WebKnox uses external services that might have previously provided an answer or computes an answer using its knowledge base. If those options fail, WebKnox tries to find an answer on the fly.
WebKnox hosts a suite of REST APIs delivering a range of web services. The WebKnox Text-Processing API allows applications to process natural language texts. The API is able to detect the language of a given text, grade the quality of an article, find mentions of locations and other entities, find mentions of dates, auto-correct a text, detect a textâ€™s sentiment, and tag a text with part-of-speech tags.
Sentiment analysis is an important community engagement metric, and with APIs like the WebKnox Text Processing API, it is an analytical technique now open to any business. This tutorial examines how to use the WebKnox Text Processing API to conduct a sentiment analysis and to create a visualization that summarizes audience reactions.
If you have created a powerful API-as-product, do you automatically have a business model you can monetize? German startup Webknox aims to answer this question and is worth following to see how they turn a powerful data product into an investable commodity. ProgrammableWeb caught up with Dr David Urbansky at the recent API World conference to talk about the very early days of this new API enterprise and to discuss the road to success that may lay ahead.