Use Swift to interpret unstructured data from Hacker News

Get the code View the demo

Summary

Getting insights from large amounts of unstructured data sources is getting easier to do because of machine-learning technologies. Learn how to pull data points – concepts, entities, categories, keywords, sentiment, emotion, etc. – from Hacker News articles using natural-language service calls from a Swift-based application.

Description

NLP enables developers to organize and structure knowledge to perform tasks such as named entity recognition, relationship extraction, sentiment analysis, and speech recognition. The application of NLP is being used in many fields, including medicine, law, and others where there are vast amounts of unstructured data users need to quickly pull information from.

Typically, we have seen applications that utilize NLP APIs built in Python or Node.js. This journey has a twist by introducing you to embedding machine-learning capabilities in a Swift-based application. You will use the Watson™ Natural Language Understanding API to interpret unstructured text from Hacker News to identify the latest trends and key topic areas discussed by developers. You will see how easy it is to call this service from a Swift application.

Flow

flow

  1. The user deploys the application to IBM Cloud®.
  2. Application loads the data from the Hacker News API.
  3. The user interacts with the application UI using a browser.
  4. When the user performs any action, UI calls the server application API, which uses the Watson NLU service to analyze the respective news article.

Instructions

Ready to put this code pattern to use? Complete details on how to get started running and using this application are in the README.