Co-authored with Evaline Ju

Whenever we check any level of news — from local to international, we see are headlines regarding the COVID-19 pandemic. Most of these articles report new cases, death counts, and government policies, all of which contribute to an increasingly negative atmosphere. Among these news articles, people often find it difficult to identify progress in fighting the coronavirus, such as research for cures and vaccinations or patient recovery stories.

Image for post
Image for post

We wanted to find more positive news about the pandemic using our Watson Natural Language Understanding (NLU) sentiment analysis capability. However, as developers, we are aware that stock sentiment models are not trained to handle data in the healthcare domain which could sometimes limit their capability to identify positive news articles related to the pandemic. Our sentiment models are trained on social media and user reviews data, where any mention of “coronavirus” may trigger negative sentiment. Certain domains like healthcare have specific vocabulary usage and rules as compared to those like social media. …

Image for post
Image for post

AI and machine learning systems are considered as black box especially when they are being consumed with an API. Users may wonder: how did the system predict a certain output and what contributed to the prediction? IBM Watson Natural Language Understanding now makes it easier to understand the results of the categorization feature, by giving explanations for each predicted label. This explanation is provided in the form of snippets from the input text itself that contributed towards the results.

Categories is a hierarchical classification system that predicts labels up to 5 levels of hierarchy. Now, with a simple toggle `explanation: true`, users will be able to get explanations for the predictions. This feature can also be used with our newly released customization of categories. For those who are using this customization option and looking to improve their model, this explanation can come in handy, as it can point towards the text snippets that cause the system to predict incorrect labels. …


Gaurav Kumbhat

Machine Learning Engineer — IBM Watson Natural Language Understanding

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store