Accelerate the value of multicloud with collaborative DevSecOps Learn more

Use advanced natural language processing and tone analysis to extract meaningful insights

Summary

Learn how to extract insights from natural language text, such as category, concepts, emotion, entities, keywords, sentiment, top positive sentences, and word clouds by using IBM® Watson™ Natural Language Understanding and Watson Tone Analyzer.

Description

Watson Natural Language Understanding includes a set of text analytics features that can be used to extract meanings from unstructured data such as a text file. Watson Tone Analyzer understands emotions and communication styles in a text. By combining the capabilities of both services, you can extract meaningful insights in the form of a natural language understanding analysis report from a natural language transcript. The transcript used in this code pattern is generated from a video recording of the IBM Q1 2019 earnings meeting. The report consists of a sentiment analysis of the meeting, top positive sentences spoken in the meeting, and word clouds based on keywords, using a Python Flask runtime.

After completing the code pattern, you understand how to:

  • Use advanced natural language processing to analyze text and extract metadata from content such as concepts, entities, keywords, categories, sentiment, and emotion
  • Leverage Watson Tone Analyzer cognitive linguistic analysis to identify a variety of tones at both the sentence and document level
  • Connect applications directly to Cloud Object Storage

Flow

Use advanced NLP flow diagram

  1. The transcribed text from the previous code pattern of the series is retrieved from IBM Cloud Object Storage.
  2. Watson Natural Language Understanding and Watson Tone Analyzer are used to extract insights from the text.
  3. The response from Watson Natural Language Understanding and Watson Tone Analyzer is analyzed by the application, and a report is generated.
  4. The user can download the report, which consists of the textual insights.

Instructions

Find the detailed steps for this pattern in the readme file. The steps show you how to:

  1. Clone the GitHub repository.
  2. Create the Watson services.
  3. Add the credentials to the application.
  4. Deploy the application.
  5. Run the application.

This code pattern is part of the Extracting insights from videos with IBM Watson use case series, which showcases the solution on extracting meaningful insights from videos using Watson Speech to Text, Watson Natural Language Processing, and Watson Tone Analyzer services.