NLP emotion detector

Category
Open source

What is it?

Natural Language Understanding is a collection of APIs that offer text analysis through natural language processing. This set of APIs can analyze text to help you understand its concepts, entities, keywords, sentiment, and more. Additionally, you can create a custom model for some APIs to get specific results that are tailored to your domain. This system is for demonstration purposes only and is not intended to process Personal Data.

The purpose of this project was to create a demonstration of different NLP processes and it was divided into two phases:

  1. Algorithm development
  2. Development of a web application

Algorithm development

This phase will cover the creation and testing of different NLP approaches.

NLP approaches that we would like to cover include:

  1. Emotion detection
  2. Entity detection (extracting dates, addresses, personal names)

Some of these approaches will require finding and exploring data, data preprocessing, model training, and similar.

Some NLP approaches have already been developed. These should be included in the web application only:

  1. Sentiment analysis
  2. Text categorization based on GCP categories
  3. Keyword extraction

This stage should last 1.5 to 2 months and includes:

  • Finding data sets
  • Exploratory data analysis
  • Exploring and testing different approaches. Reporting results.
  • Creating methods for inference

Note: Limited to English language only.

Web application

The web application consists of two parts:

  1. Application page for algorithm demonstration
  2. Dashboard for model retraining

Algorithm demonstration

You can find some inspiration regarding the application page for algorithm demonstration here:

https://natural-language-understanding-demo.ng.bluemix.net

https://www.ibm.com/demos/live/natural-language-understanding/self-service/home

The dashboard for model retraining should contain a page for data relabeling for different use cases (e.g. relabeling for sentiment, relabeling for emotion) as well as the relabeling trigger button.

Let’s get started.

Tell us what you’re working on, we’ll answer right away.

← Previous

Twitalyzr - Twitter stream

Other success stories

See all stories→
Email sentiment analysis
User projects

Email sentiment analysis

Read post →
Churn of business customers
User projects

Churn of business customers

Read post →
FAQ chatbot with back-office
User projects

FAQ chatbot with back-office

Read post →
Search ranking for a large-scale job platform
User projects

Search ranking for a large-scale job platform

Read post →