An Emotion Detection system that processes input provided by the user in text format and deciphers the associated emotion expressed.
EmotionDetectionFinal.mp4
Emotion detection involves the process extracting the finer emotions: joy, sadness, anger, and so on, from statements rather than the simple polarity that sentiment analysis provides. This makes emotion detection a very important branch of study and businesses use such systems widely for their AI based recommendation systems, automated chat bots, and so on. For this project, I used the Emotion Predict function of IBM's Watson AI Natural Language Processing Library.
The following tasks were done as part of this project:
- Created an Emotion Detection application using the functions from embeddable AI libraries.
- Extracted relevant information from the output received from the function.
- Tested and packaged the application created using the Emotion Detection function..
- Completed web deployment of the application using Flask.
- Incorporated error handling in the application to account for invalid input to the application.
- Written codes that are in perfect compliance with PEP8 guidelines, getting 10/10 score in static code analysis.
- Python
- HTML5
- JavaScript
- Requests
- IBM Watson AI NLP Library
- Flask
For this project, you need access to Watson AI Natural Language Processing Library
- Go to https://www.ibm.com/products/natural-language-processing
- Click on 'Start your Free Guided Trial'
- The next 5 pages will give you many options to choose from. Choose each option as shown below:
- Click Next
- Go to Step 3 and generate a container URL by logging in or signing up:
- After log-in, a pop-up showing the container URL will be shown. Copy the URL and save it for future use.
- Fork this repository
- Clone it to your local PC
- In the repository, go to EmotionDetection & open emotion_detection.py in a code editor
- Inside emotion_detector function, paste the container URL you saved to the variable 'base_url' & uncomment it.
- Save the file, open commandline, navigate to the repository and run server.py. Your app will be hosted on web.
- Go to localhost address '127.0.0.1:5000' on any browser to use the app.
This project was done as part of the certification Developing Applications with Python and Flask by IBM on Coursera.