Created by team ASU-FITers on February 03, 2023

We track emotional states within text, then we provide a recommendation or simply show an ad that is suitable with what the user really feels. This project is using many  machine learning algorithms to train a classifier. We deployed cohere embedding system API. The backend service was built using python django framework. The motivation behind this work is that a big share of people spends a long time online, and although they express their negative emotions freely, they don’t actively take action to improve them. Even when they have positive emotions, they don’t make use of their excitement and energy. On the other hand, many local activities and services are available out there, but not everyone knows about them. Besides, the truth is that a single type of activity isn’t suitable for all. So, a strategy must be followed to recommend a specific activity to people with a specific type of emotions. Many companies and organizations will be interested in advertising, especially the ones that offer life coaching services, trip organizers, fitness and massage centers, comedy shows, therapists, and many other activity organizers and human well-being services.

Category tags: