Predicting User Engagement

Primary supervisor

Abhinav Dhall

Is the user paying attention? Is the content engaging enough?

 

The degree of concentration, enthusiasm, optimism, and passion displayed by individual(s) while interacting with a
machine is referred to as ‘user engagement’. Engagement is a positive psychological state characterized by active behavioral participation, positive emotional experiences, and intense cognitive focus. Being able to detect engagement and/or attention has wide applications in consumer commerce, smart cars, augmented reality etc. 

 

This project deals with developing multimodal neural networks for predicting engagement and attention of user.

Student cohort

Single Semester
Double Semester

Aim/outline

Develop engagement and attention prediction using deep learning and ideas from affective computing.

URLs/references

1. Towards Engagement Prediction: A Cross-Modality Dual-Pipeline Approach using Visual and Audio Features, ACM ICMI 2024.

2. Do i have your attention: A large scale engagement prediction dataset and baselines, ACM ICMI 2023

Required knowledge

Python programming

Python programming

Should have credited NLP or Intelligent Image & Video Analysis or Deep Learning or Machine Learning unit (exceptions can be made in case relevant experience can be demonstrated)