Do I Have Your Attention: A Large Scale Engagement Prediction Dataset and Baselines
This work addresses the need for robust engagement prediction systems in real-world applications like education or customer service, but it is incremental as it primarily provides a new dataset and baseline methods.
The authors tackled the problem of predicting user engagement in human-machine interactions by introducing EngageNet, a large-scale dataset with 31 hours of data from 127 participants under varied conditions, and found that features like action units and eye gaze are useful for engagement prediction, with the dataset validated on an external benchmark.
The degree of concentration, enthusiasm, optimism, and passion displayed by individual(s) while interacting with a machine is referred to as `user engagement'. Engagement comprises of behavioral, cognitive, and affect related cues. To create engagement prediction systems that can work in real-world conditions, it is quintessential to learn from rich, diverse datasets. To this end, a large scale multi-faceted engagement in the wild dataset EngageNet is proposed. 31 hours duration data of 127 participants representing different illumination conditions are recorded. Thorough experiments are performed exploring the applicability of different features, action units, eye gaze, head pose, and MARLIN. Data from user interactions (question-answer) are analyzed to understand the relationship between effective learning and user engagement. To further validate the rich nature of the dataset, evaluation is also performed on the EngageWild dataset. The experiments show the usefulness of the proposed dataset. The code, models, and dataset link are publicly available at https://github.com/engagenet/engagenet_baselines.