Essential Site Maintenance: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at [email protected] in case you face any issues.

loading page

Evaluating Significant Features in Context-Aware Multimodal Emotion Recognition with XAI Methods
  • +1
  • Talal Shaikh,
  • Aaishwarya Khalane,
  • Rikesh Makwana,
  • Abrar Ullah
Talal Shaikh
Heriot-Watt University - Dubai Campus

Corresponding Author:[email protected]

Author Profile
Aaishwarya Khalane
Heriot-Watt University - Dubai Campus
Author Profile
Rikesh Makwana
Heriot-Watt University - Dubai Campus
Author Profile
Abrar Ullah
Heriot-Watt University - Dubai Campus
Author Profile

Abstract

Analysis of human emotions from multimodal data for making critical decisions is an emerging area of research. The evolution of deep learning algorithms has improved the potential for extracting value from multimodal data. However, these algorithms do not often explain how certain outputs from the data are produced. This study focuses on the risks of using black-box deep learning models for critical tasks, such as emotion recognition, and describes how human understandable interpretations of these models are extremely important. This study utilizes one of the largest multimodal datasets available - CMU-MOSEI. Many researchers have used the pre-extracted features provided by the CMU Multimodal SDK with black-box deep learning models making it difficult to interpret the contribution of individual features. This study describes the implications of individual features from various modalities (audio, video, text) in Context-Aware Multimodal Emotion Recognition. It describes the process of curating reduced feature models by using the GradientSHAP XAI method. These reduced models with highly contributing features achieve comparable and even better results compared to their corresponding all feature models as well as the baseline model GraphMFN proving that carefully selecting significant features can help improve the model robustness and performance and in turn make it trustworthy.
10 Jan 2023Submitted to Expert Systems
17 Jan 2023Submission Checks Completed
17 Jan 2023Assigned to Editor
14 Feb 2023Reviewer(s) Assigned
12 Mar 2023Review(s) Completed, Editorial Evaluation Pending
13 Mar 2023Editorial Decision: Revise Major
05 Jun 20231st Revision Received
12 Jun 2023Submission Checks Completed
12 Jun 2023Assigned to Editor
14 Jun 2023Reviewer(s) Assigned
03 Jul 2023Review(s) Completed, Editorial Evaluation Pending
04 Jul 2023Editorial Decision: Accept