Dialog speech sentiment classification for imbalanced datasets

TL;DR

This paper addresses the challenge of detecting underrepresented sentiments in dialog speech datasets by analyzing single and bi-modal features and proposing a novel architecture that achieves state-of-the-art results on an imbalanced dataset.

Contribution

It introduces a new architecture with a learning rate scheduler and monitoring criteria for improved sentiment classification in imbalanced dialog speech datasets.

Findings

Achieved state-of-the-art results on the SWITCHBOARD dataset.

Identified key factors aiding sentiment detection in imbalanced datasets.

Demonstrated effectiveness of bi-modal analysis for underrepresented sentiments.

Abstract

Speech is the most common way humans express their feelings, and sentiment analysis is the use of tools such as natural language processing and computational algorithms to identify the polarity of these feelings. Even though this field has seen tremendous advancements in the last two decades, the task of effectively detecting under represented sentiments in different kinds of datasets is still a challenging task. In this paper, we use single and bi-modal analysis of short dialog utterances and gain insights on the main factors that aid in sentiment detection, particularly in the underrepresented classes, in datasets with and without inherent sentiment component. Furthermore, we propose an architecture which uses a learning rate scheduler and different monitoring criteria and provides state-of-the-art results for the SWITCHBOARD imbalanced sentiment dataset.