Speech emotion recognition and text sentiment analysis for financial distress prediction

Abstract

In recent years, there has been an increasing interest in text sentiment analysis and speech emotion recognition in finance due to their potential to capture the intentions and opinions of corporate stakeholders, such as managers and investors. A considerable performance improvement in forecasting company financial performance was achieved by taking textual sentiment into account. However, far too little attention has been paid to managerial emotional states and their potential contribution to financial distress prediction. This study seeks to address this problem by proposing a deep learning architecture that uniquely combines managerial emotional states extracted using speech emotion recognition with FinBERT-based sentiment analysis of earnings conference call transcripts. Thus, the obtained information is fused with traditional financial indicators to achieve a more accurate prediction of financial distress. The proposed model is validated using 1278 earnings conference calls of the 40 largest US companies. The findings of this study provide evidence on the essential role of managerial emotions in predicting financial distress, even when compared with sentiment indicators obtained from text. The experimental results also demonstrate the high accuracy of the proposed model compared with state-of-the-art prediction models.

XEmoAccent: Embracing Diversity in Cross-Accent Emotion Recognition Using Deep Learning

“…The potential applications of this framework are in online education [62], family household robot assistant [63], noise detection for human robots [64], stress identification for air traffic controllers [65], financial distress management [66], and remote health care [67]. For instance, during the online education system, the proposed system can be used to enhance the teaching quality due to cross-culture background of students and teachers [62].…”

“…The proposed cross-accent SER can enhance their inter-communications [65]. Furthermore, cross-accent SER can enhance the estimates of emotions in a diverse financial distress, social interaction, and healthcare management [66], [67].…”

UniC: a Dataset for Emotion Analysis of Videos with Multimodal and Unimodal Labels

“…Furthermore, spontaneous speech features authentic emotion expressions which might be more subtle and more challenging to distinguish than acted emotions [21]. Since speech is always intertwined with text, they usually come together in emotion-related tasks [22].…”

Temporal Convolutional Networks and BERT-Based Multi-Label Emotion Analysis for Financial Forecasting

“…Such fine-tuning procedures are now common practice, and, actually, the model is also used within the experimental framework of the present work. Furthermore, in [8], a deep learning architecture that leverages managerial emotion representations formed by speech recognition using FinBERT-based sentiment analysis applied to earnings conference call transcripts is proposed. In [9], text-based emotion recognition with a focus on deep learning techniques is explored.…”