Hybrid Emotion Recognition: Enhancing Customer Interactions Through Acoustic and Textual Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wewelwala, Sahan Hewage, Sumanathilaka, T. G. D. K.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909555837894656
author Wewelwala, Sahan Hewage
Sumanathilaka, T. G. D. K.
author_facet Wewelwala, Sahan Hewage
Sumanathilaka, T. G. D. K.
contents This research presents a hybrid emotion recognition system integrating advanced Deep Learning, Natural Language Processing (NLP), and Large Language Models (LLMs) to analyze audio and textual data for enhancing customer interactions in contact centers. By combining acoustic features with textual sentiment analysis, the system achieves nuanced emotion detection, addressing the limitations of traditional approaches in understanding complex emotional states. Leveraging LSTM and CNN models for audio analysis and DistilBERT for textual evaluation, the methodology accommodates linguistic and cultural variations while ensuring real-time processing. Rigorous testing on diverse datasets demonstrates the system's robustness and accuracy, highlighting its potential to transform customer service by enabling personalized, empathetic interactions and improving operational efficiency. This research establishes a foundation for more intelligent and human-centric digital communication, redefining customer service standards.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid Emotion Recognition: Enhancing Customer Interactions Through Acoustic and Textual Analysis
Wewelwala, Sahan Hewage
Sumanathilaka, T. G. D. K.
Computation and Language
This research presents a hybrid emotion recognition system integrating advanced Deep Learning, Natural Language Processing (NLP), and Large Language Models (LLMs) to analyze audio and textual data for enhancing customer interactions in contact centers. By combining acoustic features with textual sentiment analysis, the system achieves nuanced emotion detection, addressing the limitations of traditional approaches in understanding complex emotional states. Leveraging LSTM and CNN models for audio analysis and DistilBERT for textual evaluation, the methodology accommodates linguistic and cultural variations while ensuring real-time processing. Rigorous testing on diverse datasets demonstrates the system's robustness and accuracy, highlighting its potential to transform customer service by enabling personalized, empathetic interactions and improving operational efficiency. This research establishes a foundation for more intelligent and human-centric digital communication, redefining customer service standards.
title Hybrid Emotion Recognition: Enhancing Customer Interactions Through Acoustic and Textual Analysis
topic Computation and Language
url https://arxiv.org/abs/2503.21927