Application of natural language processing in client feedback using facial sentimental analysis and opinion mining

Author

Murindagomo, Divine R.

Title

Application of natural language processing in client feedback using facial sentimental analysis and opinion mining

Abstract

The research topic focuses on creating a machine learning-based customer facial sentimental analysis system for client feedback regarding their level of satisfaction from business services. The goal of this approach is to automate the process of determining emotions in real time, by analyzing the various features of a face such as eyebrows, eyes, mouth, and other features, and mapping them to a set of emotions such as anger, fear, surprise, sadness and happiness. Businesses can adjust their marketing efforts and services that are customer satisfactory by identifying various customer feedback. Various machine learning algorithms, such as Naïve Bayes, linear regression, support vector machine, and deep learning, will be employed in this study to analyze consumer feedback data and customer sentiment into different categories. This research will also look into how various data preprocessing approaches and feature selection methods affect the performance of machine learning models. To ensure the system's performance and industry applicability, it will be tested using real-world customer data from an organization such as a bank. The findings of this study will give companies with an effective tool for client sentimental analysis and high quality products. It will also help enhance machine learning approaches for client sentiment analysis, which can be used in fields other than e-commerce organizations.

Date

June 2024

Publisher

BUSE

Keywords

Customer sentiment analysis

Machine learning

Natural language processing

Client feedback

Supervisor

Mr. H. Chikwiriro