Customer Feedback Analysis Using Aspect Based Sentiment Analysis and Fuzzy Analytic Hierarchy Process
Priya Sinha, Sayak Roychowdhury, Bhosale Akshay Tanaji · 2024
Customer feedback analysis has become crucial in the area of business analytics in recent years. Proper assessment of customers’ perception of products and services helps organizations make data-driven decisions and maintain a competitive edge. In this article, we have developed a decision support framework to help consumers make informed choices, using Natural Language Processing (NLP) on customer feedback. Our proposed technique first uses Aspect-based Sentiment Analysis (ABSA)to identify key features and the corresponding sentiments. We have used Bi-directional Encoder Representations from Transformers (BERT) to derive sentiment scores for different criteria across different alternatives. Then, a multi-criteria decision-making (MCDM) technique such as Fuzzy Analytical Hierarchy Process (FAHP) is used for ranking of preferred alternatives. The framework is demonstrated using a case study on customer opinions shared on social media about several airlines.