Year: 2023
Type: dissertation
Abstract: This study investigate the Sentiment Analysis for a Business Recommendation System for businesses that use Sentiment Analysis to make the buying experience better for customers. The system uses a set of around 100,000 Yelp reviews to look at customer ratings, comments, and reviews in order to make personalised suggestions. By using information from customer data, this method goes beyond traditional recommendation algorithms. The study uses advanced feature extraction methods like TF-IDF vectorization and BERT tokenization, along with machine learning techniques like DBScan, K-means, and K-Nearest Neighbor (KNN), to rate these models on their accuracy, precision, recall, and F1-score. The results show that the KNN model works best, especially when BERT tokenization is used. The model developed shows great potential. The project’s successfully opens the door for more research into personalised retail solutions that meet customers’ changing needs.
Source: NORMA
Author: Sisal, Akhil Bharat
Institution: National College of Ireland
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7043246274
