An NLP-Deep Learning Approach for Product Rating Prediction Based on Online Reviews and Product Features

Abstract

An NLP-Deep Learning approach for Product Rating Prediction Based on Online Reviews and Product FeaturesTolou AmirifarThis study focuses on predicting the popularity of a product based on its overall rating score.Unlike previous studies that focus on predicting the review rating based on sentiment analysis and polarity of the reviews, in this thesis, the effect of product features in determining its popularity is directly measured and analyzed in order to predict its overall rating score. To this end, a methodology consisting of three phases is considered. Phase 1 predicts the overall rating by feeding the general product features, extracted from the online product information available on Amazon webpages to a Deep Learning (DL) model. Phase 2 identifies other features that customers care about the most by applying the Named Entity Recognition (NER) algorithm to the customer online reviews; and lastly, Phase 3 feeds the combination of the general and custom features to the DL model to predict the overall rating score of the product.The experimental results on a dataset of laptop products, collected from Amazon, indicate an impressive performance of the proposed approach, which is mainly attributed to including custom product features to the inputs of the DL algorithm when compared with the existing method. More precisely, the proposed model could achieve the highest accuracy score of 84.01%, 84.68% for recall, 87.63% for precision, and 84.06% for F1 score. Applying this procedure could help businesses identify the specific areas of strengths and weaknesses of their products or services from the perspective of their customers, allowing them to thrive in today's competitive markets. from the Department of Supply Chain and Business Technology Management at the John Molson School of Business, for their noble supervision, support with full encouragement and enthusiasm, valuable suggestions, and motivating advice. This thesis would not have been possible without your trust in me and your guidance from the initial step in research that allowed me to develop an understanding of the subject. I am grateful for my parents whose constant love and support keep me motivated and confident. My accomplishments and success are because they believed in me. Finally, I owe my deepest gratitude to my husband, Ali. I am forever thankful for the unconditional love and support throughout the entire thesis process and every day. v Contents List of Figures .

Design and Implementation of an Intelligent Hybrid Assessment Framework for Supplier Risk

“…NLP technology enables the automated processing and analysis of large volumes of unstructured text data [35]. By utilizing advanced methods such as sentiment analysis and topic detection [36], NLP can rapidly extract key information from sources like news reports, social media, and customer feedback, providing businesses with more comprehensive and real-time market analysis for assessing supplier risks [37]. At the same time, NLP technology compensates for the shortcomings of expert assessments in handling large-scale data and real-time data analysis, and also enhances the objectivity and accuracy of the overall assessment framework.…”