Prediction of Customer Review's Helpfulness Based on Feature Engineering Driven Deep Learning Model
International Journal of Software Innovation
; 11(1):27-27, 2023.
Article
in English
| Web of Science | ID: covidwho-2235499
ABSTRACT
Online consumer reviews play a pivotal role in boosting online shopping. After Covid-19, the e-commerce industry has been grown exponentially. The e-commerce industry is greatly impacted by the online customer reviews, and a lot of work has been done in this regard to identify the usefulness of reviews for purchasing online products. In this proposed work, predicting helpfulness is taken as binary classification problem to identify the helpfulness of a review in context to structural, sentimental, and voting feature sets. In this study, the authors implemented various leading ML algorithms such as KNN, LR, GNB, LDA and CNN. In comparison to these algorithms and other existing state of art methods, CNN yielded better classification results, achieving highest accuracy of 95.27%. Besides, the performance of these models was also assessed in terms of precision, recall, F1 score, etc. The results shown in this paper demonstrate that proposed model will help the producers or service providers to improve and grow their business.
Full text:
Available
Collection:
Databases of international organizations
Database:
Web of Science
Type of study:
Prognostic study
Language:
English
Journal:
International Journal of Software Innovation
Year:
2023
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS