Revisiting Review Depth in Search for Helpful Online Reviews

Date

2023-01-03

Contributor

Advisor

Department

Instructor

Depositor

Speaker

Researcher

Consultant

Interviewer

Narrator

Transcriber

Annotator

Journal Title

Journal ISSN

Volume Title

Publisher

Volume

Number/Issue

Starting Page

2200

Ending Page

Alternative Title

Abstract

This study investigates online review features that constitute review depth and assess their impacts on review helpfulness. It develops a model capturing the moderating effects of heuristic and systematic cues of an online review on the relationship between review length and its helpfulness. In particular, this study examines the moderating effects of price, product type, review readability and the presence of two-sided arguments. For testing the model, a dataset of 568,454 reviews from 256,059 different reviewers on Amazon.com were analyzed. The variables were operationalized using test processing techniques and relationships were empirically tested using regression and machine learning models. The results highlight significant moderating effects of review readability and the presence of two-sided arguments on the relationship between review length and its helpfulness. However, the results did not confirm the moderating effects of price and product type. This article discusses the significant implications for a better understanding of review depth and helpfulness in e-commerce platforms.

Description

Keywords

Data Analytics, Data Mining, and Machine Learning for Social Media, consumer decision-making, readability, review depth, review helpfulness, two-sided argument

Citation

Extent

10

Format

Geographic Location

Time Period

Related To

Proceedings of the 56th Hawaii International Conference on System Sciences

Related To (URI)

Table of Contents

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Rights Holder

Local Contexts

Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.