Features influencing the concept of trust in online reviews | IEEE Conference Publication | IEEE Xplore

Features influencing the concept of trust in online reviews


Abstract:

The number of online reviews increase considerably on platforms and have a significant impact on purchase decisions. These reviews can represent both an opportunity and a...Show More

Abstract:

The number of online reviews increase considerably on platforms and have a significant impact on purchase decisions. These reviews can represent both an opportunity and a threat for a company. It is therefore essential to detect among the huge quantity of reviews, those which are unreliable. A question then arises: how to detect deceptive reviews? In this paper, we were interested in the concept of review trustworthiness. To detect the reliability of reviews, we give our definition of the reliability and propose a machine learning approach based on different classifiers. We consider that the information related to the comment itself (sentiments, linguistic elements etc.), and that relating to the user (activity, experience, sociability etc.) play a role on reliability of the review. We propose to include in our method these two classes of information. We did a series of experiments on the Yelp open dataset. Furthermore, in these experiments we have compared the performances of our trust model with a second model based only on the review’s content (using TF-IDF vectorisation method). Our results show on the one hand that the information we used (comments+users) play a role in determining the reliability of the review, and on the other hand that we achieve better performances with our features (i.e. without using TF-IDF method).
Date of Conference: 22-25 June 2022
Date Added to IEEE Xplore: 14 July 2022
ISBN Information:

ISSN Information:

Conference Location: Madrid, Spain
No metrics found for this document.

I. INTRODUCTION

In the last decades, the evolution of the Internet has enabled the creation of new communication tools, such as social networks for companies as well as for individuals. The business sector quickly understood the importance of using social media for financial purposes and for managing their reputation. By giving their opinions on social networks, users influence the reputation of companies, particularly in sectors such as e-shopping, hotels, restaurants, travel and tourism. Whether these opinions are positive or negative, users are paying attention to them. For instance, TripAdvisor and Yelp are two platforms for business evaluation. TripAdvisor is the benchmark for tourism ratings. In addition to its booking service, TripAdvisor has more than 200 million consumer reviews of about hotels, restaurants, and destinations. The American company Yelp, is very successful because its platform makes very easy and quick to publish its opinion or assessment via its smartphone concerning any type of shops and services. Thus, the importance of consumer reviews generated on the Internet is no longer to be proven, and its importance is such that a real economy has developed around online reviews. In this new context, there are abuses (false consumer opinions, or paid opinions). Whether fake positive opinions posted by a professional, or negative opinions written by a competitor or any other malicious person, these comments mislead the consumer and leads to unfair competition. These opinions can represent both an opportunity and a threat for a company, and therefore have a major impact on turnover, customer loyalty, company reputation and even sustainability. In this article, we were interested in detecting the reliability/trustworthiness of reviews. The questions addressed in this article are:

How the concept of review trustworthiness can be modeled?

What are the features that determine the trustworthiness of the review?

Does the reviewer plays a role in the trustworthiness?

Which role opinion plays in the notion of trustworthiness?

What role the reviewer’s gender plays in the notion of trustworthiness?

Usage
Select a Year
2025

View as

Total usage sinceJul 2022:100
00.20.40.60.811.2JanFebMarAprMayJunJulAugSepOctNovDec100000000000
Year Total:1
Data is updated monthly. Usage includes PDF downloads and HTML views.

References

References is not available for this document.