Automatic detection of fake reviews at marketplaces using expert-based features and consumers’ reactions
The article presents the results of a practical study of the features of fake reviews that are described by marketers and other experts. Due to the abundance of fake reviews on marketplaces, consumer trust falls not only in the seller or platform, but in the genre itself. The paper presents the resu...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
State University of Management
2024-10-01
|
| Series: | Цифровая социология |
| Subjects: | |
| Online Access: | https://digitalsociology.guu.ru/jour/article/view/327 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540666115129344 |
|---|---|
| author | A. N. Borodulina E. V. Mikhalkova |
| author_facet | A. N. Borodulina E. V. Mikhalkova |
| author_sort | A. N. Borodulina |
| collection | DOAJ |
| description | The article presents the results of a practical study of the features of fake reviews that are described by marketers and other experts. Due to the abundance of fake reviews on marketplaces, consumer trust falls not only in the seller or platform, but in the genre itself. The paper presents the results of automatic classification of reviews from Russian marketplaces into potentially fake and honest ones using modelling of features that experts call labels of a fake review (presence of template words, exclamation marks, emoji, positive sentiment), and machine learning algorithms. To solve the problem, a corpus of 6 288 texts from the Russian marketplaces Wildberries and Megamarket has been collected. The target variable (predicted class) is the ratio of likes and dislikes given to the review by other buyers. The best result is demonstrated by the support vector machine algorithm in binary classification into reviews with a low and high ratings (without neutral ones). The classification model confirms that the formal features identified by experts as indicating fake reviews indeed have predictive potential. The quality of the model is reduced by the imbalance in classes and insufficient number of reviews with buyer reactions in our corpus, which leaves room for further work. |
| format | Article |
| id | doaj-art-56f428f0e0d745fbbf0063a0a608b84b |
| institution | Kabale University |
| issn | 2658-347X 2713-1653 |
| language | Russian |
| publishDate | 2024-10-01 |
| publisher | State University of Management |
| record_format | Article |
| series | Цифровая социология |
| spelling | doaj-art-56f428f0e0d745fbbf0063a0a608b84b2025-02-04T16:32:35ZrusState University of ManagementЦифровая социология2658-347X2713-16532024-10-0173425210.26425/2658-347X-2024-7-3-42-52206Automatic detection of fake reviews at marketplaces using expert-based features and consumers’ reactionsA. N. Borodulina0E. V. Mikhalkova1Tyumen State UniversityEuropean University at St. PetersburgThe article presents the results of a practical study of the features of fake reviews that are described by marketers and other experts. Due to the abundance of fake reviews on marketplaces, consumer trust falls not only in the seller or platform, but in the genre itself. The paper presents the results of automatic classification of reviews from Russian marketplaces into potentially fake and honest ones using modelling of features that experts call labels of a fake review (presence of template words, exclamation marks, emoji, positive sentiment), and machine learning algorithms. To solve the problem, a corpus of 6 288 texts from the Russian marketplaces Wildberries and Megamarket has been collected. The target variable (predicted class) is the ratio of likes and dislikes given to the review by other buyers. The best result is demonstrated by the support vector machine algorithm in binary classification into reviews with a low and high ratings (without neutral ones). The classification model confirms that the formal features identified by experts as indicating fake reviews indeed have predictive potential. The quality of the model is reduced by the imbalance in classes and insufficient number of reviews with buyer reactions in our corpus, which leaves room for further work.https://digitalsociology.guu.ru/jour/article/view/327fake reviewmarketplaceconsumer trustdata analysisfeature modellingcomputational linguisticsmachine learningsvmbinary classification |
| spellingShingle | A. N. Borodulina E. V. Mikhalkova Automatic detection of fake reviews at marketplaces using expert-based features and consumers’ reactions Цифровая социология fake review marketplace consumer trust data analysis feature modelling computational linguistics machine learning svm binary classification |
| title | Automatic detection of fake reviews at marketplaces using expert-based features and consumers’ reactions |
| title_full | Automatic detection of fake reviews at marketplaces using expert-based features and consumers’ reactions |
| title_fullStr | Automatic detection of fake reviews at marketplaces using expert-based features and consumers’ reactions |
| title_full_unstemmed | Automatic detection of fake reviews at marketplaces using expert-based features and consumers’ reactions |
| title_short | Automatic detection of fake reviews at marketplaces using expert-based features and consumers’ reactions |
| title_sort | automatic detection of fake reviews at marketplaces using expert based features and consumers reactions |
| topic | fake review marketplace consumer trust data analysis feature modelling computational linguistics machine learning svm binary classification |
| url | https://digitalsociology.guu.ru/jour/article/view/327 |
| work_keys_str_mv | AT anborodulina automaticdetectionoffakereviewsatmarketplacesusingexpertbasedfeaturesandconsumersreactions AT evmikhalkova automaticdetectionoffakereviewsatmarketplacesusingexpertbasedfeaturesandconsumersreactions |