University of Twente Student Theses
Review Hijacking In Online Shops
Simionescu, S.O. (2024) Review Hijacking In Online Shops.
|
PDF
2MB |
| Abstract: | Customer reviews and ratings are critical decision-making tools for online customers in the rapidly growing e-commerce space. However, review hijacking, opinion spamming, and suppressing negative reviews are a few of many deceitful tactics that can undermine the legitimacy of the review ecosystem. Review hijacking is the practice of replacing a popular product with a different one to increase sales and popularity. The system does not operate as if it were a novel listing, as it is merely a modification of an existing product. By doing this, the product advertised ends up using unrelated reviews, and because of the number of reviews, it usually ends up showing more often in its category. This paper addresses the issue of review hijacking or review-reuse by utilizing machine learning models to determine whether a review aligns with the product. During the research, a RoBERTa model and a base BERT model for text classification were used with the aim of achieving higher accuracy in review hijacking detection with the RoBERTa model. Moreover, this paper presents a visualization concept, utilizing the implemented machine learning model, that exhibits superior performance. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/101754 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page