| Banerjee & Chua (2014) |
This study proposes several algorithms of identification of false reviews. Attention is paid to linguistic aspects of comprehension, level of detail, writing form, and cognitive indicators |
Tourism |
| Banerjee et al. (2015) |
This study investigates false reviews published on TripAdvisor. After completing a survey, users are invited to write fake hotel reviews |
Tourism |
| Cardoso, Silva & Almeida (2018) |
This paper is an exhaustive review of the content analysis methods of false review detection. To this end, the authors develop experiments based on Hotels |
Tourism |
| Chang et al. (2015) |
In this study, a rumor model is used to detect false reviews on the TripAdvisor platform based on the following three characteristics of the content: important attribute words, quantifiers, and the ratio of names and verbs. The proposed model reduces the possibility of obtaining false reviews |
Tourism |
| Deng & Chen (2014) |
This study focuses on the development of an algorithm, based on sentiment analysis, to identify false reviews of restaurants. The results demonstrate that the proposed algorithm has the predictive capacity of over 70% |
Tourism |
| Hunt (2015) |
This study focuses on the legal aspect of fake reviews and argues for the adoption of specific laws to prohibit the publication of false reviews |
Tourism |
|
Lappas, Sabnis & Valkanas (2016a) and Lappas, Sabnis & Valkanas (2016b)
|
The analysis is based on over 2.3 million comments from 4,709 hotels in 17 cities to understand the impact of false reviews on the visibility of establishments. The results suggest that, with only 50 false reviews in some markets, competitors can be overtaken in terms of visibility |
Tourism |
| Li, Feng & Zhang (2016) |
Based on the density of the reviews, as well as their semantic aspects and emotional aspects, this study creates an algorithm for false review detection based on review content applicable to the tourism industry |
Tourism |
| Munzel (2016) |
This study analyzes published reviews and rejected reviews taking into account the information about the author, age, and stars the user has been given in recently published reviews. The results emphasize the importance of the previous history of users who publish reviews for false review detection |
Tourism |
| Chen, Guo & Deng (2014) |
This study proposes an algorithm based on sentiment analysis to identify false reviews in restaurants. The results demonstrate that the proposed algorithm has the predictive capacity of 74% |
Restaurants - Hospitality Industry |
| Li et al. (2014) |
This study focuses on the Dianping, China’s largest restaurant review platform, and analyzes the dependencies among reviews, users, and IP addresses using an algorithm called Multi-typed Heterogeneous Collective Classification (MHCC), and then extends it to Collective Positive and Unlabeled learning (CPU) |
Restaurants - Hospitality Industry |
| Li et al. (2018) |
In this study, the Louvain community detection method is used to study online communities. The results suggest that false reviews predominate in profiles with low scores, and that the more followers a community has, the greater the number of false reviews |
Restaurants - Hospitality Industry |
| Luca & Zervas (2016) |
This study analyzes the reviews published on the Yelp site. The results demonstrate that only 16% of the reviews are filtered (those that more extreme, either positively or negatively). The restaurants that usually publish false reviews are those with fewer comments or negative comments. Restaurant chains usually publish fewer false reviews. Finally, more competitive restaurants are more likely to get false reviews |
Restaurants - Hospitality Industry |
| Elmurngi & Gherbi (2017) |
In this study, textual classification and sentiment analysis are used to identify false reviews in E-commerce. Four rating sentiment classification algorithms are compared: Naïve Bayes (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN-IBK), and Decision Tree (DT-J48). The results show that algorithms can effectively predict false reviews |
E-Commerce |
| Lin et al. (2014) |
This study proposes a new approach to identifying false reviews that is based on the content of the reviews and the behavior of the users. The results show that the proposed approach is more precise and accurate than current algorithms |
All Industries |
| Ramalingam & Chinnaiah (2018) |
This study reviews the latest algorithms of false profile detection in social networks |
All Industries |
| Zhang et al. (2016) |
This study analyzes non-verbal characteristics of users who write false reviews to create a predictive algorithm of detection of false reviews. The algorithm can complement the traditional method of detection of false reviews |
All Industries |
