Detecting Fake Review with Rumor Model—Case Study in Hotel Review

Chang, Tien Chan; Hsu, Ping-Yu; Cheng, Ming Shien; Chung, Chen Yao; Chung, Yi Liang

doi:10.1007/978-3-319-23862-3_18

Cited by 10 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The studies summarized in Table 1 demonstrate the growing interest in the concept of fake reviews and social networking sites, particularly in the hospitality and tourism industries. Some of these studies (e.g., Banerjee & Chua, 2014;Cardoso, Silva & Almeida, 2018;Chang et al, 2015;Hunt, 2015;Lappas, Sabnis & Valkanas, 2016a;Lappas, Sabnis & Valkanas, 2016b;Li, Feng & Zhang, 2016;Munzel, 2016) focus on the Tourism industry category, while others fall into the hospitality industry category (Chen, Guo & Deng, 2014;Li et al, 2014;Li et al, 2018;Luca & Zervas, 2016). Some works (Lin et al, 2014;Zhang et al, 2016;Ramalingam & Chinnaiah, 2018) were included as part of the analysis because their results can be implemented in every industry that allows consumers to write reviews, including the tourism industry.…”

Section: Exploratory Analysis Of Resultsmentioning

confidence: 99%

“…First, most studies in the present systematic review of the literature focus on analysis of the algorithms of false review detection and their improvement. In these studies, large amounts of data from social communities such as TripAdvisor or Yelp are typically used (Chang et al, 2015;Li et al, 2014). The second most used methodology is sentiment analysis, focusing on the emotional aspects and feelings expressed in written reviews.…”

Section: Methodologies Used In Previous Researchmentioning

confidence: 99%

“…Here, the studies tend to focus on two types of content. On the one hand, some studies focus on the textual content of reviews, i.e., on their linguistic aspects, such as the ratio of nouns to verbs, the type of words or the attributes used to write false reviews Cardoso, Silva & Almeida, 2018;Chang et al, 2015;Chen, Guo & Deng, 2014;Elmurngi & Gherbi, 2017;Lappas, Sabnis & Valkanas, 2016a;Lappas, Sabnis & Valkanas, 2016b). On the other hand, there are studies that prioritize detecting behavioral and emotional characteristics of users who write false reviews (Banerjee & Chua, 2014;Li, Feng & Zhang, 2016;Li et al, 2018;Luca & Zervas, 2016;Zhang et al, 2016).…”

Section: Unit Of Analysismentioning

confidence: 99%

“…The discipline with the highest number of publications was Computer Science as can be seen in Table 4. There are a total of 11 publications that belong to the category (Chen, Guo & Deng, 2014;Chang et al, 2015).…”

Section: Scientometric Analysismentioning

confidence: 99%

See 3 more Smart Citations

The importance of behavioral data to identify online fake reviews for tourism businesses: a systematic review

Reyes-Menéndez

Saura

Filipe

2019

PeerJ Computer Science

View full text Add to dashboard Cite

In the last several decades, electronic word of mouth (eWOM) has been widely used by consumers on different digital platforms to gather feedback about products and services from previous customer behavior. However, this useful information is getting blurred by fake reviews—i.e., reviews that were created artificially and are thus not representative of real customer opinions. The present study aims to thoroughly investigate the phenomenon of fake online reviews in the tourism sector on social networking and online reviews sites. To this end, we conducted a systematic review of the literature on fake reviews for tourism businesses. Our focus was on previous studies that addressed the following two main topics: (i) tourism (ii) fake reviews. Scientific databases were used to collect relevant literature. The search terms “tourism” and “fake reviews” were applied. The database of Web of Science produced a total of 124 articles and, after the application of different filters following the PRISMA 2009 Flow diagram, the process resulted in the selection of 17 studies. Our results demonstrate that (i) the analysis of fake reviews is interdisciplinary, ranging from Computer Science to Business and Management, (ii) the methods are based on algorithms and sentiment analysis, while other methodologies are rarely used; and (iii) the current and future state of fraudulent detection is based on emotional approaches, semantic analysis and new technologies such as Blockchain. This study also provides helpful strategies to counteract the ubiquity of fake reviews for tourism businesses.

show abstract

Section: Exploratory Analysis Of Resultsmentioning

confidence: 99%

Section: Methodologies Used In Previous Researchmentioning

confidence: 99%

Section: Unit Of Analysismentioning

confidence: 99%

Section: Scientometric Analysismentioning

confidence: 99%

See 2 more Smart Citations

The importance of behavioral data to identify online fake reviews for tourism businesses: a systematic review

Reyes-Menéndez

Saura

Filipe

2019

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Several works have also investigated strategies to identify rumors amid non‐rumors (Oh et al, ; Zhang, Zhang et al, ). Cutting across these two lines of research, works such as Chang, Hsu, Cheng, Chung, & Chung () employed a rumor model to distinguish between genuine and deceptive reviews. Additionally, several works have attempted to detect deception in computer‐mediated communication (Ho et al, ; Zhou, Burgoon, Nunamaker, & Twitchell, ).…”

Section: Resultsmentioning

confidence: 99%

Reviewing the landscape of research on the threats to the quality of user‐generated content

Pal

Chua

2016

Proc. Assoc. Info. Sci. Tech.

View full text Add to dashboard Cite

The objective of the paper is to review and synthesize scholarly articles on the threats to the quality of usergenerated content (UGC). In this paper, threats to the quality of UGC are defined as the perpetration of misleading information caused by the lack of editorial control. They include deception, disinformation, manipulation, misinformation and rumors whose veracity cannot be easily established. In particular, this paper identifies (a) the research objectives that had been investigated, (b) the research methods that had been employed, and (c) the disciplines that studied the threats to the quality of UGC. The dominant research objective includes investigating the dynamics of threats. The most widely adopted research methods include quantitative analysis of real world data. This area of research was found to attract both intra-disciplinary and inter-disciplinary scholarly attention. It even attracted attention from practitioners affiliated to non-academic institutes. Finally, this paper serves as a call for scholars to identify possible ways to mitigate the threats to the quality of UGC. It also encourages the use of qualitative approaches.

show abstract

Detecting Fake Reviews Based on Review-Rating Consistency and Multi-dimensional Time Series

Fang

Wang

et al. 2018

Algorithms and Architectures for Parallel Processing

View full text Add to dashboard Cite

Detecting Fake Review with Rumor Model—Case Study in Hotel Review

Cited by 10 publications

References 13 publications

The importance of behavioral data to identify online fake reviews for tourism businesses: a systematic review

The importance of behavioral data to identify online fake reviews for tourism businesses: a systematic review

Reviewing the landscape of research on the threats to the quality of user‐generated content

Detecting Fake Reviews Based on Review-Rating Consistency and Multi-dimensional Time Series

Contact Info

Product

Resources

About