Lightning Talk - Think Outside the Dataset: Finding Fraudulent Reviews using Cross-Dataset Analysis

Nilizadeh, Shirin; Aghakhani, Hojjat; Gustafson, Eric; Kruegel, Christopher; Vigna, Giovanni

doi:10.1145/3308560.3316477

Cited by 6 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous scholars have outlined and suggested the latest AI-based techniques for early detection of fraudulent patterns and outliers (A. Leite, Gschwandtner, Miksch, Gstrein, & Kuntner, 2020;Nilizadeh, Aghakhani, Gustafson, Kruegel, & Vigna, 2019). Despite the availability of diverse redress channels in Malaysia to cater to the grievances of consumers, it is imperative for consumers to take the initiative of self-protection instead of resorting to governmental agencies and non-governmental organisations for resolving disputes with online traders.…”

Section: Conclusion and Implicationmentioning

confidence: 99%

The Mediating Effect of Trust on Consumers’ Purchase Decision in Mobile Social Commerce

2023

BJSSH

View full text Add to dashboard Cite

The convergence of social commerce and mobile commerce, harnessed by collaborative technological advancement and innovative users, which has transformed e-commerce platforms into effective instruments that support business strategies and provide consumers convenience. The ubiquitous nature of smartphones and the availability of real-time internet connections drive mobile social commerce. Online consumers are vulnerability to opportunistic exploitation if some parties withhold resources. Effective social interaction requires information transparency and trust. Consumers may depart from their routine buying decisions, which may or may not be the result warranted. Even so, in order to achieve the necessary level of success in online shopping, users must have confidence in their capacity to organise and execute a sequence of actions. This research examined three factors that affect consumers' purchase decision on mobile social commerce, namely social capital, situational influence and technology self-efficacy. A snowball sampling approach was applied in this research to gather responses from the e-consumers in Sabah, Sarawak and the Federal Territory of Labuan by means of WhatsApp, Wechat and email using a questionnaire. A total of 396 samples were analysed using SPSS and SmartPLS software. The assessment of the PLS-SEM structural model demonstrated that social capital and situational influence have a significant effect on consumers' purchase decisions, while trust partially mediates the relationships. Although technology self-efficacy has no direct impact on consumers' purchase decision, it is mediated by trust. This research provides information on the factors which directly affecting consumers' decision using mobile social commerce. Besides depending on AI-based techniques for early detection of fraudulent patterns and outliers for protection, consumers should take the initiative of self-protection during online shopping. Future studies should include psychological and personality characteristics, such as resilience and vulnerability to add to the body of knowledge on mobile social commerce.

show abstract

Section: Conclusion and Implicationmentioning

confidence: 99%

The Mediating Effect of Trust on Consumers’ Purchase Decision in Mobile Social Commerce

2023

BJSSH

View full text Add to dashboard Cite

show abstract

“…Other studies have linked datasets together to gain a better vantage on the review landscape, but still rely on a single snapshot for each data point. For example, Nilizadeh et al [31] used reviews from multiple different review platforms along with change point analysis to find fraudlent reviews. To the best of our knowledge, no other studies focus on review reclassification.…”

Section: Related Workmentioning

confidence: 99%

Reviews in motion: a large scale, longitudinal study of review recommendations on Yelp

Amos¹,

Maio²,

Mittal³

2022

Preprint

View full text Add to dashboard Cite

The United Nations Consumer Protection Guidelines lists "access ... to adequate information ... to make informed choices" as a core consumer protection right. However, problematic online reviews and imperfections in algorithms that detect those reviews pose obstacles to the fulfillment of this right. Research on reviews and review platforms often derives insights from a single web crawl, but the decisions those crawls observe may not be static. A platform may feature a review one day and filter it from view the next day. An appreciation for these dynamics is necessary to understand how a platform chooses which reviews consumers encounter and which reviews may be unhelpful or suspicious. We introduce a novel longitudinal angle to the study of reviews. We focus on "reclassification," wherein a platform changes its filtering decision for a review. To that end, we perform repeated web crawls of Yelp to create three longitudinal datasets. These datasets highlight the platform's dynamic treatment of reviews. We compile over 12.5M reviews-more than 2M unique-across over 10k businesses. Our datasets are available for researchers to use.Our longitudinal approach gives us a unique perspective on Yelp's classifier and allows us to explore reclassification. We find that reviews routinely move between Yelp's two main classifier classes ("Recommended" and "Not Recommended") -up to 8% over eight years -raising concerns about prior works' use of Yelp's classes as ground truth. These changes have impacts on small scales; for example, a business going from a 3.5 to 4.5 star rating despite no new reviews. Some reviews move multiple times: we observed up to five reclassifications in eleven months. Our data suggests demographic disparities in reclassifications, with more changes in lower density and low-middle income areas. Because our web crawls coincided with the COVID-19 pandemic, our data also allowed limited exploration of the impact of mask policies and discussions on reviews.

show abstract

“…Motivated by previous work, Nilizadeh, et al [142] proposed OneReview fake review detection model based on textual and metadata features. OneReview concentrates on separating anomalous changes in business profiles via multiple review websites to discover harmful activity without depending on particular patterns.…”

Section: ) Traditional Statistical Supervised Learning In Detecting Fake Rreviewsmentioning

confidence: 99%

Fake Reviews Detection: A Survey

Mohawesh

Tran

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In e-commerce, user reviews can play a significant role in determining the revenue of an organisation.Online users rely on reviews before making decisions about any product and service. As such, the credibility of online reviews is crucial for businesses and can directly affect companies' reputation and profitability. That is why some businesses are paying spammers to post fake reviews. These fake reviews exploit consumer purchasing decisions. Consequently, the techniques for detecting fake reviews have extensively been explored in the past twelve years. However, there still lacks a survey that can analyse and summarise the existing approaches. To bridge up the issue, this survey paper details the task of fake review detection, summing up the existing datasets and their collection methods. It analyses the existing feature extraction techniques. It also summarises and analyses the existing techniques critically to identify gaps based on two groups: traditional statistical machine learning and deep learning methods. Further, we conduct a benchmark study to investigate the performance of different neural network models and transformers that have not been used for fake review detection yet. The experimental results on two benchmark datasets show that RoBERTa performs about 7% better than the state-of-the-art methods in a mixed domain for the deception dataset with the highest accuracy of 91.2%, which can be used as a baseline for future studies. Finally, we highlight the current gaps in this research area and the possible future directions. INDEX TERMSFake review; Fake review detection; Feature engineering, Machine learning; Deep learning.

show abstract

Lightning Talk - Think Outside the Dataset: Finding Fraudulent Reviews using Cross-Dataset Analysis

Cited by 6 publications

References 7 publications

The Mediating Effect of Trust on Consumers’ Purchase Decision in Mobile Social Commerce

The Mediating Effect of Trust on Consumers’ Purchase Decision in Mobile Social Commerce

Reviews in motion: a large scale, longitudinal study of review recommendations on Yelp

Fake Reviews Detection: A Survey

Contact Info

Product

Resources

About