Feature Analysis for Fake Review Detection through Supervised Classification

Fontanarava, Julien; Pasi, Gabriella; Viviani, Marco

doi:10.1109/dsaa.2017.51

Cited by 48 publications

(37 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of the aforementioned studies have proposed a spam reviews detection technique while working on the dataset “DOSC” such as Narayan et al (), Etaiwi and Awajan (), Mani et al () and Etaiwi and Naymat () while Vanta and Aono () proposed the technique while working on “YelpNYC” dataset and (Fontanarava et al, ) worked on “YelpZIP” dataset.…”

Section: Evaluation Results and Discussionmentioning

confidence: 99%

“…Vanta and Aono () used some features extracted from reviews' texts and reviews' ratings and achieved an accuracy of 78.40%, a precision of 78.40%, and a recall of 78.40%. Fontanarava et al () analyzed the most appropriate review and reviewer‐centric features for the detection of spam reviews and reached an accuracy of 80.60%, a precision of 77.60%, and a recall of 86.10%.…”

Section: Evaluation Results and Discussionmentioning

confidence: 99%

“…Etaiwi and Awajan (2017) used the same classification algorithms except gradient-boosted trees. Fontanarava, Pasi, and Viviani (2017) performed a general level feature analysis in order to analyze the main features related to the review and the reviewer that are suited for the detection of spam reviews. Random Forest classifier has been employed to detect spam reviews.…”

Section: Salasmentioning

confidence: 99%

See 2 more Smart Citations

An enhanced feature‐based sentiment analysis approach

Saeed

Helal

Badr

et al. 2019

WIREs Data Min & Knowl

View full text Add to dashboard Cite

In the last few years, online reviews where individuals express their thoughts, interests, experiences, and opinions have broadly spread over the internet. Sentiment analysis has evolved to analyze these online reviews and provide valuable insights for both individuals and organizations that may help them in making decisions. Unfortunately the performance of sentiment analysis process is affected by the nature of online reviews' content that may contain emoticons and negation words. Moreover, spam reviews have been written for the purpose of deceiving others. Therefore, there is a need to develop an approach that considers these issues. In this paper, an enhanced approach for sentiment analysis is proposed which aims to enhance the performance of classifying reviews based on their features and assigning accurate sentiment score to features. This enhanced approach is achieved by handling negation, detecting emoticons, and detecting spam reviews using a combination of different types of properties which leads to achieving better predictive performance. The proposed approach has been verified against three datasets of different sizes. The results indicate that the proposed approach achieves a maximum accuracy of about 99.06% in detecting spam reviews and a maximum accuracy of about 97.13% in classifying reviews. This article is categorized under: Algorithmic Development > Text Mining Technologies > Classification Technologies > Machine Learning

show abstract

Section: Evaluation Results and Discussionmentioning

confidence: 99%

Section: Evaluation Results and Discussionmentioning

confidence: 99%

Section: Salasmentioning

confidence: 99%

See 1 more Smart Citation

An enhanced feature‐based sentiment analysis approach

Saeed

Helal

Badr

et al. 2019

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…Furthermore, combining spam review detection and spammer detection by analyzing their behaviors is more effective solution for detecting review spam than either approach alone. In this way, we cite the proposed methods in (Fontanarava et al, 2017;Rayana and Akoglu, 2015), that exploit both relational data and metadata of reviewers and reviews. Results prove that this kind of methods outperform all others.…”

Section: Introductionmentioning

confidence: 99%

Fake Reviews Detection Based on Both the Review and the Reviewer Features Under Belief Function Theory

Khalifa¹,

Elouedi²,

Lefèvre³

2019

Proceedings of the 16th International Conference on Applied Computing 2019

View full text Add to dashboard Cite

The online reviews play an increasingly spreading role in consumer purchasing decisions and they are also considered as one of the most powerful source of information for companies. Due to this attraction, manufacturers and retailers rely on spammers to promote their own products and demote the competitors' one by posting fake reviews. Therefore, it is essential to detect deceptive reviews in order to ensure customers confidence and to maintain companies' fair competition. To tackle this problem, we propose a new approach able to spot spam reviews relying both on the rating reviews and the different spammers' indicators under the belief function framework. This method treats uncertainty in the given reviews also in the reviewers' information to take into account each reviewer spamicity when making decision. Experiments are conducted on two real-world review data-sets from Yelp.com with filtered (spam) and recommended (non-spam) reviews to demonstrate our method the effectiveness.

show abstract

“…Reviews refer to any view or opinion made about a product or service by an individual usually not associated with the business. The reviews that appear on the website are specifically referred to as user generated content (UGC) [2]. Reviews present a new way to learn about customer preferences, product quality as well as product"s shortcomings.…”

Section: Introductionmentioning

confidence: 99%

Fake Review Detection using Classification

Chowdhary¹,

Pandit²

2018

IJCA

View full text Add to dashboard Cite

In today"s world, where Internet has become a household convenience, online reviews have become a critical tool for businesses to control their online reputation. Reviewing has changed the face of marketing in this new era. Nowadays, most companies invest money in mining the reviews to gain insights into customer preferences as well as to gain competitive intelligence and are hiring individuals to write fake reviews. The fraudsters" activities mislead potential customers and organizations reshaping their businesses and prevent opinion-mining techniques from reaching accurate conclusions. Thus, it has become essential to detect fake reviews to bring to surface the true product opinion. This paper focuses on product reviews and detecting spam fake reviews among them using supervised learning techniques using synthetic fake reviews (to cover all types) as a training set. Term frequency and user review frequency are two features whose impact on classification model is studied in this paper. It classifies the reviews to test the accuracy of the model. The results have been encouraging with an accuracy of over 98%.

show abstract

Feature Analysis for Fake Review Detection through Supervised Classification

Cited by 48 publications

References 25 publications

An enhanced feature‐based sentiment analysis approach

An enhanced feature‐based sentiment analysis approach

Fake Reviews Detection Based on Both the Review and the Reviewer Features Under Belief Function Theory

Fake Review Detection using Classification

Contact Info

Product

Resources

About