NetSpam: A Network-Based Spam Detection Framework for Reviews in Online Social Media

Abstract

Nowadays, a big part of people rely on available content in social media in their decisions (e.g. reviews and feedback on a topic or product). The possibility that anybody can leave a review provide a golden opportunity for spammers to write spam reviews about products and services for different interests. Identifying these spammers and the spam content is a hot topic of research and although a considerable number of studies have been done recently toward this end, but so far the methodologies put forth still barely detect spam reviews, and none of them show the importance of each extracted feature type. In this study, we propose a novel framework, named NetSpam, which utilizes spam features for modeling review datasets as heterogeneous information networks to map spam detection procedure into a classification problem in such networks. Using the importance of spam features help us to obtain better results in terms of different metrics experimented on real-world review datasets from Yelp and Amazon websites. The results show that NetSpam outperforms the existing methods and among four categories of features; including review-behavioral, user-behavioral, reviewlinguistic, user-linguistic, the first type of features performs better than the other categories.

Spam Detection Framework Using Sentimenatl Analysis

“…On the off chance that two connections have a place with a similar kind, the sorts of beginning hub and closure hub of those connections are the same [1].…”

“…It is seen, from the past couple of year's kinfolk who routinely purchase things or organizations from these online social doors settle on decisions in light of the made studies which empowers or cripples them in their assurance of things and organizations. [1] Then again, a lot of writing has been distributed on the systems used to recognize spam and spammers and in addition distinctive sort of investigation on this theme. These systems can be classi fied into various classifications; some utilizing phonetic examples in content, which are for the most part in view of bigram, and unigram [2], others depend on behavioral examples that depend on highlights removed from designs in clients' conduct which are generally metadata based, and even a few procedures utilizing diagrams and chart based calculations and classifiers [3].…”

Research of Deceptive Review Detection Based on Target Product Identification and Metapath Feature Weight Calculation

“…The experiments in this section will compare the performance of the TM-DRD and the NFC [24], SpEagle [30], and NetSpam [32] on accuracy indices such as AP and AUC. We verify the impact of the target product review dataset and feature weight calculation on the detection efficiency of TM-DRD and the accuracy of the test results.…”

“…The datasets YelpChiOP and YelpNYCOP are, respectively, related review datasets on the target product identified by the fusion algorithm based on the anomaly scores proposed in chapter 4 from the original data sets YelpChi and YelpNYC [30]. Next, we will compare the performance of TM-DRD and NFC [24], SpEagle [30], and NetSpam [32] in AP and AUC, respectively, on the above 4 review datasets. We analyze the impact of feature weights on the accuracy of deceptive review detection.…”

“…The two are equal, and here is 13, the number of features. We use TM-DRD and NFC [24], SpEagle [30], and NetSpam [32], respectively, to calculate the deceptive degree probability of each review in the experimental review datasets above. We sort all the reviews according to the deceptive probability in descending to obtain a list of reviews.…”