Opinion Spam Detection in Web Forum

Chen, Yu-Ren; Chen, Hsin-Hsi

doi:10.1145/2736277.2741085

Cited by 60 publications

(46 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In our setting, we used the learning rates η t that asymptotically decrease with iteration numbers (Bottou, 2012). Following previous work (Ott et al, 2011;Chen and Chen, 2015), we conducted five-fold cross-validation experiments, and determined the values of the regularization and hyper parameters via a grid-search method. Table 3 reports the spam and nonspam review detection accuracy of our methods SMTL-LLR and MTL-LR against all other baseline methods.…”

Section: Methodsmentioning

confidence: 99%

“…They found that the supervised support vector machines (SVM) trained on the textual n-gram features can achieve good performance. Feng et al (2012) presented syntactic stylometry features and trained SVM model for deception detection, while Chen and Chen (2015) built the SVM classifier on a diversity of features, such as content and thread features, for opinion spam detection in web forum. In addition, Li et al (2014) employed a featurebased additive model to explore the general rule for deceptive opinion spam detection.…”

Section: Related Workmentioning

confidence: 99%

“…By formulating deceptive opinion spam detection as a classification problem, existing work primarily focuses on extracting different types of features and applies off-the-shelf supervised classification algorithms to the problem (Jindal and Liu, 2008;Ott et al, 2011;Feng et al, 2012;Chen and Chen, 2015). Then, one weakness of previous work lies in the demand of manually recognizing a large amount of ground truth review spam data for model training.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deceptive Review Spam Detection via Exploiting Task Relatedness and Unlabeled Data

Hai

Zhao

Cheng

et al. 2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Existing work on detecting deceptive reviews primarily focuses on feature engineering and applies off-the-shelf supervised classification algorithms to the problem. Then, one real challenge would be to manually recognize plentiful ground truth spam review data for model building, which is rather difficult and often requires domain expertise in practice. In this paper, we propose to exploit the relatedness of multiple review spam detection tasks and readily available unlabeled data to address the scarcity of labeled opinion spam data. We first develop a multi-task learning method based on logistic regression (MTL-LR), which can boost the learning for a task by sharing the knowledge contained in the training signals of other related tasks. To leverage the unlabeled data, we introduce a graph Laplacian regularizer into each base model. We then propose a novel semi-supervised multitask learning method via Laplacian regularized logistic regression (SMTL-LLR) to further improve the review spam detection performance. We also develop a stochastic alternating method to cope with the optimization for SMTL-LLR. Experimental results on real-world review data demonstrate the benefit of SMTL-LLR over several well-established baseline methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deceptive Review Spam Detection via Exploiting Task Relatedness and Unlabeled Data

Hai

Zhao

Cheng

et al. 2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…In [28], the authors used temporal approach to detect spams and is based on the burst patterns and frequency of reviews. Chen and Chen [29] used similar burst patterns approach of reviews along with a temporal feature to detect the behaviour of the users. A burst pattern may not be a good indicator to judge the spam, as a user may be writing reviews for many products.…”

Section: Related Workmentioning

confidence: 99%

Finding Rotten Eggs: A Review Spam Detection Model using Diverse Feature Sets

2018

KSII TIIS

View full text Add to dashboard Cite

Social media enables customers to share their views, opinions and experiences as product reviews. These product reviews facilitate customers in buying quality products. Due to the significance of online reviews, fake reviews, commonly known as spam reviews are generated to mislead the potential customers in decision-making. To cater this issue, review spam detection has become an active research area. Existing studies carried out for review spam detection have exploited feature engineering approach; however limited number of features are considered. This paper proposes a Feature-Centric Model for Review Spam Detection (FMRSD) to detect spam reviews. The proposed model examines a wide range of feature sets including ratings, sentiments, content, and users. The experimentation reveals that the proposed technique outperforms the baseline and provides better results.

show abstract

“…Chen and Chen [23] introduced research relied on a set of interior records of opinion spams collected from a shady marketing campaign. They discovered the properties of opinion spams and spammers on a website to get some insights.…”

Section: Opinion Spam Detectionmentioning

confidence: 99%

Sentiment Detection, Recognition and Aspect Identification

Alasmari¹,

Dahab²

2017

IJCA

View full text Add to dashboard Cite

Sentiment analysis is the study of people's opinions, attitudes, feelings, and emotions discuss any object such as entities, events, topics, product, issues, services, etc. are respected for extraction of useful subjective information out of the text. The task is challenging and considered for customers and producers, for instance, Customers need to have general ideas about products, and companies need to know customers' needs and the opportunity to investigate and analyze those opinions towards their products and services. The increasing growth of the social network sites generating a big resource of social data. So, researchers considering about harnessing the effeteness of social media and sentiment analysis. These recent studies classified according to their contributions in the different SA methods. The main target of this paper is to give the illustration of the current trend of research in the sentiment analysis Detection, Recognition, Aspect Identification.

show abstract

Opinion Spam Detection in Web Forum

Cited by 60 publications

References 18 publications

Deceptive Review Spam Detection via Exploiting Task Relatedness and Unlabeled Data

Deceptive Review Spam Detection via Exploiting Task Relatedness and Unlabeled Data

Finding Rotten Eggs: A Review Spam Detection Model using Diverse Feature Sets

Sentiment Detection, Recognition and Aspect Identification

Contact Info

Product

Resources

About