Learning to Identify Review Spam

By Fangtao Li, Minlie Huang, Yi Yang, Xiaoyan Zhu. International Joint Conference on Artificial Intelligence, 2011

437 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/e406c7d0bf67ea13dc9553fd4514ceaa3a61f6df

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

A comprehensive review on ensemble deep learning: Opportunities and challenges (2023, methodology): “In contrast, in the Arabic language, the authors in Saeed et al. (2022) applied both voting and stacking for spam detection based on ﬁve baseline classiﬁers (SVM, NB, LR, DT, KNN) using two data-sets from Opinion Spam Corpus (Li et al., 2011).”
False Information on Web and Social Media: A Survey (2018, background): “[51] added sentiment, subjectivity, and pronoun usage features to the set.”
Collective Opinion Spam Detection: Bridging Review Networks and Metadata (2015, methodology): “Current approaches can also be grouped as those that detect fake reviews [6, 7, 9, 13, 14, 22, 26, 28], spam users [1, 5, 15, 18, 26], or spam user groups [19, 29].”
Spotting fake reviewer groups in consumer reviews (2012, methodology): “Due to this inherent nature of the problems, the closest that one can get to gold standards is by creating a manually labeled dataset using human experts [5, 21, 23, 27, 28].”
Spotting opinion spammers using behavioral footprints (2013, background): “In [25], a manually labeled dataset was used, which also has reliability issues because it has been shown that the accuracy of human labeling of fake reviews is very poor [34].”
A survey on opinion mining and sentiment analysis: Tasks, approaches and applications (2015, methodology): “Some promising review spam detection methods included duplicate finding methods [234], concept similarity based method [235], content based method [200, 210], and review and reviewer oriented features based method [236] etc.”
Identifying fake Amazon reviews as learning from crowds (2014, methodology): “The methodological approach and performance achieved in this exper-iment seems to be comparable to that of Strappar-ava and Mihalcea (2009) and, more recently, of Li et al. (2011).”
Review Graph Based Online Store Review Spammer Detection (2011, background): “Our second contribution is the introduction of three fundamental concepts, i.e. the trustiness of reviewers, the honesty of reviews, and the reliability of stores, and the identification of their interrelationships: a reviewer is more trustworthy if (s)he has written more honesty reviews, a store…”
Why people hate your app: making sense of user feedback in a mobile app store (2013, background): “Much work has focused on detecting spam reviews [14, 16, 20, 22, 21].”
Exploiting Burstiness in Reviews for Review Spammer Detection (2021, background): “Most existing works focused on analyzing one review or one reviewer at a time, neglecting the potential relationships among multiple reviews or reviewers (Jindal and Liu 2008; Lim et al. 2010; Jindal, Liu, and Lim, 2010; Li et al. 2011; Ott et al. 2011).”
Detecting opinion spams and fake news using text classification (2018, background): “Li et al.(27) decided not to focus entirely on heuristic rules like previous researchers.”
Opinion Fraud Detection in Online Reviews by Network Effects (2013, neutral): “(Li et al. 2011) uses sentiment scores, product brand, and reviewer profile attributes to train classifiers.”
Automated Crowdturfing Attacks and Defenses in Online Review Systems (2017, background): “All these features are defined in SentiWordNet [3], a popular lexical resource for opinion mining [31, 53, 56].”
Assisting consumers in detecting fake reviews: The role of identity information disclosure and consensus (2016, background): “, 2011), word duplication and number of sentences (Bhattarai, Rus and Dasgupta, 2009), and different reviewer- and behavior-related characteristics based on machine-learning methods (Jindal and Liu, 2008; Li et al., 2011; Lim et al., 2010).”