Filters








59 Hits in 8.2 sec

Combating Product Review Spam Campaigns via Multiple Heterogeneous Pairwise Features [chapter]

Chang Xu, Jie Zhang
2015 Proceedings of the 2015 SIAM International Conference on Data Mining  
In this paper, we explore multiple heterogeneous pairwise features in virtue of some collusion signals found in reviewers' rating behaviors and linguistic patterns.  ...  Spam campaigns spotted in popular product review websites (e.g., amazon.com) have attracted mounting attention from both industry and academia, where a group of online posters are hired to collaboratively  ...  Acknowledgements We thank the anonymous reviewers for their helpful comments. This work is supported by the MOE AcRF Tier 2 Grant M4020110.020 awarded to Dr. Jie Zhang.  ... 
doi:10.1137/1.9781611974010.20 dblp:conf/sdm/XuZ15 fatcat:l7loyjgagjcnjbueawpesgluiq

Survey on Astroturfing Detection and Analysis from an Information Technology Perspective

Tong Chen, Jiqiang Liu, Yalun Wu, Yunzhe Tian, Endong Tong, Wenjia Niu, Yike Li, Yingxiao Xiang, Wei Wang, Zhe-Li Liu
2021 Security and Communication Networks  
Hence, the manner of detecting and combating astroturfing behavior has become highly urgent, attracting interest from researchers both from information technology and sociology.  ...  In the current paper, we restudy it mainly from the perspective of information technology, summarize the latest research findings of astroturfing detection, analyze the astroturfing feature, classify the  ...  [37] realized a new framework named NetSpam. ese frameworks use spam features to model the review data set as a heterogeneous information network and map the spam detection processing to the category  ... 
doi:10.1155/2021/3294610 fatcat:j3x3c5c6zfh6rcphaebenq6u3e

Online Social Deception and Its Countermeasures for Trustworthy Cyberspace: A Survey [article]

Zhen Guo, Jin-Hee Cho, Ing-Ray Chen, Srijan Sengupta, Michin Hong, Tanushree Mitra
2020 arXiv   pre-print
Cyber attackers have exploited the sophisticated features of SNSs to carry out harmful OSD activities, such as financial fraud, privacy threat, or sexual/labor exploitation.  ...  In addition, this work identified both spam profiles and spam campaigns based on the shared URL. Virvilis et al.  ...  Advertising, campaigns [33] Fake reviews Malicious users write fake reviews, opinions, or comments in social media to mislead other users.  ... 
arXiv:2004.07678v1 fatcat:k4a6siywefb6lhkmyn67lmoqwe

Sentiment Analysis and Opinion Mining [chapter]

Lei Zhang, Bing Liu
2017 Encyclopedia of Machine Learning and Data Mining  
A store is connected to a reviewer via this reviewer's review about the store. Each node is also attached with a set of features.  ...  This paper used a heterogeneous review graph with three types of nodes, i.e., reviewers, reviews and stores, to capture their relationships and to model spamming clues.  ... 
doi:10.1007/978-1-4899-7687-1_907 fatcat:iy5ty44cyzbrtodxfo7osy3iu4

False Information on Web and Social Media: A Survey [article]

Srijan Kumar, Neil Shah
2018 arXiv   pre-print
., fake reviews), and fact-based (e.g., false news and hoaxes).  ...  A recent surge of research in this area has aimed to address the key issues using methods based on feature engineering, graph mining, and information modeling.  ...  Feature-based Harris et al. [33] , Jindal et al. [43] , Gupta et al. [32] , Horne et al. [37] , Li et al. [51, 52, 54] , Lin et al. [55] , Kumar et al. [50], Perez et al. [74] , Minnich et al.  ... 
arXiv:1804.08559v1 fatcat:2qv3tigktzdnvpe37mef3mrg4a

Survey of Generative Methods for Social Media Analysis [article]

Stan Matwin, Aristides Milios, Paweł Prałat, Amilcar Soares, François Théberge
2021 arXiv   pre-print
Social dynamics are important for understanding the spreading of influence or diseases, formation of friendships, the productivity of teams, etc.  ...  The plethora of heterogeneous online platforms fostered a vast scientific production on various applications of social media analysis, ranging from sentiment analysis to cyber influence campaigns.  ...  reviews.  ... 
arXiv:2112.07041v1 fatcat:xgmduwctpbddfo67y6ack5s2um

Proceedings of the 3rd International Open Search Symposium #ossym2021 [article]

Andreas Wagner, Michael Granitzer, Christian Guetl, Christine Plote, Voigt Stefan
2022 Zenodo  
areas of the public internet, which is typically not possible in multiple heterogeneous data sources.  ...  Imagine searching through a collection of personal and company blogs curated by the community. • "Product Reviews without commercial intent".  ...  The learning modules will be published as OER via Wikiversity.  ... 
doi:10.5281/zenodo.6839942 fatcat:imuoppkmuzdtfnas63ckln4qei

Proceedings of the 3rd International Open Search Symposium #ossym2021 [article]

Andreas Wagner, Michael Granitzer, Christian Guetl, Christine Plote, Voigt Stefan
2022 Zenodo  
areas of the public internet, which is typically not possible in multiple heterogeneous data sources.  ...  Imagine searching through a collection of personal and company blogs curated by the community. • "Product Reviews without commercial intent".  ...  The learning modules will be published as OER via Wikiversity.  ... 
doi:10.5281/zenodo.6840911 fatcat:tw5xbexkwjguhoqcyxn5tdvbta

Turning the Hunted into the Hunter via Threat Hunting: Life Cycle, Ecosystem, Challenges and the Great Promise of AI [article]

Caroline Hillier
2022 arXiv   pre-print
The Insider threat detection via Probabilistic pairwise interaction and Heterogeneous Event's entity embedding (IPH) is a probabilistic model that plots the likelihood of heterogeneous event sequences  ...  ISTIS enhances Littoral Combat Ship (LCS) Surface Mission Module including threat ID process, quality and productivity [67] .  ... 
arXiv:2204.11076v1 fatcat:jc3bghaiungxxlta5itgjnla2a

Explicit web search result diversification

Rodrygo L.T. Santos
2012 SIGIR Forum  
A more sophisticated spam detection feature was devised by Cormack et al. (2011) .  ...  For entity-oriented features, up to four types (denoted "t") are considered: persons, organisations, products, and locations.  ... 
doi:10.1145/2492189.2492205 fatcat:g3f4j6r6ivhtzbm6mfi2zigsm4

Program

2022 2022 International Conference on Decision Aid Sciences and Applications (DASA)  
Ten different features are extracted from these IMFs. Only Hjorth parameters (activity, mobility, complexity) are selected using the Kruskal-Wallis test.  ...  A maximum of 92.90% classification accuracy is obtained using the features of IMF-4 with 10-fold cross-validation. The results conclude that the proposed method can detect AD patients efficiently.  ...  Since much information is available in multiple reviews (sometimes running in thousands) for a single product, it can create decision paralysis for the buyer.  ... 
doi:10.1109/dasa54658.2022.9765271 fatcat:ttqppf4j3navnaxe653mrzmezi

Detecting Intruders and Packet Modifiers in Wireless Sensor Networks

S. Navaneethan
2013 IOSR Journal of Computer Engineering  
Novaes, Joaquim Rausis, Natanael Cardoso, mainly Moema Bassfeld (librarian) and the anonymous reviewers for their valuable comments that helped us refine our message as well improving the former draft  ...  The actual productive effort is converted into the estimated productive effort (or project velocity) V i , via a bias b i , which represents any consistent bias in the team"s estimations.  ...  This architecture is also capable of performing noise tolerant searches across multiple features on large volumes of time series data.  ... 
doi:10.9790/0661-0850103 fatcat:ju24fypkjvgdzcg3ajc6hkto4u

Profiling, Modelling and Facilitating Online Activism

Julia Proskurnia
2017
We showed performance variations of the designed model with various combinations of external factors that outperform not only multiple baselines, but also is interpretable across various petitions.  ...  To this end, we introduced a generic methodology for categorizing online campaigns based on their goals and user engagement, as well as extracted campaigns' actions from their social media traces.  ...  I would also like to thank my highlyesteemed committee members: Carlos Castillo, Philippe Cudré-Mauroux, Robert West, Pierre Dillenbourg for the time and effort in reviewing on my thesis, as well as their  ... 
doi:10.5075/epfl-thesis-7925 fatcat:fxugng2lufeblilhmcmfdut574

Digital Rhetorical Ecosystem Analysis: Sensemaking of Digital Memetic Discourse [article]

Mridula Mascarenhas, Richard J. Cordes, Daniel A. Friedman
2021 Zenodo  
While raw datasets do not constitute a formal intelligence product, the data collected and used for projections and other features are nonetheless a product which should be made available both internally  ...  Recommendations: • Review best practices in improving information quality of crowdsourced subject -matter tagging in physical, digital, and rhetorical eco system contexts. • Review and synthesize research  ... 
doi:10.5281/zenodo.5573947 fatcat:6ecmq2b7inbdnl3vfhkyofbouu

Learning Representations of Social Media Users [article]

Adrian Benton
2018 arXiv   pre-print
In this thesis, we begin by showing how user representations can be learned from multiple types of user behavior on social media.  ...  We then show how user features can be employed as distant supervision to improve topic model fit.  ...  Amazon Product Reviews The Amazon product reviews corpus (McAuley and Yang, 2016) contains reviews of products as well as images of the product.  ... 
arXiv:1812.00436v1 fatcat:qp2hf6f6nfe7djyjakkns36epq
« Previous Showing results 1 — 15 out of 59 results