94,077 Hits in 3.8 sec

Author Profiling for Abuse Detection

Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis, Ekaterina Shutova
2018 International Conference on Computational Linguistics  
Experimenting with a dataset of 16k tweets, we show that our methods significantly outperform the current state of the art in abuse detection.  ...  The current state-of-the-art approaches to abuse detection are oblivious to user and community information and rely entirely on textual (i.e., lexical and semantic) cues.  ...  In this paper, we present the first approach to abuse detection that leverages author profiling information based on properties of the authors' social network and investigate its effectiveness.  ... 
dblp:conf/coling/MishraTYS18 fatcat:ehr445abijcjpgbptko3hf5lam

Abusive Language Detection with Graph Convolutional Networks [article]

Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis, Ekaterina Shutova
2019 arXiv   pre-print
Previous research on automated abusive language detection in Twitter has shown that community-based profiling of users is a promising technique for this task.  ...  We show that such a heterogeneous graph-structured modeling of communities significantly advances the current state of the art in abusive language detection.  ...  Acknowledgments We would like to thank the anonymous reviewers for their useful feedback. Helen Yannakoudakis was supported by Cambridge Assessment, University of Cambridge.  ... 
arXiv:1904.04073v1 fatcat:6yhy2iajgvfwpkmjmo5t4r6m4q

Ability of Substance Abusers to Escape Detection on the Minnesota Multiphasic Personality Inventory-Adolescent (MMPI-A) in a Juvenile Correctional Facility

L. A. R. Stein, John R. Graham
2005 Assessment (Odessa, Fla.)  
For feigning substance abusers, only about 10% of substance abusers were detected, with about 72% being categorized as faking and needing further assessment.  ...  However, the Lie Scale (L) was able to detect more than 75% of deceptive profiles and about 77% of honest profiles.  ...  The authors gratefully acknowledge Beverly Kaemmer and the University of Minnesota Press for their support in completing this project.  ... 
doi:10.1177/1073191104270838 pmid:15695741 pmcid:PMC2860861 fatcat:guziefx3yjcbjpthvqz3ucrotm


2017 Journal of Natural Sciences, Engineering and Technology  
Traditional methods of detecting health care fraud and abuse are time-consuming and inefficient. In this paper, the health care insurance fraud and abuse detection system (HECIFADES) was proposed.  ...  After testing, it was observed that HECIFADES was indeed an effective system for detecting fraudulent activities and yet very secured way for generating medical claims.  ...  The authors selected nine expense-related variables and compared them in two groups of fraudulent and nonfraudulent claims for building the detection models.  ... 
doi:10.51406/jnset.v15i2.1662 fatcat:wfyiirtrknaj3lpy363kukghla

Discouraging Abusive Behavior in Privacy-Preserving Online Social Networking Applications

Álvaro García-Recuero
2016 Proceedings of the 25th International Conference Companion on World Wide Web - WWW '16 Companion  
For example, in [9] , authors apply belief function theory to the problem of "troll" detection.  ...  Also, based on gender classification of Twitter profiles, [1] investigated the detection of deceptive profiles by looking at profile attributes such as first names, profile-, text-, link-and sidebar-colors  ... 
doi:10.1145/2872518.2888600 dblp:conf/www/Garcia-Recuero16 fatcat:isohjj3xafhf3erypgcmmmz6cq

Misuse detection for information retrieval systems

Rebecca Cathey, Ling Ma, Nazli Goharian, David Grossman
2003 Proceedings of the twelfth international conference on Information and knowledge management - CIKM '03  
Our approach is based on building and maintaining a profile of the behavior of the system user through tracking, or monitoring, of user activity within the information retrieval system.  ...  We propose three different methods to detect misuse in information retrieval systems. Our results favorably demonstrate the validity of our approach.  ...  Any new activity of the user is compared to the user profile to detect a potential misuse for the authorized user.  ... 
doi:10.1145/956863.956901 dblp:conf/cikm/CatheyMGG03 fatcat:as7lnzksbfhltb62s5lcee36nm

Detecting Credential Abuse in the Grid Using Bayesian Networks

Christopher Kunz, Nina Tahmasebi, Thomas Risse, Matthew Smith
2011 2011 IEEE/ACM 12th International Conference on Grid Computing  
Proxy Credentials serve as a principal for authentication and authorization in the Grid. Despite their limited lifetime, they can be intercepted and abused by an attacker.  ...  Our approach combines modifications to the security infrastructure with a Bayesian classifier in order to provide a reliable method for detecting abusive Grid credential usage and alerting the legitimate  ...  Proxy Credentials serve as a principal for authentication and authorization in the Grid. Despite their limited lifetime, they can be intercepted and abused by an attacker.  ... 
doi:10.1109/grid.2011.23 dblp:conf/grid/KunzTRS11 fatcat:x2wjguun4fdlfhgywofm5pd7pi

Has the Online Discussion Been Manipulated? Quantifying Online Discussion Authenticity within Online Social Media [article]

Aviad Elyashar, Jorge Bendahan, Rami Puzis
2018 arXiv   pre-print
The detection of online discussion topics manipulated by OSM abusers is an emerging issue attracting significant attention.  ...  Some individuals view OSM as fertile ground for abuse and use it to disseminate misinformation and political propaganda, slander competitors, and spread spam.  ...  ACKNOWLEDGMENT The authors would like to thank Robin Levy-Stevenson for proofreading this article.  ... 
arXiv:1708.02763v2 fatcat:nohnogibibewxmmt6z5sujodwi

Influence of Personality Traits and Its Interaction with the Phenomenon of Bullying: Multi-Centre Descriptive Study

Manuel Pabón-Carrasco, Lucia Ramirez-Baena, Nerea Jiménez-Picón, José Antonio Ponce Blandón, José Manuel Martínez-Montilla, Raúl Martos-García
2019 International Journal of Environmental Research and Public Health  
Various studies suggest that the personality of teenagers is a risk profile for bullying.  ...  The results showed that 14% (n = 13) of the sample were detected as victims and another 14% (n = 13) were detected as aggressors.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ijerph17010172 pmid:31881733 pmcid:PMC6981670 fatcat:comoghnkcvgftak4get63ce3zu

AIS-based profiling of fishing vessels falls short as a "proof of concept" for identifying forced labor at sea

Wilf Swartz, Andrés M. Cisneros-Montemayor, Gerald G. Singh, Patrick Boutet, Yoshitaka Ota
2021 Proceedings of the National Academy of Sciences of the United States of America  
The authors create profiles from vessels reported to have committed labor abuses, search for similar profiles in a database of 16,000 vessels with available positioning (automatic identification system  ...  In conclusion, McDonald et al. falls short as a "proof of concept," and therefore, the capacity of remote sensing as a tool for detecting fishing vessels engaged in labor abuses remains unsubstantiated  ... 
doi:10.1073/pnas.2100341118 pmid:33941675 pmcid:PMC8126828 fatcat:wwkymboviredleng7pyilk53ba

Too good to be true? Predicting author profiles from abusive language [article]

Isabelle van der Vegt, Bennett Kleinberg, Paul Gill
2020 arXiv   pre-print
The problem of online threats and abuse could potentially be mitigated with a computational approach, where sources of abuse are better understood or identified through author profiling.  ...  This study examines statistical relationships between author demographics and abusive vs normal language, and performs prediction experiments for personality, age, and gender.  ...  In our view, an important step has been missed in the use of author profiling for threat assessment; the link between author characteristics and abusive language remains unestablished.  ... 
arXiv:2009.01126v2 fatcat:4xrm3k37ybedfbimuhot7fetya

Tackling Online Abuse: A Survey of Automated Abuse Detection Methods [article]

Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
2020 arXiv   pre-print
We describe the existing datasets and review the computational approaches to abuse detection, analyzing their strengths and limitations.  ...  Consequently, over the past few years, there has been a substantial research effort towards automated abuse detection in the field of natural language processing (NLP).  ...  A similar trend also holds for abuse detection across domains.  ... 
arXiv:1908.06024v2 fatcat:53nwpcbspjdbrnyplzmsyjxmpu

Screening for child abuse at emergency departments: a systematic review

E. C F M Louwers, M. J Affourtit, H. A Moll, H. J d. Koning, I. J Korfage
2009 Archives of Disease in Childhood  
In these studies the intervention consisted of a checklist of indicators of risk for child abuse.  ...  Introduction Child abuse is a serious problem worldwide and can be difficult to detect.  ...  In 1979, Hight et al. developed a risk profile for children with burns to improve the recognition of child abuse. [31] After the introduction of Hight's profile, Clark et al. reported an increase of suspected  ... 
doi:10.1136/adc.2008.151654 pmid:19773222 fatcat:jeivc5xzora2vcsqbh3rmtnrja

Persistent HIV Viremia: Description of a Cohort of HIV Infected Individuals with ART Failure in Puerto Rico

Gerónimo Maldonado-Martínez, Robert Hunter-Mellado, Diana Fernández-Santos, Eddy Ríos-Olivares
2015 International Journal of Environmental Research and Public Health  
and does not necessarily represent the official views of the National Center for Research Resources of the National Institutes of Health.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ...  © 2015 by the authors; licensee MDPI, Basel, Switzerland.  ... 
doi:10.3390/ijerph13010050 pmid:26703691 pmcid:PMC4730441 fatcat:zxmuz4gohrfhbck6y3zzlzwsmm

Modeling Users and Online Communities for Abuse Detection: A Position on Ethics and Explainability [article]

Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
2021 arXiv   pre-print
In this position paper, we discuss the role that modeling of users and online communities plays in abuse detection.  ...  Consequently, over the past few years, there has been a substantial research effort towards automated abusive language detection in the field of NLP.  ...  Then for each comment to be classified, the researchers extracted the ego-graph of its author and created a feature vector for the comment from the ego-graph using node2vec along with measures like degree  ... 
arXiv:2103.17191v2 fatcat:o2ngw6bv5nexpjotlpngynkzw4
« Previous Showing results 1 — 15 out of 94,077 results