Filters








1,484 Hits in 7.0 sec

Towards generalisable hate speech detection: a review on obstacles and solutions [article]

Wenjie Yin, Arkaitz Zubiaga
2021 arXiv   pre-print
obstacles, and then proposes directions of future research to improve generalisation in hate speech detection.  ...  Hate speech is one type of harmful online content which directly attacks or promotes hate towards a group or an individual member based on their actual or perceived aspects of identity, such as ethnicity  ...  analysis of the main obstacles to generalisable hate speech detection and existing attempts to address them, and (3) suggestions for future research to address these obstacles.  ... 
arXiv:2102.08886v1 fatcat:7uemuqrehnfvnbenp657hv3fpy

Towards generalisable hate speech detection: a review on obstacles and solutions

Wenjie Yin, Arkaitz Zubiaga
2021 PeerJ Computer Science  
the main obstacles, and then proposes directions of future research to improve generalisation in hate speech detection.  ...  Hate speech is one type of harmful online content which directly attacks or promotes hate towards a group or an individual member based on their actual or perceived aspects of identity, such as ethnicity  ...  Even without a focus on generalisation per se, easier access to evaluation data and models to compare to can help shift hate speech detection research, as a whole, towards more generalisable outputs.  ... 
doi:10.7717/peerj-cs.598 fatcat:lhjvmezkdbanje6kycnxet6vmm

ETHOS: an Online Hate Speech Detection Dataset [article]

Ioannis Mollas, Zoe Chrysopoulou, Stamatis Karlos, Grigorios Tsoumakas
2021 arXiv   pre-print
A robust and reliable system for detecting and preventing the uploading of relevant content will have a significant impact on our digitally interconnected society.  ...  As a result, the lack of accurate hate speech detection mechanisms would severely degrade the overall user experience, although its erroneous operation would pose many ethical concerns.  ...  if a tweet does not contain hate speech towards religion by 97.82%, but its performance is downgraded on the opposite case, achieving 27.31%.  ... 
arXiv:2006.08328v2 fatcat:ppg2phh4nber3p42pgbgpyfmrq

A systematic review of Hate Speech automatic detection using Natural Language Processing [article]

Md Saroar Jahan, Mourad Oussalah
2021 arXiv   pre-print
With the multiplication of social media platforms, which offer anonymity, easy access and online community formation, and online debate, the issue of hate speech detection and tracking becomes a growing  ...  This paper provides a systematic review of literature in this field, with a focus on natural language processing and deep learning technologies, highlighting the terminology, processing pipeline, core  ...  Table 4 : 4 Review of identified survey papers on automatic hate speech detection Paper Title Authors, Year Publisher Name Review Focus Citation Review Type A Survey on Hate Speech De- tection  ... 
arXiv:2106.00742v1 fatcat:qwxjwgma4zaynemge57cu7xqlm

A Survey of Online Hate Speech through the Causal Lens [article]

Antigoni-Maria Founta, Lucia Specia
2021 arXiv   pre-print
This survey summarises the relevant research that revolves around estimations of causal effects related to online hate speech.  ...  Initially, we provide an argumentation as to why re-establishing the exploration of hate speech in causal terms is of the essence.  ...  Practitioners should then be able to take crucial actions towards either its efficient and interpretable detection or, even further, its a priori prevention.  ... 
arXiv:2109.08120v1 fatcat:u5465pwcivgb5eocl3hcxjvr7u

The Female Detective [chapter]

2020 Women and Crime in Post-Transitional South African Crime Fiction  
As so often in South African crime fiction, the criminal investigation involves a review of the past and the grip that it has on the present.  ...  In her analysis of African American female detectives at the turn of the 1990s, Munt perceives a movement from "Black Woman as a sight, towards a new generation of investigatory visions, controlled by  ... 
doi:10.1163/9789004437449_005 fatcat:u6h2rmvea5hvlpue6nvmlkwdei

Offensive communications: exploring the challenges involved in policing social media

Mark Williams, Michelle Butler, Anna Jurek-Loughrey, Sakir Sezer
2019 Contemporary Social Science  
Acknowledgements The research reported in this article was carried out with funding provided by a postgraduate research scholarship from the Leverhulme Interdisciplinary Network on Cybersecurity and Society  ...  and a massive breach of freedom of speech.  ...  and investigate hate crime and abuse occurring on Twitter andFacebook.  ... 
doi:10.1080/21582041.2018.1563305 fatcat:rkd5bzadx5ewva4illiszhq5xu

LIPIcs : an Open-Access Series for International Conference Proceedings

Marc Herbstritt, Wolfgang Thomas
2016 ERCIM News  
Pallis (University of Cyprus) and Evangelos Markatos (FORTH) MANDOLA wants to make a bold step towards improving our understanding of the prevalence and spread of online hate speech and towards empowering  ...  (ii) Poor awareness about how to deal with the issue since there is a fine line between hate speech and freedom of speech: the boundaries between legal and illegal hate speech are sometimes blurred, and  ...  Multi-cloud applications rely on the adoption of cloud services of different capability types (i.e. infrastructure, platform or software as a service) from different Cloud Service Providers (CSPs).  ... 
doi:10.18154/rwth-2018-223393 fatcat:ddo7qz65l5b7peuksw2amaoxai

Signal detection theory in Hilbert space

Marcus Vinícius C. Baldo
2013 Behavioral and Brain Sciences  
and discriminability.  ...  AbstractThe Hilbert space formalism is a powerful language to express many cognitive phenomena.  ...  ACKNOWLEDGMENTS We are grateful to Diederik Aerts, Harald Atmanspacher, Thomas Filk, James Hampton, Mike Oaksford, Steven Sloman, Jennifer Trueblood, and Christoph Weidemann for their helpful comments.  ... 
doi:10.1017/s0140525x12002865 pmid:23673024 fatcat:6ky3e5ojprbdbnhcktmbi2tdzm

Conversational artificial intelligence - demystifying statistical vs linguistic NLP solutions

Kulvinder Panesar
2020 Journal of Computer-Assisted Linguistic Research  
We will delve into the spectrum of conversational interfaces and focus on a strong artificial intelligence concept.  ...  This paper aims to demystify the hype and attention on chatbots and its association with conversational artificial intelligence.  ...  A second goal was to review the nature of conversational systems and how the solutions work and how they are evaluated.  ... 
doi:10.4995/jclr.2020.12932 fatcat:oogpuyd6zvhixi22k33xawe3dm

Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities [article]

Nenad Tomasev, Kevin R. McKee, Jackie Kay, Shakir Mohamed
2021 arXiv   pre-print
We explore queer concerns in privacy, censorship, language, online safety, health, and employment to study the positive and negative effects of artificial intelligence on queer communities.  ...  These issues underscore the need for new directions in fairness research that take into account a multiplicity of considerations, from privacy preservation, context sensitivity and process fairness, to  ...  ACKNOWLEDGMENTS We would like to thank Aliya Ahmed, Dorothy Chou, Ben Coppin, Michelle Dunlop, Thore Graepel, William Isaac, Koray Kavukcuoglu, Guy Scully, and Laura Weidinger for the support and insightful  ... 
arXiv:2102.04257v2 fatcat:xs5s7er5lffn7kdnubursl4ytq

Generalisability of Topic Models in Cross-corpora Abusive Language Detection

Tulika Bose, Irina Illina, Dominique Fohr
2021 Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda   unpublished
Rapidly changing social media content calls for robust and generalisable abuse detection models.  ...  Our performance analysis reveals that topic models are able to capture abuse-related topics that can transfer across corpora, and result in improved generalisability.  ...  Towards generalisable hate speech detection: a review on obstacles and solutions. arXiv preprint arXiv:2102.08886. Fuzhen Zhuang, Ping Luo, Peifeng Yin, Qing He, and Zhongzhi Shi. 2013.  ... 
doi:10.18653/v1/2021.nlp4if-1.8 fatcat:ddr65gqwpvdttiiw4lqfdp57ii

Applications and challenges of AI-based algorithms in the COVID-19 pandemic

Danai Khemasuwan, Henri G Colt
2021 BMJ Innovations  
Next, we review some of the literature relevant to outbreak detection, contact tracing, forecasting an outbreak, detecting COVID-19 disease on medical imaging, prognostication and drug and vaccine development  ...  Artificial intelligence (AI) and, in particular, machine learning (ML) and deep learning (DL) are being applied on multiple fronts to overcome the pandemic.  ...  DL is used for internet data searches, language translation and speech recognition on smart phones.  ... 
doi:10.1136/bmjinnov-2020-000648 fatcat:7txylmnwdvefvfw67irgkesb7i

A Systematic Survey of Online Data Mining Technology Intended for Law Enforcement

Matthew Edwards, Awais Rashid, Paul Rayson
2015 ACM Computing Surveys  
As more and more crime takes on a digital aspect, law enforcement bodies must tackle an online environment generating huge volumes of data.  ...  Such technologies must be well-designed and rigorously grounded, yet no survey of the online data-mining literature exists which examines their techniques, applications and rigour.  ...  [Warner and Hirschberg 2012] focus on detecting hate speech on the web, discussing issues with clearly defining hate speech -such as distinguishing reclamation or discussion of racial slurs from their  ... 
doi:10.1145/2811403 fatcat:qpvfebejpfgp5bh3cgykaoumze

Forecasting the governance of harmful social media communications: findings from the digital wildfire policy Delphi

Adam Edwards, Helena Webb, William Housley, Roser Beneito-Montagut, Rob Procter, Marina Jirotka
2020 Policing and Society: An International Journal of Research and Policy  
of hate speech and do not breach their terms and conditions.  ...  detect and classify harmful communications.  ... 
doi:10.1080/10439463.2020.1839073 fatcat:yu6agq7gl5ertnrf7mh2ijdx64
« Previous Showing results 1 — 15 out of 1,484 results