13 Hits in 9.6 sec

Cross-lingual Capsule Network for Hate Speech Detection in Social Media [article]

Aiqi Jiang, Arkaitz Zubiaga
2021 pre-print
We propose a cross-lingual capsule network learning model coupled with extra domain-specific lexical semantics for hate speech (CCNL-Ex).  ...  In this paper we investigate the cross-lingual hate speech detection task, tackling the problem by adapting the hate speech resources from one language to another.  ...  Capsule network has not been considered in cross-lingual hate speech detection so far.  ... 
doi:10.1145/3465336.3475102 arXiv:2108.03089v1 fatcat:75raleyx3rbehhil62ne2rwlzi

Offensive Language Identification in Greek [article]

Zeses Pitenis, Marcos Zampieri, Tharindu Ranasinghe
2020 arXiv   pre-print
As offensive language has become a rising issue for online communities and social media platforms, researchers have been investigating ways of coping with abusive content and developing systems to detect  ...  its different types: cyberbullying, hate speech, aggression, etc.  ...  offensive language detection, as well as Fotini and that helped review tweets with ambivalent labels.  ... 
arXiv:2003.07459v2 fatcat:elsf6hwburhwdcbo25uc7f7z2y

Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Posts [article]

Charangan Vasantharajan, Uthayasanker Thayasivam
2021 arXiv   pre-print
Offensive Language detection in social media platforms has been an active field of research over the past years.  ...  In non-native English spoken countries, social media users mostly use a code-mixed form of text in their posts/comments.  ...  Acknowledgements We would like to express our thanks to Mr.Sanjeepan Sivapiran 11 and Mr.Temcious Fernando 12 for their helpful suggestions to improve and clarify this manuscript.  ... 
arXiv:2108.10939v2 fatcat:i5cydkgna5cuvijqqspjbv2ewe

A Survey on Stance Detection for Mis- and Disinformation Identification [article]

Momchil Hardalov, Arnav Arora, Preslav Nakov, Isabelle Augenstein
2021 arXiv   pre-print
Stance detection has been framed in different ways in the literature, including (a) as a component of fact-checking, rumour detection, and detecting previously fact-checked claims, or (b) as a task in  ...  Understanding the attitudes expressed in texts, also known as stance detection, plays an important role in systems aiming to detect false information online, be it misinformation (unintentionally false  ...  The success of these models is also seen in cross-lingual settings.  ... 
arXiv:2103.00242v2 fatcat:5a7uwxjvonhpxaamxobzjvyzm4

YNU_oxz at SemEval-2020 Task 12: Bidirectional GRU with Capsule for Identifying Multilingual Offensive Language

Xiaozhi Ou, Hongling Li
2020 Proceedings of the Fourteenth Workshop on Semantic Evaluation   unpublished
This article describes the system submitted to SemEval-2020 Task 12 OffensEval 2: Multilingual Offensive Language Recognition in Social Media.  ...  The task is to classify offensive language in social media. The shared task contains five languages (English, Greek, Arabic, Danish, and Turkish) and three subtasks.  ...  Fortuna and Nunes (2018) believed that the field of automatic detection of hate speech and offensive language in text is very important for online social platforms and has unquestionable potential for  ... 
doi:10.18653/v1/2020.semeval-1.300 fatcat:dpbveuofyffbdpmuf6wmadddgi

Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks [article]

Aakanksha Naik, Jill Lehman, Carolyn Rose
2021 arXiv   pre-print
Our answers to these questions highlight major avenues for future research in transfer learning for the long tail.  ...  We assess trends in transfer learning research through a qualitative meta-analysis of 100 representative papers on transfer learning for NLU.  ...  Social Security Administration.  ... 
arXiv:2111.01340v1 fatcat:rlg77auu3zfwdggxy3kwm7fu2m

An Impossible Dialogue! Nominal Utterances and Populist Rhetoric in an Italian Twitter Corpus of Hate Speech against Immigrants

Gloria Comandini, Viviana Patti
2019 Proceedings of the Third Workshop on Abusive Language Online   unpublished
Thus, human ratings in the context of toxicity in language raise important questions around the various socio-cultural biases that affect those ratings, but also on the impact it has on the psychological  ...  human-in-the-loop solutions that rely on crowd workers' ratings along with automated moderation, and embedding the evaluations of models into the cultural fabric.  ...  experiments on hate speech detection approaches, features and data sets.  ... 
doi:10.18653/v1/w19-3518 fatcat:liwo47b4kzblhifxy7gn4lrifq

Applications of Artificial Intelligence in Battling Against Covid-19: A Literature Review

Mohammad-H. Tayarani-N.
2020 Chaos, Solitons & Fractals  
We also tried to conclude the paper with ideas on how the problems can be tackled in a better way and provide some suggestions for future works.  ...  The rapid growth of the pandemic has wreaked havoc and prompted the need for immediate reactions to curb the effects.  ...  It is important for media, like social media to detect and remove them as soon as they are generated.  ... 
doi:10.1016/j.chaos.2020.110338 pmid:33041533 pmcid:PMC7532790 fatcat:gl3i37hag5gflajsa7fh6khvva

Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments [article]

Julian Risch, Anke Stoll, Lena Wilms, Michael Wiegand
All ensemble models outperform single models, while BERTweet is the winner of all individual models in every subtask.  ...  This paper describes our approach (ur-iw-hnt) for the Shared Task of GermEval2021 to identify toxic, engaging, and fact-claiming comments.  ...  Acknowledgements This work was supported by the project COURAGE: A Social Media Companion Safeguarding and Educating Students funded by the Volkswagen Foundation, grant number 95564.  ... 
doi:10.48415/2021/fhw5-x128 fatcat:u3fcq4x23jba7ic2a5ldcsdbna

Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey [article]

Jinjie Ni, Tom Young, Vlad Pandelea, Fuzhao Xue, Vinay Adiga, Erik Cambria
2021 arXiv   pre-print
Furthermore, we comprehensively review the evaluation methods and datasets for dialogue systems to pave the way for future research.  ...  , CNN, RNN, Hierarchical Recurrent Encoder-Decoder, Memory Networks, Attention, Transformer, Pointer Net, CopyNet, Reinforcement Learning, GANs, Knowledge Graph, Survey, Review  ...  question answering, dialogue reasoning, conversational semantic parsing, dialogue relation extraction, dialogue sentiment analysis, hate speech detection, MISC detection, etc.  ... 
arXiv:2105.04387v4 fatcat:stperoq73rgyja5b7zcfysjh5q

Talking Appalachian: voice, identity, and community

2013 ChoiceReviews  
We would like to thank the entire WVDP crew over the years for their research efforts and feedback on this essay.  ...  Many words and usages are in the process of diffusing geographically, moving along networks usually centered in urban areas or dispersing through media influences, regardless of whether their users move  ...  Mother's influence lives on in my daughter's work with female Appalachian folk artists and her position as a fund-raiser for Appalshop, a socially activist Appalachian film media organization.  ... 
doi:10.5860/choice.51-0157 fatcat:pmm2hvpyejg3vjapclw7ig7qaq


2012 Dementia and Geriatric Cognitive Disorders  
For example, monitoring for bulbar weakness and directing the early intervention of speech aids.  ...  Discussion: Our study confirms the presence of SQSTM1 gene mutations in patients with ALS. In addition, we detected SQSTM1 mutations in patients with FTLD.  ...  The case is presented for its rarity of relatively late onset of FTD with possible temporal association with a parasagittal meningioma, and the challenges faced in management.  ... 
doi:10.1159/000342903 pmid:23007027 fatcat:io2rfqz7hndlddkrquqhkjhm7m

Mapping (Dis-)Information Flow about the MH17 Plane Crash

Mareike Hartmann, Yevgeniy Golovchenko, Isabelle Augenstein
2019 Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda   unpublished
., neural networks, logistic regression) and representations (e.g., manually-engineered features, distributional representations).  ...  A total of 39 teams submitted runs; 21 teams participated in the FLC subtask and 35 teams took part in the SLC subtask.  ...  the establishment of the Centre for Linguistic Theory and Studies in Probability (CLASP) at the University of Gothenburg.  ... 
doi:10.18653/v1/d19-5006 fatcat:77l3dndrkvfmlhjt6qvnrassgi