9,498 Hits in 6.1 sec

Author Profiling for Hate Speech Detection [article]

Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis, Ekaterina Shutova
2019 arXiv   pre-print
Experimenting with a dataset of 16k tweets, we show that our methods significantly outperform the current state of the art in hate speech detection.  ...  The current state-of-the-art approaches to hate speech detection are oblivious to user and community information and rely entirely on textual (i.e., lexical and semantic) cues.  ...  hate speech detection.  ... 
arXiv:1902.06734v1 fatcat:6f7wliv4dnfg7hfqmhtapgnmf4

Early Detection of Online Hate Speech Spreaders with Learned User Representations

Darius Irani, Avyakta Wrat, Silvio Amir
2021 Conference and Labs of the Evaluation Forum  
We developed and evaluated models for early detection of online hate speech spreaders.  ...  can combined to improve hate speech detection.  ...  Experiments We investigate the impact of learned user-level representations on the performance of author profiling models for online hate speech detection.  ... 
dblp:conf/clef/IraniWA21 fatcat:xksihdhoj5fpxnxuob2bva2iku

Phonetic Detection for Hate Speech Spreaders on Twitter

Edwin Puertas, Juan Carlos Martínez Santos
2021 Conference and Labs of the Evaluation Forum  
Here, we illustrate how we used lexical and phonetic features to determine if the author spreads hate speech.  ...  Efficient and effective detection of hate profiles requires various scientific disciplines, such as computational linguistics and sociology.  ...  The model used for Profiling Hate Speech Spreaders on Twitter at PAN 2021 determines whether the author of a Twitter feed spreads hate speech.  ... 
dblp:conf/clef/PuertasS21 fatcat:lgf2xhj7wjdj7ncchqvbwdq4di

Profiling Hate Speech Spreaders on Twitter: SVM vs. Bi-LSTM

Inna Vogel, Meghana Meghana
2021 Conference and Labs of the Evaluation Forum  
Additionally, the psychological burden of manual moderation has necessitated the need for automated hate speech detection methods.  ...  In this notebook, we describe our profiling system to the PAN at CLEF 2021 lab "Profiling Hate Speech Spreaders on Twitter".  ...  the National Research Center for Applied Cybersecurity ATHENE and under grant agreement "Lernlabor Cybersicherheit" (LLCS) for cyber security research and training.  ... 
dblp:conf/clef/VogelM21 fatcat:63sjkugi7ngzba5mpu76plt5pe

Profiling Hate Speech Spreaders on Twitter Task at PAN 2021

Francisco Rangel, Gretel Liz De la Peña Sarracén, Berta Chulvi, Elisabetta Fersini, Paolo Rosso
2021 Conference and Labs of the Evaluation Forum  
This overview presents the Author Profiling shared task at PAN 2021. The focus of this year's task is on determining whether or not the author of a Twitter feed is keen to spread hate speech.  ...  The main aim is to show the feasibility of automatically identifying potential hate speech spreaders on Twitter.  ...  We thank Symanto for sponsoring again the award for the best performing system at the author profiling shared task  ... 
dblp:conf/clef/RangelSCFR21 fatcat:xoovcnyeazha3mim3zudxlddpq

Profiling Hate Speech Spreaders on Twitter

Kumar Gourav Das, Buddhadeb Garai, Srijan Das, Braja Gopal Patra
2021 Conference and Labs of the Evaluation Forum  
This has aggravated over time because spreading hate speech is often inconsequential to its authors. Hate speech detection can help organizations identify, monitor and manage hate speech spreaders.  ...  This task aims to identify whether the author of the tweets spreads hate speech.  ...  The combination of lexicons and ML approaches obtained better results for classifying hate speech detection [24] .  ... 
dblp:conf/clef/DasGDP21 fatcat:mqekbtiuinbdxj2b3ypkj6iaqe

Profiling Spreaders of Hate Speech with N-grams and RoBERTa

Christopher Bagdon
2021 Conference and Labs of the Evaluation Forum  
This paper outlines our approach to the 2021 CLEF Conference Shared Task, Profiling Hate Speech Spreaders on Twitter.  ...  On the test set our system performed moderately well in comparison to other submissions, with 81% accuracy for Spanish and 67% for English. Overall our system placed 15 th of 66 entries.  ...  This paper details our submission to the 2021 PAN Author Profiling Shared Task, Profiling Hate Speech Spreaders on Twitter.  ... 
dblp:conf/clef/Bagdon21 fatcat:qq6pffairrdhlb6ytuqpdecsze

Profiling Hate Speech Spreaders by Classifying Micro Texts Using BERT Model

Esam Alzahrani, Leon Jololian
2021 Conference and Labs of the Evaluation Forum  
Hate speech detection has lately gained considerable attention from researchers. To profile authors effectively, we consider classifying all tweets for a specific author independently.  ...  Then, we added an extra layer, called a confidence layer, by which we calculate the percentage of classified hateful tweets by the model and decide whether this author is spreading hate speech or not.  ...  The goal of this task is to profile authors who are seen as hate speech spreaders on Twitter.  ... 
dblp:conf/clef/AlzahraniJ21 fatcat:egcnecorpvfbvmu3jvtzaxicxi

Profiling Hate Speech Spreaders on Twitter: Transformers and mixed pooling

Álvaro Huertas-García, Javier Huertas-Tato, Alejandro Martín, David Camacho
2021 Conference and Labs of the Evaluation Forum  
In this work, we propose a system for Authors Profiling Hate Speech Spreaders in the Twitter Spanish and English tasks at PAN@CLEF 2021.  ...  We explore the incorporation of features from Transformer-based models, Sentiment Analysis, and Hate lexicons to boost the feature extraction process.  ...  funding agencies: Spanish Ministry of Science and Innovation under TIN2017-85727-C4-3-P (DeepBio) grant, by Comunidad Autónoma de Madrid under S2018/TCS-4566 grant (CYNAMON), and by BBVA FOUNDATION GRANTS FOR  ... 
dblp:conf/clef/Huertas-GarciaH21a fatcat:uxfty7tvjbbhtn53jrvfiftktq

You Are What You Tweet: Profiling Users by Past Tweets to Improve Hate Speech Detection [article]

Prateek Chaudhry, Matthew Lease
2021 arXiv   pre-print
We then investigate profiling users by their past utterances as an informative prior to better predict whether new utterances constitute hate speech.  ...  Hate speech detection research has predominantly focused on purely content-based methods, without exploiting any additional context. We briefly critique pros and cons of this task formulation.  ...  Acknowledgments We thank the reviewers for their valuable feedback, and the many talented workers who provided the hate speech annotations that enable research on it.  ... 
arXiv:2012.09090v2 fatcat:2qn4g3rpuzb5ncvuxgj6autcem

Unified and Multilingual Author Profiling for Detecting Haters [article]

Ipek Baris Schlicht, Angel Felipe Magnossão de Paula
2021 arXiv   pre-print
This paper presents a unified user profiling framework to identify hate speech spreaders by processing their tweets regardless of the language.  ...  The framework encodes the tweets with sentence transformers and applies an attention mechanism to select important tweets for learning user profiles.  ...  AI systems are encouraged for easing the process and understanding the rationales behind hate speech dissemination [7, 8] .  ... 
arXiv:2109.09233v1 fatcat:7qpmlg5ebrc2xbqa2nm6g6vdoq

Hate Speech Detection on Twitter

Carolina Martín del Campo Rodríguez, Grigori Sidorov, Ildar Z. Batyrshin
2021 Conference and Labs of the Evaluation Forum  
hate speech; the second based in the concatenation of tweets by author for processing.  ...  This document describes two approaches taken to detect hate speech by author: the first based on the individual processing of tweets by the author, which establishes a threshold of hate tweets to identify  ...  In this paper we describe our approach to detect hate speech authors on Twitter applying Support Vector Machine and Deep Neural Networks, participating in the PAN 2021 [4] task "Profiling Hate Speech  ... 
dblp:conf/clef/RodriguezSB21 fatcat:jxpuzb7yzbhwniyogtdqrimfx4

Hindi-English Hate Speech Detection: Author Profiling, Debiasing, and Practical Perspectives

Shivang Chopra, Ramit Sawhney, Puneet Mathur, Rajiv Ratn Shah
In an attempt to bridge this gap, we introduce a three-tier pipeline that employs profanity modeling, deep graph embeddings, and author profiling to retrieve instances of hate speech in Hindi-English code-switched  ...  Code-switching in linguistically diverse, low resource languages is often semantically complex and lacks sophisticated methodologies that can be applied to real-world data for precisely detecting hate  ...  Community based Author Profiling Representations of users in a social network have been utilized for author profiling because people connected on social media are likely to post similarly.  ... 
doi:10.1609/aaai.v34i01.5374 fatcat:ywifnbgg7vayhbuyxf6kkblzcu

Use of Lexical and Psycho-Emotional Information to Detect Hate Speech Spreaders on Twitter - Notebook for PAN at CLEF 2021

Riccardo Cervero
2021 Conference and Labs of the Evaluation Forum  
This notebook summarises the participation at the "Profiling Hate Speech Spreaders on Twitter" shared task [1] at PAN at CLEF 2021 [2] , and describes the proposed method for the goal of binary classification  ...  into hate speech spreaders and non spreaders.  ...  For the participation to the "Profiling Hate Speech Spreaders on Twitter" task at PAN at CLEF 2021, an ensemble method inspired by a previous work by Buda and Bolonyai is proposed for the detection of  ... 
dblp:conf/clef/Cervero21 fatcat:r3l2afx2djdktkpvwpy5ivlncy

Hate speech spreader detection using contextualized word embeddings

Evgeny Finogeev, Mariam Kaprielova, Artem Chashchin, Kirill Grashchenkov, George Gorbachev, Oleg Bakhteev
2021 Conference and Labs of the Evaluation Forum  
he paper presents a method of hate speech spreaders recognition developed for the task of "Profiling Hate Speech Spreaders on Twitter" at the PAN@CLEF Conference 2021.  ...  In this paper, we present a model to detect hate speech spreaders based on their Twitter posts.  ...  Hate Speech Spreaders profiling task considers the problem of hate speech detection in social networks [6, 7] : given a set of tweets written by a user, one should establish, whether the user can potentially  ... 
dblp:conf/clef/FinogeevKCGGB21 fatcat:drtf7dm56fdejaniedthrf6rmu
« Previous Showing results 1 — 15 out of 9,498 results