8 Hits in 2.9 sec

Sexism Identification in Tweets and Gabs using Deep Neural Networks [article]

Amikul Kalra, Arkaitz Zubiaga
2021 arXiv   pre-print
binary and multiclass sexism classification on the dataset of tweets and gabs from the sEXism Identification in Social neTworks (EXIST) task in IberLEF 2021.  ...  This paper explores the classification of sexism in text using a variety of deep neural network model architectures such as Long-Short-Term Memory (LSTMs) and Convolutional Neural Networks (CNNs).  ...  This paper presented a variety of deep neural networks using BERT and DistilBERT to differentiate sexist tweets and gabs from non-sexist ones, as well as further classify sexist text into types of sexism  ... 
arXiv:2111.03612v1 fatcat:jhwntmhj2zewrcaryluwh66zji

Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models [article]

Angel Felipe Magnossão de Paula and Roberto Fray da Silva and Ipek Baris Schlicht
2021 arXiv   pre-print
This work proposes a system to use multilingual and monolingual BERT and data points translation and ensemble strategies for sexism identification and classification in English and Spanish.  ...  It was conducted in the context of the sEXism Identification in Social neTworks shared 2021 (EXIST 2021) task, proposed by the Iberian Languages Evaluation Forum (IberLEF).  ...  ); and (ii) Gab, with 492 gabs in English and 490 gabs in Spanish (used only for testing purposes).  ... 
arXiv:2111.04551v1 fatcat:v3vkvdwbanhs3ebuypnu7fexfy

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

Md Saroar Jahan, Mourad Oussalah
2021 arXiv   pre-print
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  ...  In the sequel, existing surveys, limitations, and future research directions are extensively discussed.  ...  Commonly word embedding can be jointly used in a neural network model as an embedding layer which helps to enhance deep learning performance.  ... 
arXiv:2106.00742v1 fatcat:qwxjwgma4zaynemge57cu7xqlm

ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI [article]

Amanda Cercas Curry, Gavin Abercrombie, Verena Rieser
2021 arXiv   pre-print
We present the first English corpus study on abusive language towards three conversational AI systems gathered "in the wild": an open-domain social bot, a rule-based chatbot, and a task-based system.  ...  We find that the distribution of abuse is vastly different compared to other commonly used datasets, with more sexually tinted aggression towards the virtual persona of these systems.  ...  We use l2 normalisation and set C=1. • Multi-Layer Perceptron: A standard neural network with one hidden layer consisting of 256 units, ReLu activation, a dropout rate of 0.75, and Adam optimisation with  ... 
arXiv:2109.09483v1 fatcat:h434pu77lzdhjkmx6jqks3mray

An Information Retrieval Approach to Building Datasets for Hate Speech Detection [article]

Md Mustafizur Rahman, Dinesh Balakrishnan, Dhiraj Murthy, Mucahid Kutlu, Matthew Lease
2021 arXiv   pre-print
To intelligently and efficiently select which tweets to annotate, we apply standard IR techniques of pooling and active learning.  ...  Firstly, because hate speech is relatively rare, random sampling of tweets to annotate is very inefficient in finding hate speech.  ...  This research was supported in part by Wipro (HELIOS), the Knight Foundation, the Micron Foundation, and Good Systems (, a UT Austin Grand Challenge to develop responsible  ... 
arXiv:2106.09775v3 fatcat:56cg2t7nwbfe3lwdqw7z2eqjoy

Directions in abusive language training data, a systematic review: Garbage in, garbage out

Bertie Vidgen, Leon Derczynski, Natalia Grabar
2020 PLoS ONE  
However, creating training datasets which are large, varied, theoretically-informed and that minimize biases is difficult, laborious and requires deep expertise.  ...  We discuss the challenges and opportunities of open science in this field, and argue that although more dataset sharing would bring many benefits it also poses social and ethical risks which need careful  ...  Alex Harris for providing research assistance and feedback. Author Contributions Conceptualization: Bertie Vidgen, Leon Derczynski.  ... 
doi:10.1371/journal.pone.0243300 pmid:33370298 fatcat:o42xcoc5ybarjac7opss6cizti

Biologically-inspired machine learning approaches to large-scale neural data analysis

Pamela Hathway, Daniel Goodman, Imperial College London
I investigate whether a spiking neural network equipped with biologically plausible synaptic learning rules can provide a biologically interpretable way of finding repeating spike patterns in neuronal  ...  Recent progress in recording techniques now allows researchers to record from hundreds and even thousands of neurons simultaneously.  ...  to contemplate sexism in the use of language -a goal as important as neural data analysis. within each 100 ms time window.  ... 
doi:10.25560/86622 fatcat:syvbv5t56rgojoknlhjyyphgae

CCCC Reviews Coordinator Reviews Editors Reviews Assistant Editors Kairos Senior Editor and Publisher Kairos Editor Book Design #4C15: What Were We Talking about When We Were Tweeting?

Andrea Beaudin, Andrea Beaudin, Steven Corbett, Chris Dean, Alexis Hart, Will Hochman, Michelle Lafrance, Randall Mcclure, Kathy Patterson, Angela Shaffer, Fred Siegel, Stephanie Vie (+17 others)
Using a smaller time frame than Beaudin and inspired by Collin Brooke's tweet archive of CWCON, I used the software Tweet Archivist to collect Figure 1.  ...  Having developed an interest in conference tweeting experiences after studying the tweets from Computers and Writing 2014 (#cwcon) with a colleague, I decided to create my own tweet archive for CCCC 2015  ...  Bre's tenor and moxie were a perfect match for us to talk nonstop, gabbing way past cordial and surface discourse to the heart and point of common insights, analyses, and experiences.  ...