Detecting Hate Speech on Twitter Using a Convolution-GRU Based Deep Neural Network

By Ziqi Zhang, David Robinson, Jonathan A. Tepper. 2018

653 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Communication, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Communication

In Natural Language Processing

Citations in the corpus

The Risk of Racial Bias in Hate Speech Detection (2019, background): “Many datasets have been created, but most are either small-scale pilots ( ∼ 100 instances; Kwok and Wang, 2013; Burnap and Williams, 2015; Zhang et al., 2018), or focus on other domains (e.g., Wikipedia edits; Wulczyn et al., 2017).”
Challenges and frontiers in abusive content detection (2019, methodology): “Key innovations include the use of deep learning and ensemble architectures, using contextual word embeddings, applying dependency parsing, and the inclusion of user-level variables within models (Badjatiya, Gupta, Gupta, & Varma, 2017; Zhang et al., 2018).”
Challenges for Toxic Comment Classification: An In-Depth Error Analysis (2018, methodology): “We analyse common error classes of our ensemble based on research from Zhang and Luo (2018); Zhang et al. (2018); Qian et al. (2018); Davidson et al. (2017); Schmidt and Wiegand (2017); No-bata et al. (2016).”
HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection (2020, methodology): “Several hate speech datasets (Ousidhoum et al. 2019; Qian et al. 2019b; de Gibert et al. 2018; Sanguinetti et al. 2018), models (Zhang, Robinson, and Tepper 2018; Mishra et al. 2018; Qian et al. 2018b,a), and shared tasks (Basile et al. 2019; Bosco et al. 2018) have been made available in the…”
All You Need is "Love": Evading Hate Speech Detection (2018, methodology): “However, CNN+GRU trained on T2 was more resilient to all attacks than LSTM trained on T2, indicating that model choice also had an eﬀect. results from all attacks and their mitigation are presented in Table 8.”
Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases (2021, methodology): “Supervised training based methods rely on large labeled datasets to train models (Badjatiya et al., 2017; Pavlopoulos et al., 2017; Zhang et al., 2018; D’sa et al., 2019; Caselli et al., 2020; Silva et al., 2020).”
Cross-Domain Detection of Abusive Language Online (2018, background): “works (Pavlopoulos et al., 2017; Gao and Huang, 2017; Pitsilis et al., 2018; Zhang et al., 2018).”
Studying Generalisability across Abusive Language Detection Datasets (2019, background): “Deep Neural networks such as Convolutional Neural Networks, CNN (Zhang et al., 2018; Gamb¨ack and Sikdar, 2017) and variations of Recurrent Neural Networks, RNN (Pitsilis et al., 2018; Gao and Huang, 2017) have seen widespread success, regularly obtaining state-of-the-art results on various datasets”
Aggression Detection in Social Media: Using Deep Neural Networks, Data Augmentation, and Pseudo Labeling (2018, background): “(Gambäck and Sikdar, 2017) employed convolutional neural networks to classify hate speech and (Zhang et al., 2018) used a combination of convolutional neural network and gated recurrent unit (GRU) for the same task.”
Tackling Online Abuse: A Survey of Automated Abuse Detection Methods (2019, background): “Some researchers (Wang, 2018; Zhang et al., 2018) have shown that sequentially combining CNN s with gated recurrent unit ( GRU ) RNN s can enhance performance by taking advantage of properties of both architectures (e.g., 1-2% increase in F 1 compared to only using CNN s).”
Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection (2020, background): “, 2009), to more recent neural networks (Park and Fung, 2017; Zhang and Tepper, 2018; Agrawal and Awekar, 2018; Corazza et al., 2018).”
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research (2022, methodology): “Several models 826 including CNN-GRU [172], BiRNN [173], and BiRNN- 827 Attention [174] were used and tested on this dataset 828 whereas explainability-based metrics such as Intersection- 829 Over-Union (IOU), comprehensiveness, and sufficiency were 830 utilized to evaluate the model interpretabilit”
Detecting harassment in real-time as conversations develop (2019, background): “Zhang et al. (2018b) conduct an extensive evaluation of approaches for detecting hate speech so far and propose a combination of CNNs and RNNs to outperform them.”
Abusive Language Detection using Syntactic Dependency Graphs (2020, neutral): “Current state-of-the-art methods in abusive language detection use either n-gram features (Waseem and Hovy, 2016; Davidson et al., 2017) or employ sequential deep learning models like CNN or LSTM (Zhang et al., 2018b; Badjatiya et al., 2017).”
BEEP! Korean Corpus of Online News Comments for Toxic Speech Detection (2020, background): “, neologism, polysemy, use-mention distinction), and more importantly, not all hate speech are detectable using such terms (Zhang et al., 2018).”
Predictive Embeddings for Hate Speech Detection on Twitter (2018, methodology): “Zhang et al. (2018), meanwhile, used pre-trained word2vec embeddings, which were then fed into a convolutional neural network (CNN) with max pooling to produce input vectors for a Gated Recurrent Unit (GRU) neural network.”
HABERTOR: An Efficient and Effective Deep Hatespeech Detector (2020, methodology): “, 2017; Agrawal and Awekar, 2018), combining CNN with RNN (Zhang et al., 2018), or fine tuning a pretrained language models (Indurthi et al.”