Aggression Detection in Social Media: Using Deep Neural Networks, Data Augmentation, and Pseudo Labeling
By Segun Taofeek Aroyehun, Alexander Gelbukh. 2018
148 citations recorded by the source corpus.
Subfields: Sentiment & Opinion Analysis, AI Ethics, Fairness & Society
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Sentiment & Opinion Analysis
- Marcos Zampieri
- Vukosi Marivate
- Husam Quteineh
- Spyridon Samothrakis
- Ritesh Kumar
- Helen Yannakoudakis
- Wanxiang Che
- Bohan Li
In AI Ethics, Fairness & Society
- Sara Rosenthal
- Marcos Zampieri
- Eugene Yang
- Preslav Nakov
- Nazli Goharian
- Vukosi Marivate
- Husam Quteineh
- Spyridon Samothrakis
Citations in the corpus
- SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval) (2019, methodology): “The best performing systems in this competition used deep learning approaches based on convolutional neural networks (CNN), recurrent neural networks, and LSTMs (Aroyehun and Gelbukh, 2018; Majumder et al., 2018).”
- Textual Data Augmentation for Efficient Active Learning on Tiny Datasets (2020, methodology): “This technique is applied in the works of Sennrich et al. (2015); Aroyehun and Gelbukh (2018).”
- A Unified Deep Learning Architecture for Abuse Detection (2018, background): “Finally, authors in [1] succeed to detect aggression on Facebook posts with an LSTM classifier combined with word embeddings.”
- Benchmarking Aggression Identification in Social Media (2018, background): “Team Hindi English System Description Paper saroyehun X (Aroyehun and Gelbukh, 2018) EBSI-LIA-UNAM X (Arroyo-Fernández et al.”
- Hate speech detection: Challenges and solutions (2019, methodology): “6425 using a recurrent neural network, without reporting accuracy or macro-averaged F1 [19, 42].”
- Data Augmentation Approaches in Natural Language Processing: A Survey (2021, methodology): “In addition to some trained machine translation models, Google’s Cloud Translation API service is a common tool for back-translation widely applied by some works like [7, 19, 59, 42, 60, 61, 10, 62, 63].”
- Improving short text classification through global augmentation methods (2019, methodology): “al sentences are translated with an existing machine translation system into source language, that is used as additional parallel data to retrain the source-to-target NMT model. Aroye hun and Gelbukh [2] used English RTT on four intermediate languages (French, Spanish, German, and Hindi) that increa”
- Tackling Online Abuse: A Survey of Automated Abuse Detection Methods (2019, methodology): “The top approach on the task’s English dataset (Aroyehun and Gelbukh, 2018) comprised RNN s and CNN s along with transfer learning via machine translation (macro F 1 of 64 .”