Deep Learning for Detecting Cyberbullying Across Multiple Social Media Platforms

By Sweta Agrawal, Amit Awekar. European Conference on Information Retrieval, 2018

349 citations recorded by the source corpus.

Harassment by cyberbullies is a significant phenomenon on the social media. Existing works for cyberbullying detection have at least one of the following three bottlenecks. First, they target only one particular social media platform (SMP). Second, they address just one topic of cyberbullying. Third, they rely on carefully handcrafted features of the data. We show that deep learning based models can overcome all three bottlenecks. Knowledge learned by these models on one dataset can be transferred to other datasets. We performed extensive experiments using three real-world datasets: Formspring (12k posts), Twitter (16k posts), and Wikipedia(100k posts). Our experiments provide several useful insights about cyberbullying detection. To the best of our knowledge, this is the first work that systematically analyzes cyberbullying detection on various topics across multiple SMPs using deep learning based models and transfer learning.

Subfields: Artificial Intelligence, Social Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/bcf9b7058473787ea925fd6ee6b1e0706ce986a5

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 Social Psychology

In Signal Processing

Citations in the corpus

Abusive Language Detection using Syntactic Dependency Graphs (2020, methodology): “Earlier studies have either used the CNN (Gambäck and Sikdar, 2017; Park and Fung, 2017) or RNN (Badjatiya et al., 2017; Agrawal and Awekar, 2018) to compute these embeddings.”
Toxicity Detection can be Sensitive to the Conversational Context (2021, background): “Cyberbullies attack victims on different topics such as race, religion, and gender across multiple social media platforms (Agrawal and Awekar, 2018).”
Overview of the GermEval 2018 Shared Task on the Identification of Offensive Language (2018, background): “On several comparable English datasets, much higher classification scores have been reported (Agrawal and Awekar, 2018; Badjatiya et al., 2017).”
Challenges and frontiers in abusive content detection (2019, background): “Initial studies show this can help improve performance by leveraging existing datasets when there is little training data available (Agrawal & Awekar, 2018; Karan & Šnajder, 2018).”
Detection of Abusive Language: the Problem of Biased Datasets (2019, methodology): “We need to ﬁnd an explanation for this deviation since Waseem is by far the most frequently used dataset for detecting abusive language (Badjatiya et al., 2017; Bourgonje et al., 2017; Pitsilis et al., 2018; Agrawal and Awekar, 2018; Karan and Snajder, 2018; Kshirsagar et”
HABERTOR: An Efficient and Effective Deep Hatespeech Detector (2020, methodology): “Recent works have used deep neural network architectures for hatespeech detection (Zampieri et al., 2019; Mou et al., 2020) such as CNN (Gambäck and Sikdar, 2017; Park and Fung, 2017), RNN (i.e. LSTM and GRU) (Badjatiya et al., 2017; Agrawal and Awekar, 2018), combining CNN with RNN (Zhang et al., ”
DeepHate: Hate Speech Detection via Multi-Faceted Text Representations (2020, methodology): “• LSTM: The LSTM model ,is another model that was commonly explored in previous hate speech detection studies [1, 3, 21].”
Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection (2020, neutral): “…a combination of manually crafted features such as n-grams (Wulczyn et al., 2017), syntactic features (Nobata et al., 2016), and linguistic features (Yin et al., 2009), to more recent neural networks (Park and Fung, 2017; Zhang and Tepper, 2018; Agrawal and Awekar, 2018; Corazza et al., 2018).”