# Detecting Offensive Language in Tweets Using Deep Learning

arXiv: https://arxiv.org/abs/1801.04433 · HTML: https://mlsanity.com/paper/1801.04433/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2018.

## Built on by (most cited first, 23 of 23)

- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations](https://mlsanity.com/paper/2406.12223/) (2024)
- [A systematic review of Hate Speech automatic detection using Natural Language Processing](https://mlsanity.com/paper/2106.00742/) (2021)
- [Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Model](https://mlsanity.com/paper/2111.01515/) (2021)
- [Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate](https://mlsanity.com/paper/2106.05903/) (2021)
- [Hate Speech Detection in Roman Urdu](https://mlsanity.com/paper/2108.02830/) (2021)
- [Offensive Language Identification in Low-resourced Code-mixed Dravidian languages using Pseudo-labeling](https://mlsanity.com/paper/2108.12177/) (2021)
- [User-Aware Multilingual Abusive Content Detection in Social Media](https://mlsanity.com/paper/2410.21321/) (2024)
- [T5 for Hate Speech, Augmented Data and Ensemble](https://mlsanity.com/paper/2210.05480/) (2022)
- [The Naughtyformer: A Transformer Understands Offensive Humor](https://mlsanity.com/paper/2211.14369/) (2022)
- [Down the Rabbit Hole: Detecting Online Extremism, Radicalisation, and Politicised Hate Speech](https://mlsanity.com/paper/2301.11579/) (2023)
- [Chinese Offensive Language Detection:Current Status and Future Directions](https://mlsanity.com/paper/2403.18314/) (2024)
- [Selecting and combining complementary feature representations and classifiers for hate speech detection](https://mlsanity.com/paper/2201.06721/) (2022)
- [MasonPerplexity at ClimateActivism 2024: Integrating Advanced Ensemble Techniques and Data Augmentation for Climate Activism Stance and Hate Event Identification](https://mlsanity.com/paper/2402.01976/) (2024)
- [SOLD: Sinhala Offensive Language Dataset](https://mlsanity.com/paper/2212.00851/) (2022)
- [Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem](https://mlsanity.com/paper/2204.10521/) (2022)
- [AtteSTNet -- An attention and subword tokenization based approach for code-switched text hate speech detection](https://mlsanity.com/paper/2112.11479/) (2021)
- [Improved two-stage hate speech classification for twitter based on Deep Neural Networks](https://mlsanity.com/paper/2206.04162/) (2022)
- ["Can We Detect Substance Use Disorder?": Knowledge and Time Aware Classification on Social Media from Darkweb](https://mlsanity.com/paper/2304.10512/) (2023)
- [Hate Content Detection via Novel Pre-Processing Sequencing and Ensemble Methods](https://mlsanity.com/paper/2409.05134/) (2024)
- [A Unified Multi-Task Learning Architecture for Hate Detection Leveraging User-Based Information](https://mlsanity.com/paper/2411.06855/) (2024)
- [Exploration and Evaluation of Bias in Cyberbullying Detection with Machine Learning](https://mlsanity.com/paper/2412.00609/) (2024)
- [The Hidden Language of Harm: Examining the Role of Emojis in Harmful Online Communication and Content Moderation](https://mlsanity.com/paper/2506.00583/) (2025)

## Abstract (arXiv)

This paper addresses the important problem of discerning hateful content in social media. We propose a detection scheme that is an ensemble of Recurrent Neural Network (RNN) classifiers, and it incorporates various features associated with user-related information, such as the users' tendency towards racism or sexism. These data are fed as input to the above classifiers along with the word frequency vectors derived from the textual content. Our approach has been evaluated on a publicly available corpus of 16k tweets, and the results demonstrate its effectiveness in comparison to existing state of the art solutions. More specifically, our scheme can successfully distinguish racism and sexism messages from normal text, and achieve higher classification quality than current state-of-the-art algorithms.