Enhanced Offensive Language Detection Through Data Augmentation

By Ruibo Liu, Guangxuan Xu, Soroush Vosoughi. 2020

10 citations recorded by the source corpus.

Detecting offensive language on social media is an important task. The ICWSM-2020 Data Challenge Task 2 is aimed at identifying offensive content using a crowd-sourced dataset containing 100k labelled tweets. The dataset, however, suffers from class imbalance, where certain labels are extremely rare compared with other classes (e.g, the hateful class is only 5% of the data). In this work, we present Dager (Data Augmenter), a generation-based data augmentation method, that improves the performance of classification on imbalanced and low-resource data such as the offensive language dataset. Dager extracts the lexical features of a given class, and uses these features to guide the generation of a conditional generator built on GPT-2. The generated text can then be added to the training set as augmentation data. We show that applying Dager can increase the F1 score of the data challenge by 11% when we use 1% of the whole dataset for training (using BERT for classification); moreover, the generated data also preserves the original labels very well. We test Dager on four different classifiers (BERT, CNN, Bi-LSTM with attention, and Transformer), observing universal improvement on the detection, indicating our method is effective and classifier-agnostic.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, Safety, Robustness & Interpretability

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

1. Varun Prashant Gangal
2. Soroush Vosoughi
3. Eduard H. Hovy
4. Teruko Mitamura
5. Jason Wei
6. Steven Y. Feng
7. Sarath Chandar
8. Mohit Bansal

In Information Systems

1. Varun Prashant Gangal
2. Eduard H. Hovy
3. Teruko Mitamura
4. Jason Wei
5. Sarath Chandar
6. Steven Y. Feng
7. Mirella Lapata
8. Chin-Yew Lin

In Natural Language Processing

1. Varun Prashant Gangal
2. Eduard H. Hovy
3. Teruko Mitamura
4. Soroush Vosoughi
5. Jason Wei
6. Steven Y. Feng
7. Sarath Chandar
8. Mohit Bansal

In Safety, Robustness & Interpretability

1. Jason Wei
2. Sarath Chandar
3. Eduard H. Hovy
4. Soroush Vosoughi

Citations in the corpus

• A Survey of Data Augmentation Approaches for NLP (2021, background): “…et al., 2021), augmenting misclassified examples (Dreossi et al., 2018), BERT cross-encoder labeling of new inputs (Thakur et al., 2021), guided generation us-ing large-scale generative language models (Liu et al., 2020b,c), and automated text augmentation (Hu et al., 2019; Cai et al., 2020).”