Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection

12/31/2020
by   Bertie Vidgen, et al.
0

We present a first-of-its-kind large synthetic training dataset for online hate classification, created from scratch with trained annotators over multiple rounds of dynamic data collection. We provide a 40,623 example dataset with annotations for fine-grained labels, including a large number of challenging contrastive perturbation examples. Unusually for an abusive content dataset, it comprises 54 performance and robustness can be greatly improved using the dynamic data collection paradigm. The model error rate decreased across rounds, from 72.1 in the first round to 35.8 increasingly harder to trick – even though content become progressively more adversarial as annotators became more experienced. Hate speech detection is an important and subtle problem that is still very challenging for existing AI methods. We hope that the models, dataset and dynamic system that we present here will help improve current approaches, having a positive social impact.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/24/2020

ANLIzing the Adversarial Natural Language Inference Dataset

We perform an in-depth error analysis of Adversarial NLI (ANLI), a recen...
10/16/2021

Analyzing Dynamic Adversarial Training Data in the Limit

To create models that are robust across a wide range of test inputs, tra...
07/19/2021

Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech

Undermining the impact of hateful content with informed and non-aggressi...
07/28/2017

Online Deception Detection Refueled by Real World Data Collection

The lack of large realistic datasets presents a bottleneck in online dec...
01/23/2020

The Pushshift Telegram Dataset

Messaging platforms, especially those with a mobile focus, have become i...
09/28/2020

Reactive Supervision: A New Method for Collecting Sarcasm Data

Sarcasm detection is an important task in affective computing, requiring...
04/27/2020

"Unsex me here": Revisiting Sexism Detection Using Psychological Scales and Adversarial Samples

To effectively tackle sexism online, research has focused on automated m...