Abusive Comment Detection

Tencent Cloud Developer

Mar 21, 2018 · Artificial Intelligence

Abusive Comment Detection Using TextCNN: A Strategy + Algorithm Approach

The article proposes a hybrid approach that first filters blacklist words and then classifies suspicious comments with a character-level TextCNN, achieving around 89% precision and 87% recall, demonstrating that simple convolutional networks outperform keyword filters and RNNs for short, noisy abusive Chinese text.