Character-level and Multi-channel Convolutional Neural Networks for Large-scale Authorship Attribution

Understand

Convolutional neural networks (CNNs) have demonstrated superior capability for extracting information from raw signals in computer vision.

• Recently, character-level and multi-channel CNNs have exhibited excellent performance for sentence classification tasks.
• We apply CNNs to large-scale authorship attribution, which aims to determine an unknown text's author among many candidate authors, motivated by their ability to process character-level signals and to differentiate between a large number of classes, while making fast predictions in comparison to state-of-the-art approaches.
• We extensively evaluate CNN-based approaches that leverage word and character channels and compare them against state-of-the-art methods for a large range of author numbers, shedding new light on traditional approaches.