Improving LSTMs’ under-performance in Authorship Attribution for short texts

Abstract

We present a novel approach for conducting authorship attribution over tweets using Long-Short Term Memory networks (LSTMs). Vanilla LSTMs use the last hidden state for prediction. Our strategy introduces a mechanism based on Max Pooling to process all the hidden states simultaneously, which helps the model to better detect authors' stylometry. We obtain a 4% accuracy improvement with respect to vanilla LSTMs. CCS CONCEPTS• Computing methodologies → Neural networks; • Security and privacy → Social network security and privacy.