A Deep Learning Analytic Suite for Maximizing Twitter Impact

We present a series of deep learning models for predicting user engagement with twitter content, as measured by the number of retweets for a given tweet. We train models based on classic LSTM-RNN and CNN architectures, along with a more complex bi-directional LSTM-RNN with attention layer. We show that the attention RNN performs the best with 61% validation accuracy, but that all three deep learning models outperform human accuracy for the same task.