A Comparison of Neural Network Training Methods for Text Classification
This work addresses text classification for weather prediction from social media, but it is incremental as it applies existing neural network methods to a new dataset.
The study tackled text classification for predicting weather conditions from Twitter messages, finding that deep neural networks with proper initialization and pretraining outperformed Support Vector Machines, with performance gains from additional hidden layers and Nesterov's Accelerated Gradient.
We study the impact of neural networks in text classification. Our focus is on training deep neural networks with proper weight initialization and greedy layer-wise pretraining. Results are compared with 1-layer neural networks and Support Vector Machines. We work with a dataset of labeled messages from the Twitter microblogging service and aim to predict weather conditions. A feature extraction procedure specific for the task is proposed, which applies dimensionality reduction using Latent Semantic Analysis. Our results show that neural networks outperform Support Vector Machines with Gaussian kernels, noticing performance gains from introducing additional hidden layers with nonlinearities. The impact of using Nesterov's Accelerated Gradient in backpropagation is also studied. We conclude that deep neural networks are a reasonable approach for text classification and propose further ideas to improve performance.