Deep Regression Ensembles(DRE) - text analysis

I read an article about Deep Regression Ensembles(DRE), which can outperform DNN using SDG. My question is could I use DRE in text classification? (for example, I can use it instead of LDA) What about sentimental analysis? or is it just a method for estimating time-series data? (I am not really a master at DL, and my supervisor sent me this article to use in my research, but I don't know where I should use it. My research field is in energy finance and predicting the price of energies like crude oil.)

This is the abstract of the article: We introduce a methodology for designing and training deep neural networks (DNN) that we call “Deep Regression Ensembles (DRE). It bridges the gap between DNN and two-layer neural networks trained with random feature regression. Each layer of DRE has two components, randomly drawn input weights and output weights trained myopically (as if the final output layer) using linear ridge regression. Within a layer, each neuron uses a different subset of inputs and a different ridge penalty, constituting an ensemble of random feature ridge regressions. Our experiments show that a single DRE architecture is at par with or exceeds state-of-the-art DNN in many data sets. Yet, because DRE neural weights are either known in closed-form or randomly drawn, its computational cost is orders of magnitude smaller than DNN.