Fig. 4From: A deep neural network approach for sentiment analysis of medically related texts: an analysis of tweets related to concussions in sportsDiagram illustrating a 2-layer stack 1D convolution network. The first 1D convolution has 1 filter of size 1, generating a 3 - 1 feature map. A second convolution takes the 3 - 1 feature map and applies a 1D convolution with 2 filters of size 2, generating a 2 - 2 feature map. 1D max Pooling is then applied after the second convolution producing a vectorBack to article page