Skip to main content

Table 3 Configuration setting for each architecture

From: A deep neural network approach for sentiment analysis of medically related texts: an analysis of tweets related to concussions in sports

Model

Layer/Filter size

FFNN

[400, 400]

[400, 400, 400]

[775, 225, 75, 25]

Single layer CNN

[1, 2]

[1, 2, 3]

[3, 4, 5]

[1, 2, 3, 4, 5]

Multi-layer CNN

[1, 2]

GRU

[205]

LSTM

[205]

Bi-Dir LSTM

[205]

TCN

[3]