A Compression-based BiLSTM for Treating Teenagers’ Depression Chatbot

Anxiety is a psychological condition that often occurs during adolescence. Due to lack of relief and counseling, teenager’s psychological anxiety may gradually develop into anxiety. Chabot can be used as a new tool to relieve anxiety among teenagers. However, the natural language understanding techniques currently applied to Chabot still have problems, such as lack of effective data, high training complexity, and lack of interpretability of the network. This paper proposes a compression-based bidirectional Long Short-Term Memory depth neural network structure. The main objective is to reduce the complexity of the parameters further, and to make the network of each layer have certain interpretability by means of the reduction of sparsity. Under our own collection of teen depression text data, this structure shows a better performance than traditional networks.