A Novel Sentiment Classification Architecture Based on Self-attention Mechanism

Zhang, Rui; Chen, Binbin; Tang, Hongbo

doi:10.1007/978-981-16-1726-3_85

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The output of attention layer, the last hidden state of BiLSTM and max pooled features of CNN were later concatenated to be passed to a fully connected layer and classified using a softmax layer. Zhang et al [32] used fused parts of speech tagging with embedding, which further help increase syntactic and semantic knowledge capture when passed through attention layers. Huang et al [33] used transformer block instead of using only an attention layer.…”

Section: Related Workmentioning

confidence: 99%

An Experimental Analysis of Deep Neural Network Based Classifiers for Sentiment Analysis Task

Shukla

Kumar

2023

IEEE Access

View full text Add to dashboard Cite

The application of natural language processing (NLP) in sentiment analysis task by using textual data has wide scale application across various domains in plethora of industries. We have methodically studied pre-existing models and proposed new models for examining sentiment analysis task. The models proposed were analysed with three widely popular word embeddings separately and in combined approach using all embeddings as unique channels. We combined deep neural network models such as Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Network (CNN) so that integrated models complement each other with their unique architectures. The word embeddings used had profound impact in accuracy of models owing to performative changes. The best word embedding was Word2Vec giving highest accuracy in almost all implemented models, followed by GloVe. FastText embedding performed consistently worse, giving much lower accuracy than other embeddings. We also observed that adding transformer encoder layers with CNN improves accuracy by 2% when compared to CNN without any transformer layers. An accuracy improvement of 2-3% over CNN-BiLSTM model was also observed by utilizing transformer encoder layer in conjunction with both BiLSTM and CNN. The proposed model achieved an accuracy of 89.04% on SST-2 dataset. We also compared larger pretrained language model used in sentiment analysis task with our proposed approach. The accuracy values obtained through combination of embeddings and models can be useful for other researchers when selecting word embeddings for their models.

show abstract

Section: Related Workmentioning

confidence: 99%