Sentiment analysis method based on CNN and attention mechanism

Lisha Yao; Junhao Zhao; Kang Su; Qingtong Shao

doi:10.1117/12.2642631

28 July 2022 Sentiment analysis method based on CNN and attention mechanism

Lisha Yao, Junhao Zhao, Kang Su, Qingtong Shao

Proceedings Volume 12303, International Conference on Cloud Computing, Internet of Things, and Computer Applications (CICA 2022); 1230317 (2022) https://doi.org/10.1117/12.2642631
Event: International Conference on Cloud Computing, Internet of Things, and Computer Applications, 2022, Luoyang, China

Abstract

Sentiment analysis of traditional deep learning algorithms does not fully consider text features and input optimization. To solve this problem, this paper proposes a deep learning model, namely CNN+ATT model, which combines the Convolutional Neural Network(CNN) model and the attention mechanism. In this paper, the sentiment analysis of the CHNSENTICORP-HTL-BA-6000 hotel review data set is carried out through the training of the convolutional neural network model. At the same time, combined with the deep learning algorithm of word2vec and Attention mechanism, compared with the CNN model, the method in this paper improves the accuracy and F1 value of the model.

Citation Download Citation

Lisha Yao, Junhao Zhao, Kang Su, and Qingtong Shao "Sentiment analysis method based on CNN and attention mechanism", Proc. SPIE 12303, International Conference on Cloud Computing, Internet of Things, and Computer Applications (CICA 2022), 1230317 (28 July 2022); https://doi.org/10.1117/12.2642631

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available