Corresponding Author

Han Lai, Huanghuai University, Henan, China, han.lai@hotmail.com

Document Type

Work in Progress

Abstract

This study is to develop a sentiment analysis system for customers’ review on a scenic site. It is based on Convolutional Neural Networks (CNNs) built on Long Short-Term Memory (LSTM) models for text feature extraction under a deep learning framework. The CNNs built on LSTM models applies convolutional filters of CNNs repeatedly operate on the output matrix of LSTM to obtain robust text feature vector. In this study, the optimal parameter configurations for each component of CNNs and LSTM are given individually in the first place. Then, the entire optimal parameter configuration for the integration recognition frame of the system is identified around the optimum of each component. The results demonstrate that, by employing such a method, the accuracy for sentiment analysis with CNNs built on LSTM model, compared with a single CNNs or LSTM model, is improved by 3.13% and 1.71% respectively.

Share

COinS