Abstract
In order to solve the high-dimensional data set of employees’ sentiment analysis on enterprise comment, in this paper, we presented three model algorithms: SVM algorithm, PCA-SVM algorithm, and AE-SVM algorithm. And we made a comparative analysis of three index parameters such as the precision, recall and F1 in three different algorithm model scenarios. According to the experimental results, the AE-SVM algorithm is superior to other two algorithms in this kind of Chinese text sentiment analysis. Based on the AE-SVM Algorithm, we also design a solution of sentiment analysis platform of employee comment. This solution has the characteristics of high availability and high concurrency. It can also collect and analyse the sentiment text information of employees’ comment in time.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
