Emotional analysis System of book review based on Neural network

2019 International Conference on Advanced Electronic Materials, Computers and Materials Engineering

无线电电子学;计算机科学;材料科学

Sun, Yanxiong^1 ; Li, Yeli^1 ; Zeng, Qingtao^1 ; Bian, Yuning^1

Beijing Institute of Graphic Communication, China^1

关键词: Accuracy of classifications;    Book publishing;    Effective analysis;    Emotional analysis;    Emotional words;    Explosive growth;    Financial resources;    Information explosion;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/563/4/042012/pdf
DOI  :  10.1088/1757-899X/563/4/042012

来源: IOP

【 摘 要 】

Contemporary society, is an era of the Information explosion. The explosive growth of book publishing makes readers choose a good book, and publishers choose to publish a book with a market, which has become a very important topic. Aiming at the non-effective analysis of the current book publishers to obtain the real feelings of the users on the book, this paper puts forward that the neural network as the main algorithm is enough to classify the user's comments emotionally. In the collection of data, through the award-winning books and the two-star score under the book review, take different weights of the calculation, the emotional words of the eigenvectors to plump. And after the book evaluation is pre-processed, the user's credibility parameters are added to the input word vector. As a result, the accuracy of classification and judgment of the whole system is improved, the consumption of human, material and financial resources is reduced, and the resource can be invested in how to improve the level of publications, which will add to the cause of book publishing in China.