Beijing, 2nd July 2022 (BISTU)--- A Text Sentiment Classification Modeling Method Based on Coordinated CNN-LSTM-Attention Model, a journal jointly completed by Prof. Zhang Yangsen, Zheng Jia and Jiang Yuru, was granted the award of outstanding journals in the field of electronic information, as was shown in the notice published by Chinese Institute of Electronics on “merit-based selection of journals in electronic information”.  

The selection process was aimed at encouraging researchers to publish their high-level journals on domestic science and technology periodicals or academic conferences. The year 2022 saw 7 journals assessed as “outstanding”.  

Introduction to the journal 

Rapid development of internet also sees surge of various opinions online. Most of these expressions are very subjective.  Therefore, it has great implications to conduct researches on classification of text sentiment.  

The major challenge that text sentiment classification modeling faces is how to capture the intrinsic semantic, emotional dependence information and the key part of the emotional expression of text. To solve this problem, the journal proposes a Coordinated CNNLSTM-Attention(CCLA) model. It learns the vector representations of sentence with CCLA unit. Semantic and emotional information of sentences and their relations are adaptively encoded to vector representations of document. And softmax regression classifier is applied to identify the sentiment tendencies in the text. Compared with other methods, the CCLA model can well capture the local and long distance semantic and emotional information. Experimental results demonstrate the effectiveness of CCLA model. It shows superior performances over several state-of-the-art baseline methods. The research results would be wide applied in the field of analysis of public opinion and e-commerce customer review.  

The journal, since firstly published in 2019, has been quoted 42 times on CNKI and 39 times in ELSEVIER.  

About the authors and the team:  

Zhang Yangsen, a second-class full professor, Ph.D. supervisor, expert enjoying special allowance of State Council, outstanding member of China Computer Federation (CCF), member of natural language process and Chinese computing in CCF, member of Chinese Information Processing Society of China, deputy director of intelligent information network committee of Chinese Association for Artificial Intelligence, and member of Beijing Audit Society.  

Institute of Intelligent Information Processing, the institute headed by Prof. Zhang Yangsen, has been engaged in theoretical research and engineering application of natural language processing and network content security. Some of their rich research achievements in recent years have been successfully commercialized. The Institute so far has been granted 6 projects with sponsorship of National Natural Science Foundation, 5 projects with sponsorship of State 242 Information Security Project, and over 40 projects with sponsorship of municipal-level foundations. The total amount of sponsorship granted to the Institute has gone beyond 20 million Yuan. The Institute has published over 200 journals in top domestic periodicals such as Chinese Journal of Computers, Acta Automatica Sinica, Journal of Electronics, Acta Electronica Sinica, etc. and over 80 journals indexed in SCI, SSCI and EI, in addition to 15 treatises published by Science Press and Higher Education Press, 8 invention patents granted, and over 40 software copyrights granted. The Institute is also a winner of a first prize in “Qian Weichang Chinese Language Information Processing Award”, two second prizes of Beijing Science and Technology Award, and one second prize of Beijing Educational Achievements in Higher Education.  

The paper could be accessed: https://mp.weixin.qq.com/s/pByT5nB93v-wLaCiYwLi9w