Cigarette online reviews can truly reflect the word-of-mouth of cigarettes, and help cigarette industrial and commercial enterprises to understand consumers’ cigarette use experience and cigarette word-of-mouth dynamics. In order to extract effective consumer experience information from massive online reviews of cigarette consumption, this paper studies the text sentiment analysis of cigarette online reviews. This paper presents a feature fusion model of convolutional neural network and BiLSTM. Experimental results show that the proposed feature fusion model effectively improves the accuracy of text classification. The model can provide new insight for the evaluation of cigarette management, dynamically monitor the change of consumers’ emotion, and grasp the trend of consumers’ emotion in the tobacco market environment in time.
This article adopts the Internet of Things technology, network communication technology, edge computing and other technologies to establish a set of data acquisition system based on the industrial Internet through the data collection, storage and reporting of the automatic control systems of the three workshops of silk making, wrapping, and power and other related information systems.
In the evaluation of cigarette quality, it usually depends on the sense organs of evaluation experts. But due to the influence of many subjective and objective factors, the accuracy of evaluation results is often difficult to guarantee. Therefore, this paper proposes a method of cigarette quality evaluation based on SVM and BP neural network. The experimental results show that the method can establish a nonlinear mapping relationship between the measured values of cigarette chemical components and the evaluation values of expert quality, and reflect the preference information and reasoning mechanism of evaluation experts. So the model is an objective and reliable method for evaluating the internal quality of tobacco after knowing the chemical composition test data of tobacco.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.