No abstract

In classroom teaching, the teachers should adjust the teaching strategy and improve the teaching effect based on the expression and learning state of each student. This paper mainly develops a micro-expression recognition algorithm for students in classroom learning, based on convolutional neural network (CNN) and automatic face detection. Specifically, the multitask deep convolution network (DNN) was adopted to detect the landmark points of human face, and a hybrid DNN was designed to extract the optical-flow features of micro-expression. The extracted features were improved through redundancy removal and dimensionality reduction. The rationality of our algorithm was proved through a comparative experiment on real-world databases and an application in classroom teaching. The research results provide a new direction for applying deep learning in face recognition.

Purpose The purpose of this paper is to identify the studies that have had the greatest impact on entrepreneurial orientation (EO) research and to analyze the changes that have taken place in the intellectual structure of this key topic in the entrepreneurship field. Design/methodology/approach This paper adopts the methods of citation analysis, co-citation analysis, social network analysis and factor analysis to analyze 2,005 studies on the theme of EO in the 12 years from 2008 to 2019. Findings The research identified the representative literature and journals in the field of EO, presented the development process and knowledge cluster by stages in the form of intuitive network mapping and summarized the main research fields and the evolutionary trend of EO during the period 2008–2019. Research limitations/implications This study provides a more comprehensive and objective knowledge structure evolution context for EO researchers, which is conducive to the mature development of the entrepreneurship-oriented field. Practical implications It is helpful for enterprise managers to have a deeper understanding of the connotations of EO and to make more scientific entrepreneurial decisions, so as to improve their ability in enterprise innovation and entrepreneurship. Originality/value This study visualizes the evolution process of EO knowledge structure, fills the gaps of recent knowledge structure analysis literature in this field and provides theoretical support for the findings of other studies.

Content analysis is a useful tool for better understanding how different portrays of public health issues may affect news dissemination. In this research, we conducted a content analysis on health-related messages published by opinionleading news outlets. We examined generic content attributes, including number of words, sentences, images, links, and published time, as well as content valence features. Our findings show that there are no significant differences in the amount words, sentences and hyperlinks used between the highly forwarded and lowly forwarded news posts when covering a public health issue. Whereas the topic and title length as well as content valence of highly forwarded new posts is different from the lowly forwarded ones. We also discuss ways to improve popularity of health-related news.

No abstract