The purpose of this study is to deeply explore the application of information mining technology in online entrepreneurship training courses, and to improve students’ learning effects and entrepreneurship success rate through systematic analysis and optimization of key data in the teaching process. With the development of online education, how to effectively use big data technology to meet personalized learning needs has become an important issue. This study takes several online entrepreneurship training courses as the research object, and uses information mining technology to extract and analyze students’ behavioral data during course participation, including data on study time, interaction frequency, assessment results, etc. Through machine learning algorithms and association rule mining, the research revealed the main factors that affect students’ learning effects and entrepreneurial success, and designed targeted teaching strategies, such as dynamically adjusting learning content, providing personalized feedback, optimizing learning paths, etc. Experimental results show that online courses using information mining technology significantly improve students’ knowledge mastery and entrepreneurial success rate, especially in terms of personalized learning experience and teaching efficiency. In addition, this study also explores the application prospects of information mining technology in future online education. It is believed that through the combination with artificial intelligence (AI) technology, the intelligence and adaptability of online courses can be further enhanced to meet more diversified learning needs.

With a large number of images provided by TV and other media flowing into the Internet and the reduction of technical barriers, images have not only become a daily practice for people to record their lives and communicate their behaviors but also become an important means for the public to express their discourse in the cyberspace. Therefore, it is of great significance to analyze the image propagation algorithm using artificial intelligence. This paper mainly studies the algorithm analysis and governance of local media image propagation in the era of artificial intelligence. In this paper, the media is the research object, with its daily dissemination of video works as the research text, in order to discover the ethical problems in its dissemination activities as the purpose, integrating disciplinary knowledge to analyze the ethical problems in this art form, and trying to find out the fundamental measures to solve the problem. The advantages and disadvantages of the video recommendation intelligent algorithm based on the BP neural network are analyzed. By comparing different algorithms, it can be seen that the video recommendation accuracy of the BP neural network algorithm based on swarm optimization (FEBP) is 15.8% higher than that of the traditional BP neural network algorithm. These intelligent algorithms are added into the image transmission system, in order to achieve the goal of improving the image transmission and recommendation effect.

With a large number of images provided by TV and other media flowing into the Internet and the reduction of technical barriers, images have not only become a daily practice for people to record their lives and communicate their behaviors but also become an important means for the public to express their discourse in the cyberspace. Therefore, it is of great significance to analyze the image propagation algorithm using artificial intelligence. This paper mainly studies the algorithm analysis and governance of local media image propagation in the era of artificial intelligence. In this paper, the media is the research object, with its daily dissemination of video works as the research text, in order to discover the ethical problems in its dissemination activities as the purpose, integrating disciplinary knowledge to analyze the ethical problems in this art form, and trying to find out the fundamental measures to solve the problem. The advantages and disadvantages of the video recommendation intelligent algorithm based on the BP neural network are analyzed. By comparing different algorithms, it can be seen that the video recommendation accuracy of the BP neural network algorithm based on swarm optimization (FEBP) is 15.8% higher than that of the traditional BP neural network algorithm. These intelligent algorithms are added into the image transmission system, in order to achieve the goal of improving the image transmission and recommendation effect.

Weibo platform is an indispensable transmission channel in education policy release and dissemination. The events and sentiments contained in education policies microblogs include the public sentiment and support the general management and guidance scientifically and efficiently. This study constructs a dataset based on the “Double Reduction Policy” relevant microblogs and comments. The policy events are extracted by Latent Dirichlet Allocation (LDA) model and Language Technology Platform (LTP). Based on the emotion dictionary, an attention-based BiLSTM model is constructed to classify the public sentiments. The experimental results reveal four themes: “industry impact,” “institutional supervision,” “public feedback,” and “policy implementation.” The distribution conforms to the development trend of online public sentiments.

近年来,大数据、人工智能等新兴技术的飞速发展,推动着计算教育学逐步走向成熟,并受到研究者的广泛关注.为此,从计算教育学发展脉络展开分析,梳理出计算教育学领域的主要支撑技术与应用场景.基于梳理结果,对CNKI数据库2001年到2019年研究文献进行分析,构建了计算教育学领域学术文本(摘要)语料库.应用"学术文本(摘要)主题分析框架"对语料库进行数据挖掘,研究发现了计算教育学领域语言模型与四个重要聚类,即"个性化学习""智慧课堂""智慧校园""创客教育".研究认为,加快形成计算教育学特有的研究范式,合力构建计算教育学技术生态系统,加强计算教育学学科人才培养尤其是研究人员的培养,将是未来计算教育学研究与发展的主要问题和重要抓手.

Citespace, a visualization-based analysis tool, has been used to analyze the literature data by visualizing the patterns and potential trends of a field. Previous studies show that when used for analyzing the literature in Chinese, Citespace could only conduct very basic analysis, different from its use in analyzing the literature data in English. To address this limitation, this study presents an approach to improving the use of Citespace for effective analysis of literature data in Chinese. The approach employs data-processing and data-analysis scripts in data collection, knowledge map generation, and interpretation steps to improve the accuracy and comprehensiveness of analysis of literature data in Chinese. An empirical evaluation has been conducted to demonstrate the effectiveness of the approach.

在科学知识图谱领域,代表性软件CiteSpace对于期刊数据的分析具有重要价值,但是CiteSpace软件对中文期刊数据的分析仅能完成几类基础聚类和数据分析,如若希望做深入解读就需要对已有中文期刊CiteSpace研究范式进行完善和创新.本研究通过深入分析CiteSpace两篇代表性文献,提取了标准研究范式,从CSSCI收录的文献中梳理出通用的CiteSpace中文期刊研究范式,并将两种范式进行对比,探究中文期刊研究范式需要优化之处.基于此,本研究通过使用自然语言处理技术(简称"NLP")主题挖掘的典型模型Latent Dirichlet Allocation(简称"LDA")处理论文摘要数据,通过这种技术完善文献检索策略和文献数据处理方法,提出的"优化范式"丰富了中文期刊CiteSpace研究来源数据,增强了中文期刊CiteSpace研究内容的深度和系统性,并通过对国内人工智能在教育领域应用的研究进一步验证了该"优化范式"的可操作性,揭示出国内人工智能在教育领域应用研究的前沿主要聚焦于智慧学习环境的构建和相关技术支持.在与国内CSSCI同类型文献的对比中,"优化范式"在数据收集、数据分析、数据解读三个阶段的表现均优于传统中文期刊CiteSpace研究范式.

Objective: Based on the topics of abstracts, times cited, and co-citation networks, this paper explores the knowledge system of dance teaching in China so as to provide a reference for future research based on bibliometrics. Method: According to the CSSCI database, a statistical analysis of Chinese research in dance teaching from 1998 to 2020 is carried out to discover implicit topics. In view of research hotspots and frontiers, this paper conducts a centrality and visualization analysis and a filtering of salient terms of research hotspots in dance teaching using CiteSpace, a knowledge graph visualization software. Also, the Latent Dirichlet Allocation model is used to extract and visualize the topics from the filtered salient terms of the abstracts. Results/Conclusion: We found that the research hotspots in dance teaching in China can be divided into 16 clusters, namely “Sports Dance”, “Dance Art”, “Classical Chinese Dance”, “Yunnan Dance”, “Dance”, “Folk Dance”, “Ethnic Dance”. “Dance teaching”, “Quality Education”, “College Students”, “Ethnic Minorities”. “Latin Dance”, “Traditional Athletic Maintenance”, “Chorus”, “Fitness Value”, and “Physical Fitness”. The research frontiers in dance teaching lie in the teaching, discovery, protection, restoration, and discipline construction of folk dance and intangible cultural heritage dance genres.

音乐教育学贯穿音乐教育的全过程,了解把握音乐教育学的研究热点对建设我国现代音乐教育有重要的现实意义.本文采用知识图谱结合LDA (Latent Dirchlet Allocation)模型,对2000年以来国内音乐教育领域研究进行统计和梳理,挖掘其中隐含主题.从研究热点、研究前沿和知识背景三个方面切入,对音乐教育研究领域研究热点的关键词进行可视化和中心度分析,对研究前沿和知识背景进行词频分析,发现新世纪以来国内研究热点聚焦于音乐教育领域的多个方面;依据音乐教育领域前沿分析推测未来音乐教育发展研究趋势,为国内音乐教育学的研究热点提供新的参考.