Research trends of machine learning in traditional medicine:a big-data based tenyear bibliometric analysis

Background:With the rapid development of the world’s technology,the connection and integration between traditional medicine and modern machine learning technology are increasingly close.In this study,we aimed to analyze publications on machine learning in traditional medicine by using bibliometric methods and explore global trends in the field.Methods:Relevant research on machine learning in traditional medicine extracted from the Web of Science Core Collection database.Bibliometric analysis and visualization were performed using the Bibliometrix package in R software.Global trends,source journals,authorship,and thematic keywords analysis were performed in this study.Results:From 2012 to 2022,a total of 282 publications on machine learning in traditional medicine were identified and analyzed.The average annual growth rate of the publications was 13.35%.China had the largest contribution in this field(53.9%),followed by the United States(32.6%).IEEE Access had the largest number of published articles,with a total of 15 articles.Calvin Yu-Chian Chen,Xiao-juan Hu and Jue Wang were the main researchers in this field.Shanghai University of Traditional Chinese Medicine and University of California,San Francisco were the main research institutions.Conclusion:This study provides information on research trends in machine learning in traditional medicine to better understand research hotspots and future developments in this field.According to current global trends,the number of publications in this field will gradually increase.China currently dominated the field.Applied research of machine learning techniques may be the next hot topic in this field and deserves further attention.

Learning Outcomes Using Cooperative Learning in Communication Classes: Evaluation Using Text Analysis

Objectives: The study examined nursing students’ acquisition of good communication skills via text analysis of learning outcomes using cooperative learning. Methods: The study involved 90 first-year students enrolled in the nursing department of a Japanese university. Participants were asked to learn three learning tasks considered to heighten communicative ability through firsthand experience using the discussion-based technique of cooperative learning: 1) to engage in self-reflection, 2) to imagine something beyond your own experience, and 3) to accept something that does not fit within the scope of your own experience or thought. A questionnaire survey consisted of five items, including learning challenges 1) to 3) as well as 4) “Satisfaction with the exercises” and 5) “Students’ hopes.” These items were evaluated using text analysis. Results: A total of 79 survey questionnaires were collected (87.8% recovery rate) for analysis. “Self-reflection and self-realizations prompted by the communication exercise” was observed as a characteristic of Task 1, “becoming aware of ideas and opinions different than one’s own by listening to the opinions of others” as a characteristic of Task 2, “deepening relationships by learning about diverse ideas and values through interactions with others” as a characteristic of Task 3, and “the effects of communicating with student subjects” as a characteristic of Task 4. The responses to Task 5 were diverse;no common characteristics were found. The intervention was found to be useful for student engagement and the communication required of nurses. Conclusions: Using cooperative learning discussion in communication class was found to be effective. As nursing is an inherently interpersonal occupation, such effects include important elements.

Inheritance and Development of Three Pre-Qin Classics of Confucianism——An Application of Topic Modeling in Classical Chinese Text Analysis

The Analects, Mengzi and Xunzi are the top-three classical works of pre-Qin Confucianism, which epitomized thoughts and ideas of Confucius, Mencius and XunKuang1. There have been lots of spirited and in-depth discussions on their ideological inheritance and development from all kinds of academics. This paper tries to cast a new light on these discussions through “machine reading2”.

A survey on deep learning for textual emotion analysis in social networks

Textual Emotion Analysis(TEA)aims to extract and analyze user emotional states in texts.Various Deep Learning(DL)methods have developed rapidly,and they have proven to be successful in many fields such as audio,image,and natural language processing.This trend has drawn increasing researchers away from traditional machine learning to DL for their scientific research.In this paper,we provide an overview of TEA based on DL methods.After introducing a background for emotion analysis that includes defining emotion,emotion classification methods,and application domains of emotion analysis,we summarize DL technology,and the word/sentence representation learning method.We then categorize existing TEA methods based on text structures and linguistic types:text-oriented monolingual methods,text conversations-oriented monolingual methods,text-oriented cross-linguistic methods,and emoji-oriented cross-linguistic methods.We close by discussing emotion analysis challenges and future research trends.We hope that our survey will assist readers in understanding the relationship between TEA and DL methods while also improving TEA development.

Climate bonds toward achieving net zero emissions and carbon neutrality:Evidence from machine learning technique

The Conference of the Parties(COP26 and 27)placed significant emphasis on climate financing policies with the objective of achieving net zero emissions and carbon neutrality.However,studies on the implementation of this policy proposition are limited.To address this gap in the literature,this study employs machine learning techniques,specifically natural language processing(NLP),to examine 77 climate bond(CB)policies from 32 countries within the context of climate financing.The findings indicate that“sustainability”and“carbon emissions control”are the most outlined policy objectives in these CB policies.Additionally,the study highlights that most CB funds are invested toward energy projects(i.e.,renewable,clean,and efficient initiatives).However,there has been a notable shift in the allocation of CB funds from climate-friendly energy projects to the construction sector between 2015 and 2019.This shift raises concerns about the potential redirection of funds from climate-focused investments to the real estate industry,potentially leading to the greenwashing of climate funds.Furthermore,policy sentiment analysis revealed that a minority of policies hold skeptical views on climate change,which may negatively influence climate actions.Thus,the findings highlight that the effective implementation of CB policies depends on policy goals,objectives,and sentiments.Finally,this study contributes to the literature by employing NLP techniques to understand policy sentiments in climate financing.

Text Detection in Natural Scene Images Using Morphological Component Analysis and Laplacian Dictionary

Text in natural scene images usually carries abundant semantic information. However, due to variations of text and complexity of background, detecting text in scene images becomes a critical and challenging task. In this paper, we present a novel method to detect text from scene images. Firstly, we decompose scene images into background and text components using morphological component analysis(MCA), which will reduce the adverse effects of complex backgrounds on the detection results.In order to improve the performance of image decomposition,two discriminative dictionaries of background and text are learned from the training samples. Moreover, Laplacian sparse regularization is introduced into our proposed dictionary learning method which improves discrimination of dictionary. Based on the text dictionary and the sparse-representation coefficients of text, we can construct the text component. After that, the text in the query image can be detected by applying certain heuristic rules. The results of experiments show the effectiveness of the proposed method.

A quantum‐like approach for text generation from knowledge graphs

Recent text generation methods frequently learn node representations from graph‐based data via global or local aggregation,such as knowledge graphs.Since all nodes are connected directly,node global representation encoding enables direct communication between two distant nodes while disregarding graph topology.Node local representation encoding,which captures the graph structure,considers the connections between nearby nodes but misses out onlong‐range relations.A quantum‐like approach to learning bettercontextualised node embeddings is proposed using a fusion model that combines both encoding strategies.Our methods significantly improve on two graph‐to‐text datasets compared to state‐of‐the‐art models in various experiments.

文本分类中Prompt Learning方法研究综述

文本分类是自然语言处理中的一项基础任务,在情感分析、新闻分类等领域具有重要应用。相较于传统的机器学习和深度学习模型,提示学习可以在数据不足的情况下通过构建提示来进行文本分类。近年来,GPT-3的出现推动了提示学习方法的发展,并且在文本分类领域取得了显著的进展。对以往的文本分类方法进行简要梳理,分析其存在的问题与不足;阐述了提示学习的发展进程,以及构建提示模板的方法,并对用于文本分类的提示学习方法研究及成果进行了介绍和总结。最后,对提示学习在文本分类领域的发展趋势和有待进一步研究的难点进行了总结和展望。

一种基于日志信息和CNN-text的软件系统异常检测方法

当前,数据挖掘作为一种高时效性、高真实性的分析方法,正在社会中扮演着越发重要的角色,其在大型数据中快速挖掘模式,发现规律的能力正逐步取代人工的作用.而在当前各个计算机领域大行其道的大型分布式系统(如Hadoop、Spark等)的日志中,每天都产生着数以百万计的系统日志,这些日志的数据量之庞杂、关系之混乱,已大大影响了程序员对系统的人工监控效率,同时也提高了新程序员的培养成本.为解决以上问题,数据挖掘及系统分析两个领域相结合是一种必然的趋势,也因此,机器学习模型也越来越多地被业界提及用于做系统日志分析.然而大多数情况下,系统日志中,报告系统运行状态为“严重”的日志占少数,而这些少数信息才是程序员最需要关注的,然而大多数用于系统日志分析的机器学习模型都假设训练集的数据是均衡数据,因此这些模型在做系统日志预警时容易过度偏向大样本数据,以至于效果不够理想.本文将从深度学习角度出发,探究深度学习中的CNN-text(CT)在系统日志分析方面的应用能力,通过将CT与主流的系统日志分析机器学习模型SVM、决策树对比,探究CT相对于这些算法的优越性;将CT与CNN-RNN-text(CRT)进行对比,分析CT对特征的处理方式,证实CT在深度学习模型中处理系统日志类文本的优越性;最后将所有模型应用至两套不同的日志类文本数据中进行对比,证明CT的普适性.在CT同日志分析的主流机器学习模型对比的实验中,CT相较于最优模型的结果召回率提升了近15%;在CT同CRT模型对比的实验中,CT相较于更为先进的CRT,模型准确率高出约20%,召回率高出约80%、查准率高出约60%;在CT的普适性实验中,将各类模型融入到本文的实验数据集logstash和公开数据集WC85_1中,在准确率同其他表现较优的模型同为100%的情况下,CT的召回率高出其余召回率最高的模型(DT-Bi)近14%.从中可看出,相较于主流系统日志分析机器学习模型,如支持向量机、决策树、朴素贝叶斯等,CNN-text的局部特征提取能力及非线性拟合能力都有更为优异的表现;同时相较于同为深度学习CNN簇的CNN-RNN-text将大量权重投入到系统日志的序列特征中的特点,CNN-text则报以较少的关注,反而在序列不规则的系统日志中展现出比CNN-RNN-text更优秀的表现.最终证明了CNN-text是本文所提到的方法中最适合进行软件系统异常检测的方法.

Deep Learning and Network Analysis:Classifying and Visualizing Geologic Hazard Reports

If progress is to be made toward improving geohazard management and emergency decision-making,then lessons need to be learned from past geohazard information.A geologic hazard report provides a useful and reliable source of information about the occurrence of an event,along with detailed information about the condition or factors of the geohazard.Analyzing such reports,however,can be a challenging process because these texts are often presented in unstructured long text formats,and contain rich specialized and detailed information.Automatically text classification is commonly used to mine disaster text data in open domains(e.g.,news and microblogs).But it has limitations to performing contextual long-distance dependencies and is insensitive to discourse order.These deficiencies are most obviously exposed in long text fields.Therefore,this paper uses the bidirectional encoder representations from Transformers(BERT),to model long text.Then,utilizing a softmax layer to automatically extract text features and classify geohazards without manual features.The latent Dirichlet allocation(LDA)model is used to examine the interdependencies that exist between causal variables to visualize geohazards.The proposed method is useful in enabling the machine-assisted interpretation of text-based geohazards.Moreover,it can help users visualize causes,processes,and other geohazards and assist decision-makers in emergency responses.

Comprehensive review of text‑mining applications in finance

Text-mining technologies have substantially affected financial industries.As the data in every sector of finance have grown immensely,text mining has emerged as an important field of research in the domain of finance.Therefore,reviewing the recent literature on text-mining applications in finance can be useful for identifying areas for further research.This paper focuses on the text-mining literature related to financial forecasting,banking,and corporate finance.It also analyses the existing literature on text mining in financial applications and provides a summary of some recent studies.Finally,the paper briefly discusses various text-mining methods being applied in the financial domain,the challenges faced in these applications,and the future scope of text mining in finance.

一种基于Context Graph主题爬虫系统的算法实现

对搜索引擎的原理结构进行深度剖析,经可行性认定后,将机器学习算法与现有的技术手段进一步融合提升,以Python为开发平台,以Context Graph为开发主题,构建并设计出可实现的目标爬虫系统.通过实际运用检测系统的实用性能,选择国内具有较大规模的汽车网站为研究对象,设置“汽车”为关键词对全部内容展开不同类别的爬取,进而分析所得结果,根据查全率、查准率和F1值综合评价系统的性能.与原有系统相比,升级后算法的模型准确性更好,在一定程度上提高爬取工作的效率.

A Lightweight Sentiment Analysis Method

The emergence of big data leads to an increasing demand for data processing methods.As the most influential media for Chinese domestic movie ratings,Douban contains a huge amount of data and one can understand users'perspectives towards these movies by analyzing these data.In this article,we study movie's critics from the Douban website,perform sentiment analysis on the data obtained by crawling,and visualize the results with a word cloud.We propose a lightweight sentiment analysis method which is free from heavy training and visualize the results in a more conceivable way.

基于网络文本分析的博物馆观众情感体验探究——以安徽博物院新馆为例

以安徽博物院新馆作为研究对象,采集网络评论,运用网络文本分析方法,使用ROST CM6软件进行分析,探究安博院新馆观众对博物馆的情感体验。分析结果显示绝大部分观众对安博院新馆持积极情绪,总体体验良好。但从展馆展品、管理服务、安徽地域文化认同维度细化分析,安博院新馆仍存在提升空间。安博院新馆可以通过丰富馆藏文物展览资源、丰富馆内工作人员的相关培训和基础设施服务、丰富文创产品,扩大文化传播空间等方式,进一步提升观众的情感体验,增强安徽文化的吸引力。

融合MD&A多维度语义的企业碳减排信用风险预警研究

本文以2011~2022年制造型企业为例,将创新性、前瞻性、风险性等10种MD&A语义指标引入基于机器学习算法构建的碳减排信用风险预警模型中,探究引入前后模型预测效果的变化,并使用SHAP可解释法揭示预警模型决策逻辑过程。研究发现:(1)MD&A语义指标可显著提升碳减排信用风险预警模型的预测效果,如P_(i)、CV_(i)评估指标的提升幅度、降低幅度分别在1%~11%、0.0029~0.1944。而相较于语义指标,碳减排信用指标对模型预测效果提升更为明显;(2)总体碳减排信用风险预警效果上,XGBoost模型最佳,其次是RF和SVM模型,LR模型最差;(3)净语调1、创新性、风险性是影响碳减排信用风险的关键语义指标。当净语调1、创新性指标增大时,模型预测为正常企业的概率增加;当风险性指标增大时,模型预测为违约企业的概率增加。

表征与非表征视角下饮食地域刻板印象的验证与测量

饮食在地域之间不断交融,跨越国界、民族及社区,既成为一种表征的文化意义结构,也成为非表征的日常参与和实践,在表征与非表征视角下,饮食地域刻板印象的存在与具体内容值得探讨。为了厘清这一问题,本研究采用混合研究法对饮食地域刻板印象进行验证和测量。子研究1使用了问卷调查法检验外显层面的饮食地域刻板印象,子研究2采用语义启动的实验范式检验内隐层面的饮食地域刻板印象。研究发现,被试在内隐和外显层面均持有饮食地域刻板印象,主要包括主食偏好、口味偏好、份量偏好和具体菜品4个维度。本研究验证了饮食地域刻板印象具有外显和内隐、经验与情景并存的特征,这扩展了表征与非表征理论相结合的饮食社会文化地理知识。

基于网络数据的洛阳市王城公园景观形象感知研究

以互联网络游客评论为数据来源,通过网络文本分析法,从词频分析、社会网络和语义分析、情感分析3个方面对洛阳市王城公园景观形象感知进行分析,以了解王城公园旅游地形象。结果表明,王城公园景观形象由空间场地、植物景观、景观设施和人文景观组成;游客感知由游客关注点、游客行为特征以及游客评价组成;游客对王城公园的整体感知印象较好,情感倾向以正面为主,负面情绪多集中在服务管理、景观设施和景观维护等方面。最后,基于为游客提供更优质的游憩体验,提出改善设施服务、提升互动体验、丰富景观内涵、加强高峰期与数字化的管理等优化建议。

战略认知差异会影响企业技术创新吗?——基于文本主题分析的实证研究

在知识经济时代,知识对创新的边际贡献超过传统物质性生产要素,企业技术创新优势更多源于管理者认知的转变,而不再由异质性的资源所决定。本文探讨了行业场景中管理者的战略认知相较于行业共享信念之间的差异对技术创新的影响,同时考虑了探索式学习与知识组合多样性在其中所发挥的路径传导作用。研究结果显示:管理者的战略认知差异能够显著促进以专利申请量为表征的技术创新数量,提高以专利外部引用为表征的技术创新质量。进一步研究发现,探索式学习和知识组合多样性在战略认知差异与技术创新的关系中发挥了部分中介作用。异质性分析发现,受到来自家族权威和行政制度的干预,管理者的战略认知差异在非家族企业与非国有企业样本中表现出更为显著的技术创新效果。研究结论从战略认知差异视角拓展了技术创新的前因研究,同时为理解中国企业的创新决策逻辑、探究创新人才培养路径提供了理论参考。

区块链技术对企业全要素生产率的影响研究--基于信任构建和降本增效的视角

为了研究区块链技术对企业的生产效率的作用,文章以2019—2021年A股上市公司中非ST制造业企业为样本,运用文本分析及机器学习word2vec方法基于上市公司年报对企业区块链应用程度进行度量,实证检验了其与制造业企业全要素生产率之间的关系。研究发现上市公司区块链技术应用程度越高,其全要素生产率越高。机制研究发现,信任构建和降本增效,是区块链应用赋能全要素生产率提高的主要路径。进一步研究发现,企业子行业类型以及企业代理成本,会影响区块链应用对生产率的促进作用。