Analyzing topics in social media for improving digital twinning based product development

Digital twinning enables manufacturers to create digital representations of physical entities,thus implementing virtual simulations for product development.Previous efforts of digital twinning neglect the decisive consumer feedback in product development stages,failing to cover the gap between physical and digital spaces.This work mines real-world consumer feedbacks through social media topics,which is significant to product development.We specifically analyze the prevalent time of a product topic,giving an insight into both consumer attention and the widely-discussed time of a product.The primary body of current studies regards the prevalent time prediction as an accompanying task or assumes the existence of a preset distribution.Therefore,these proposed solutions are either biased in focused objectives and underlying patterns or weak in the capability of generalization towards diverse topics.To this end,this work combines deep learning and survival analysis to predict the prevalent time of topics.We propose a specialized deep survival model which consists of two modules.The first module enriches input covariates by incorporating latent features of the time-varying text,and the second module fully captures the temporal pattern of a rumor by a recurrent network structure.Moreover,a specific loss function different from regular survival models is proposed to achieve a more reasonable prediction.Extensive experiments on real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods.

基于BERTopic模型的国外信息资源管理研究进展分析

[目的/意义]文章从已有研究成果中提取主题,梳理主要研究方向,展示主题热度变化趋势,为了解和评估国外信息资源管理(IRM)研究发展现状与趋势提供参考。[方法/过程]采用新兴BERTopic模型对2013—2022年期间WoS数据库中IRM相关文献进行主题提取与识别,结合相关主题词及主题距离划分研究方向,并利用动态主题模型揭示国外IRM领域的演变过程。[结果/结论]国外IRM近10年的研究可分为59个主题,可归纳为信息技术及应用、企业信息管理、图书馆管理与服务、健康信息管理、信息用户与服务、IRM基本理论与方法、文献计量与评价7个方向。大多数主题的研究热度变化偏向稳定的趋势,数字化建设、开放数据等部分主题热度逐渐上涨,而外包、知识管理等少数主题热度退却。

Mining Topical Influencers Based on the Multi-Relational Network in Micro-Blogging Sites

In micro-blogging contexts such as Twitter,the number of content producers can easily reach tens of thousands,and many users can participate in discussion of any given topic.While many users can introduce diversity,as not all users are equally influential,it makes it challenging to identify the true influencers,who are generally rated as being interesting and authoritative on a given topic.In this study,the influence of users is measured by performing random walks of the multi-relational data in micro-blogging:retweet,reply,reintroduce,and read.Due to the uncertainty of the reintroduce and read operations,a new method is proposed to determine the transition probabilities of uncertain relational networks.Moreover,we propose a method for performing the combined random walks for the multi-relational influence network,considering both the transition probabilities for intra-and inter-networking.Experiments were conducted on a real Twitter dataset containing about 260 000 users and 2.7million tweets,and the results show that our method is more effective than TwitterRank and other methods used to discover influencers.

Identification and Prediction of Interdisciplinary Research Topics: A Study Based on the Concept Lattice Theory

Purpose: Formal concept analysis(FCA) and concept lattice theory(CLT) are introduced for constructing a network of IDR topics and for evaluating their effectiveness for knowledge structure exploration.Design/methodology/approach: We introduced the theory and applications of FCA and CLT, and then proposed a method for interdisciplinary knowledge discovery based on CLT. As an example of empirical analysis, interdisciplinary research(IDR) topics in Information & Library Science(LIS) and Medical Informatics, and in LIS and Geography-Physical, were utilized as empirical fields. Subsequently, we carried out a comparative analysis with two other IDR topic recognition methods.Findings: The CLT approach is suitable for IDR topic identification and predictions.Research limitations: IDR topic recognition based on the CLT is not sensitive to the interdisciplinarity of topic terms, since the data can only reflect whether there is a relationship between the discipline and the topic terms. Moreover, the CLT cannot clearly represent a large amounts of concepts.Practical implications: A deeper understanding of the IDR topics was obtained as the structural and hierarchical relationships between them were identified, which can help to get more precise identification and prediction to IDR topics.Originality/value: IDR topics identification based on CLT have performed well and this theory has several advantages for identifying and predicting IDR topics. First, in a concept lattice, there is a partial order relation between interconnected nodes, and consequently, a complete concept lattice can present hierarchical properties. Second, clustering analysis of IDR topics based on concept lattices can yield clusters that highlight the essential knowledge features and help display the semantic relationship between different IDR topics. Furthermore, the Hasse diagram automatically displays all the IDR topics associated with the different disciplines, thus forming clusters of specific concepts and visually retaining and presenting the associations of IDR topics through multiple inheritance relationships between the concepts.

Detecting Dynamics of Hot Topics with Alluvial Diagrams:A Timeline Visualization

Purpose： In this paper, we combined the method of co-word analysis and alluvial diagram to detect hot topics and illustrate their dynamics. Design/methodology/approach： Articles in the field of scientometrics were chosen as research cases in this study. A time-sliced co-word network was generated and then clustered. Afterwards, we generated an alluvial diagram to show dynamic changes of hot topics, including their merges and splits over time. Findings： After analyzing the dynamic changes in the field of scientometrics from 2011 to 2015, we found that two clusters being merged did not mean that the old topics had disappeared and a totally new one had emerged. The topics were possibly still active the following year, but the newer topics had drawn more attention. The changes of hot topics reflected the shift in researchers＇ interests. subdivided and re-merged. For example, several topics as research progressed. Research topics in scientometrics were constantly a cluster involving ＂industry＂ was divided into Research limitations： When examining longer time periods, we encounter the problem of dealing with bigger data sets. Analyzing data year by year would be tedious, but if we combine, e.g. two years into one time slice, important details would be missed. Practical implications： This method can be applied to any research field to illustrate the dynamics of hot topics. It can indicate the promising directions for researchers and provide guidance to decision makers. Originality/value： The use of alluvial diagrams is a distinctive and meaningful approach to detecting hot topics and especially to illustrating their dynamics.

BURST-LDA: A NEW TOPIC MODEL FOR DETECTING BURSTY TOPICS FROM STREAM TEXT

Topic models such as Latent Dirichlet Allocation(LDA) have been successfully applied to many text mining tasks for extracting topics embedded in corpora. However, existing topic models generally cannot discover bursty topics that experience a sudden increase during a period of time. In this paper, we propose a new topic model named Burst-LDA, which simultaneously discovers topics and reveals their burstiness through explicitly modeling each topic's burst states with a first order Markov chain and using the chain to generate the topic proportion of documents in a Logistic Normal fashion. A Gibbs sampling algorithm is developed for the posterior inference of the proposed model. Experimental results on a news data set show our model can efficiently discover bursty topics, outperforming the state-of-the-art method.

A Metric Approach to Hot Topics in Biomedicine via Keyword Co-occurrence

Purpose:To reveal the research hotpots and relationship among three research hot topics in b iomedicine,namely CRISPR,iPS(induced Pluripotent Stem)cell and Synthetic biology.Design/methodology/approach:We set up their keyword co-occurrence networks with using three indicators and information visualization for metric analysis.Findings:The results reveal the main research hotspots in the three topics are different,but the overlapping keywords in the three topics indicate that they are mutually integrated and interacted each other.Research limitations:All analyses use keywords,without any other forms.Practical implications:We try to find the information distribution and structure of these three hot topics for revealing their research status and interactions,and for promoting biomedical developments.Originality/value:We chose the core keywords in three research hot topics in biomedicine by using h-index.

Self-Adaptive Topic Model： A Solution to the Problem of ＂Rich Topics Get Richer＂

The problem of "rich topics get richer"(RTGR) is popular to the topic models,which will bring the wrong topic distribution if the distributing process has not been intervened.In standard LDA(Latent Dirichlet Allocation) model,each word in all the documents has the same statistical ability.In fact,the words have different impact towards different topics.Under the guidance of this thought,we extend ILDA(Infinite LDA) by considering the bias role of words to divide the topics.We propose a self-adaptive topic model to overcome the RTGR problem specifically.The model proposed in this paper is adapted to three questions:(1) the topic number is changeable with the collection of the documents,which is suitable for the dynamic data;(2) the words have discriminating attributes to topic distribution;(3) a selfadaptive method is used to realize the automatic re-sampling.To verify our model,we design a topic evolution analysis system which can realize the following functions:the topic classification in each cycle,the topic correlation in the adjacent cycles and the strength calculation of the sub topics in the order.The experiment both on NIPS corpus and our self-built news collections showed that the system could meet the given demand,the result was feasible.

Mapping the evolution of research topics using ATM and SNA

Purpose:This paper introduces an analysis framework for tracking the evolution of research topics at the selected topics level,covering a research topic’s evolution trend,evolution path and its content changes over time.Design/methodology/approach:After the topics were recovered by the author-topic model,we first built the keyword-topic co-occurrence network to track the dynamics of topic trends.Then a single-mode network was constructed with each node representing a topic and edge indicating the relationship between topics.It was used to illustrate the evolution path and content changes of research topics.A case study was conducted on the digital library research in China to verify the effectiveness of the analysis framework.Findings:The experimental results show that this analysis framework can be used to track evolution of research topics at a micro level and using social network analysis method can help understand research topics’evolution paths and content changes with the passage of time.Research limitations:Using the analysis framework will produce limited results when examining unstructured data such as social media data.In addition,the effectiveness of the framework introduced in this paper needs to be verified with more research topics in information science and in more scientific fields.Practical implications:This analysis framework can help scholars and researchers map research topics’evolution process and gain insights into how a field’s topics have evolved over time.Originality/value:Tbe analysis framework used in this study can help reveal more micro evolution details.The index to measure topic association strength defined in this paper reflects both similarity and dissimilarity between topics,which belps better understand research topics’evolution paths and content changes.

Journal of Sport and Health Science Published Special Topics(2017—2019)

Promoting physical activity and health through active video games Volume 6,Issue 1,2017Guest editor:Zan Gao Hamstring muscle strain injury Volume 6,Issues 2-3,2017Guest editors:Bing Yu,Li Li Physical activity,fitness,and obesity in Chinese school-aged children and adolescents:An update Volume 6,Issue 4,2017Guest editors:Fuzhong Li.

InCites中Citation Topics功能应用于科技期刊选题策划的实证研究——以热带医学研究领域为例

以热带医学研究领域为例,探索InCites数据库中的Citation Topics功能在选题策划中的应用。选取Web of Science数据库中热带医学领域近5年SCIE收录的论文,利用Citation Topics,对个别发文量多或被引频次高的研究方向、区域、研究人员、机构进行微观主题举例分析。疟疾微观主题下表现最活跃的区域为USA,机构为University of London,研究人员为Drakeley,Chris,出版物为Malaria Journal,United States Department of Health&Human Services为疟疾微观主题提供的基金资助最多;血吸虫病、疟疾、登革热、包虫囊肿和冠状病毒是中国热带医学领域的研究重点,冠状病毒、血吸虫病、隐孢子虫、登革热和疟疾微观主题的论文影响力相对较高;研究人员Zhou,Xiao-Nong的重点研究方向为血吸虫病、疟疾和包虫囊肿,疟疾、登革热、轮状病毒、犬弓首线虫和莱姆病研究主题的论文质量和关注度高;University of London热带医学领域的研究重点为疟疾、血吸虫病和登革热。InCites中Citation Topics功能可以实现对研究主题、人员、机构、国家/地区等模块进行更精细的分析,有助于科技期刊编辑更高效地制定选题方案。

Identification of Topics from Scientific Papers through Topic Modeling

Topic modeling is a probabilistic model that identifies topics covered in text(s). In this paper, topics were loaded from two implementations of topic modeling, namely, Latent Semantic Indexing (LSI) and Latent Dirichlet Allocation (LDA). This analysis was performed in a corpus of 1000 academic papers written in English, obtained from PLOS ONE website, in the areas of Biology, Medicine, Physics and Social Sciences. The objective is to verify if the four academic fields were represented in the four topics obtained by topic modeling. The four topics obtained from Latent Semantic Indexing (LSI) and Latent Dirichlet Allocation (LDA) did not represent the four academic fields.

Research Report on MTCSOL Dissertation Topics in the Last Decade

Dissertation is one of the most important indicators to evaluate the training quality of postgraduate students.As the first step of writing dissertations,topic selection directly influences the dissertation quality.By utilizing the intelligent retrieval system of the National Science and Technology Library(NSTL),we have selected MTCSOL(Master of Teaching Chinese to Speakers of Other Languages)dissertation topics during the last 10 years,divided them into four stages and statistically analyzed the general tendency and crucial problems in these dissertations.MTCSOL dissertations have increased greatly in quantity and become more diversified and multidisciplinary.However,they are still too concentrated on similar topics with narrow scopes;and researches lack of creativity,pioneering spirits and practicality.It concludes that MTCSOL students should expand their research scopes and improve the quality of their dissertations with the historic mission of international Chinese language teaching to support the Belt and Road Initiative and build a harmonious community with shared future for humanity in the new era always in their minds.

ICS-SVM:A user retweet prediction method for hot topics based on improved SVM

In social networks,many complex factors affect the prediction of user forwarding behavior.This paper proposes an improved SVM prediction method for user forwarding behavior of hot topics to improve prediction accuracy.Firstly,we consider that the improved Cuckoo Search algorithm can select the optimal penalty parameters and kernel function parameters to optimize the SVM and thus predict the user's forwarding behavior.Secondly,this paper considers the factors that affect the user forwarding behavior comprehensively from the user's own factors and external factors.Finally,based on the characteristics of the user's forwarding behavior changing over time,the time-slicing method is used to predict the trend of hot topics.Experiments show that the method can accurately predict the user's forwarding behavior and can sense the trend of hot topics.

Research on the Chinese Path to Modernization in History,Key Topics,and Outlook:A Cite Space-based Bibliometric Analysis

In the speech delivered at the centenary celebration of the Communist Party of China(CPC),Xi Jinping,general secretary of the Communist Party of China(CPC)Central Committee,made important remarks on the“Chinese path to modernization.”This term represents the latest achievement China has scored in adapting Marxism to the Chinese context and the needs of the times.It has set the course as China embarks on a new journey of building a strong socialist country with Chinese characteristics and achieving national rejuvenation.Drawing on CiteSpace,we conducted a visualized bibliometric analysis of literature on the Chinese path to modernization by searching the CNKI database using subject terms such as“Chinese modernization,Chinese path to modernization,and Chinese-style modernization.”The findings reveal that:(a)Research on the Chinese path to modernization has gone through three stages:initial establishment,pioneering exploration,and comprehensive in-depth development.(b)Existing literature has covered the four key topics associated with the Chinese path to modernization,namely its essence,goal,methodology,and pioneering achievements.(c)Future research may focus on building up China’s strength in agriculture,developing the digital economy,modernizing China’s system and capacity for governance,and establishing a unique socialist discourse system for Chinese modernization.

基于BERTopic模型的网络暴力事件衍生舆情探测

[研究目的]在海量用户生成内容中及时探测和剖析网络暴力事件的衍生舆情能够为舆情事件链的演化分析、同类舆情的研判介入、衍生事件的监测预警提供理论支持。[研究方法]使用BERTopic模型对短文本内容主题建模并采用聚类的方式展示主题的潜在层次结构。根据词向量余弦相似度设计主题衍生度的计量算法,同时融合词共现网络在文档-词语层面信息捕捉的优势以及桑基图直观演示舆情演化过程的特点,衡量主题间的影响力与衍生关系。[研究结论]在开源数据集下多组主题模型的对照实验中,BERTopic模型在短文本建模以及下游任务的平均得分提高2.13%。在网络暴力热点事件的应用实例中,多维细粒度分析与交互式可视化方法可达到直观展示暴力事件的主题聚类、词义关联与演化态势的效果,实现网络暴力事件衍生舆情的探测与分析。