Purpose:We present an analytical,open source and flexible natural language processing and text mining method for topic evolution,emerging topic detection and research trend forecasting for all kinds of data-tagged tex...Purpose:We present an analytical,open source and flexible natural language processing and text mining method for topic evolution,emerging topic detection and research trend forecasting for all kinds of data-tagged text.Design/methodology/approach:We make full use of the functions provided by the open source VOSviewer and Microsoft Office,including a thesaurus for data clean-up and a LOOKUP function for comparative analysis.Findings:Through application and verification in the domain of perovskite solar cells research,this method proves to be effective.Research limitations:A certain amount of manual data processing and a specific research domain background are required for better,more illustrative analysis results.Adequate time for analysis is also necessary.Practical implications:We try to set up an easy,useful,and flexible interdisciplinary text analyzing procedure for researchers,especially those without solid computer programming skills or who cannot easily access complex software.This procedure can also serve as a wonderful example for teaching information literacy.Originality/value:This text analysis approach has not been reported before.展开更多
As a major strategic technology for reducing greenhouse gas emissions and ensuring energy security,carbon capture,utilization,and storage(CCUS)is of great significance to large-scale emission reduction.From the perspe...As a major strategic technology for reducing greenhouse gas emissions and ensuring energy security,carbon capture,utilization,and storage(CCUS)is of great significance to large-scale emission reduction.From the perspective of knowledge discovery,it is important to analyse the study progress based on existing study achievements,excavate the evolution characteristics of study topics over time,review stage-specific findings,and construct CCUS domain knowledge map.This will help researchers gain an overall understanding of CCUS studies and promote the industry-college-research cooperation in respect to CCUS.Based on the Web of Science(WOS)database platform and CitNet-Explorer software,the present study explore the international research progress,topic evolution track,research hotspot and research trend of CCUS technology since its birth nearly 30 years ago,using bibliometric method,citation network visualization analysis method and cluster analysis method.Through the analysis of literature citation network,it is found that:16 CCUS topics,6 hotspots have been studied in the last three decades.The topics of CCUS studies present an evolution path from CCUS technology security and economicfeasibility analysis to CCUS technological popularization,and then CCUS technological improvement and development.Cutting-edge CCUS looks at the process and infrastructure construction,cost effectiveness and development prospect analysis.CCUS focuses on improvement of process technologies and related infrastructure.展开更多
Researchers across the globe have been increasingly interested in the manner in which important research topics evolve over time within the corpus of scientific literature. In a dataset of scientific articles, each do...Researchers across the globe have been increasingly interested in the manner in which important research topics evolve over time within the corpus of scientific literature. In a dataset of scientific articles, each document can be considered to comprise both the words of the document itself and its citations of other documents. In this paper, we propose a citationcontent-latent Dirichlet allocation(LDA) topic discovery method that accounts for both document citation relations and the content of the document itself via a probabilistic generative model. The citation-content-LDA topic model exploits a two-level topic model that includes the citation information for ‘father' topics and text information for sub-topics. The model parameters are estimated by a collapsed Gibbs sampling algorithm. We also propose a topic evolution algorithm that runs in two steps: topic segmentation and topic dependency relation calculation. We have tested the proposed citation-content-LDA model and topic evolution algorithm on two online datasets, IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI) and IEEE Computer Society(CS), to demonstrate that our algorithm effectively discovers important topics and reflects the topic evolution of important research themes. According to our evaluation metrics, citation-content-LDA outperforms both content-LDA and citation-LDA.展开更多
Revealing and comparing the evolution process of hot topics in the field of Digital Library in China and abroad.[Methods]:Taking data in the field of Digital Library from core journals in CKNI and Web of Science from ...Revealing and comparing the evolution process of hot topics in the field of Digital Library in China and abroad.[Methods]:Taking data in the field of Digital Library from core journals in CKNI and Web of Science from 1990 s to 2020,topics are extracted by LDA model and hot topics are selected based on life cycle theory.Topic evolution paths are generated to contrast evolution of hot topics between home and abroad which are grouped into dimensions of technology and application.It fails to analyze the lagging performance and reasons of research hot topics in the field of Digital Library at home and abroad.In technological dimension of Digital Library,the research content in China lags behind that at abroad.In terms of application dimension,Chinese application tends to focus on social sciences,while application at abroad tends to focus on natural sciences.The evolution of overall research focus is U-shaped,which gradually shifted from technological research to application research,and now turn back to technological dimension.Nowadays,there are also many emerging topics combined with big data technology.展开更多
Purpose:This article aims to describe the global research profile and the development trends of single cell research from the perspective of bibliometric analysis and semantic mining.Design/methodology/approach:The li...Purpose:This article aims to describe the global research profile and the development trends of single cell research from the perspective of bibliometric analysis and semantic mining.Design/methodology/approach:The literatures on single cell research were extracted from Clarivate Analytic’s Web of Science Core Collection between 2009 and 2019.Firstly,bibliometric analyses were performed with Thomson Data Analyzer(TDA).Secondly,topic identification and evolution trends of single cell research was conducted through the LDA topic model.Thirdly,taking the post-discretized method which is used for topic evolution analysis for reference,the topics were also be dispersed to countries to detect the spatial distribution.Findings:The publication of single cell research shows significantly increasing tendency in the last decade.The topics of single cell research field can be divided into three categories,which respectively refers to single cell research methods,mechanism of biological process,and clinical application of single cell technologies.The different trends of these categories indicate that technological innovation drives the development of applied research.The continuous and rapid growth of the topic strength in the field of cancer diagnosis and treatment indicates that this research topic has received extensive attention in recent years.The topic distributions of some countries are relatively balanced,while for the other countries,several topics show significant superiority.Research limitations:The analyzed data of this study only contain those were included in the Web of Science Core Collection.Practical implications:This study provides insights into the research progress regarding single cell field and identifies the most concerned topics which reflect potential opportunities and challenges.The national topic distribution analysis based on the post-discretized analysis method extends topic analysis from time dimension to space dimension.Originality/value:This paper combines bibliometric analysis and LDA model to analyze the evolution trends of single cell research field.The method of extending post-discretized analysis from time dimension to space dimension is distinctive and insightful.展开更多
Purpose: This study aims to reveal the landscape and trends of graphene research in the world by using data from Chemical Abstracts Service(CAS). Design/methodology/approach: Index data from CAS have been retrieved on...Purpose: This study aims to reveal the landscape and trends of graphene research in the world by using data from Chemical Abstracts Service(CAS). Design/methodology/approach: Index data from CAS have been retrieved on 78,756 papers and 23,057 patents on graphene from 1985 to March 2016, and scientometric methods were used to analyze the growth and distribution of R&D output, topic distribution and evolution, and distribution and evolution of substance properties and roles.Findings: In recent years R&D in graphene keeps in rapid growth, while China, South Korea and United States are the largest producers in research but China is relatively weak in patent applications in other countries. Research topics in graphene are continuously expanding from mechanical, material, and electrical properties to a diverse range of application areas such as batteries, capacitors, semiconductors, and sensors devices. The roles of emerging substances are increasing in Preparation and Biological Study. More techniques have been included to improve the preparation processes and applications of graphene in various fields.Research limitations: Only data from CAS is used and some R&D activities solely reported through other channels may be missed. Also more detailed analysis need to be done to reveal the impact of research on development or vice verse, development dynamics among the players, and impact of emerging terms or substance roles on research and technology development.Practical implications: This will provide a valuable reference for scientists and developers, R&D managers, R&D policy makers, industrial and business investers to understand the landscape and trends of graphene research. Its methodologies can be applied to other fields or with data from other similar sources.Originality/value: The integrative use of indexing data on papers and patents of CAS and the systematic exploration of the distribution trends in output, topics, substance roles are distinctive and insightful.展开更多
With the progress and development of computer technology,applying machine learning methods to cancer research has become an important research field.To analyze the most recent research status and trends,main research ...With the progress and development of computer technology,applying machine learning methods to cancer research has become an important research field.To analyze the most recent research status and trends,main research topics,topic evolutions,research collaborations,and potential directions of this research field,this study conducts a bibliometric analysis on 6206 research articles worldwide collected from PubMed between 2011 and 2021 concerning cancer research using machine learning methods.Python is used as a tool for bibliometric analysis,Gephi is used for social network analysis,and the Latent Dirichlet Allocation model is used for topic modeling.The trend analysis of articles not only reflects the innovative research at the intersection of machine learning and cancer but also demonstrates its vigorous development and increasing impacts.In terms of journals,Nature Communications is the most influential journal and Scientific Reports is the most prolific one.The United States and Harvard University have contributed the most to cancer research using machine learning methods.As for the research topic,“Support Vector Machine,”“classification,”and“deep learning”have been the core focuses of the research field.Findings are helpful for scholars and related practitioners to better understand the development status and trends of cancer research using machine learning methods,as well as to have a deeper understanding of research hotspots.展开更多
The Product Sensitive Online Dirichlet Allocation model(PSOLDA)proposed in this paper mainly uses the sentiment polarity of topic words in the review text to improve the accuracy of topic evolution.First,we use Latent...The Product Sensitive Online Dirichlet Allocation model(PSOLDA)proposed in this paper mainly uses the sentiment polarity of topic words in the review text to improve the accuracy of topic evolution.First,we use Latent Dirichlet Allocation(LDA)to obtain the distribution of topic words in the current time window.Second,the word2 vec word vector is used as auxiliary information to determine the sentiment polarity and obtain the sentiment polarity distribution of the current topic.Finally,the sentiment polarity changes of the topics in the previous and next time window are mapped to the sentiment factors,and the distribution of topic words in the next time window is controlled through them.The experimental results show that the PSOLDA model decreases the probability distribution by 0.1601,while Online Twitter LDA only increases by 0.0699.The topic evolution method that integrates the sentimental information of topic words proposed in this paper is better than the traditional model.展开更多
文摘Purpose:We present an analytical,open source and flexible natural language processing and text mining method for topic evolution,emerging topic detection and research trend forecasting for all kinds of data-tagged text.Design/methodology/approach:We make full use of the functions provided by the open source VOSviewer and Microsoft Office,including a thesaurus for data clean-up and a LOOKUP function for comparative analysis.Findings:Through application and verification in the domain of perovskite solar cells research,this method proves to be effective.Research limitations:A certain amount of manual data processing and a specific research domain background are required for better,more illustrative analysis results.Adequate time for analysis is also necessary.Practical implications:We try to set up an easy,useful,and flexible interdisciplinary text analyzing procedure for researchers,especially those without solid computer programming skills or who cannot easily access complex software.This procedure can also serve as a wonderful example for teaching information literacy.Originality/value:This text analysis approach has not been reported before.
基金Supported by the Fundamental Research funds for the China Central Universities“CCUS topic detection and evolution analysis based on CitNetExplorer”[Grant number.JBK2002042].
文摘As a major strategic technology for reducing greenhouse gas emissions and ensuring energy security,carbon capture,utilization,and storage(CCUS)is of great significance to large-scale emission reduction.From the perspective of knowledge discovery,it is important to analyse the study progress based on existing study achievements,excavate the evolution characteristics of study topics over time,review stage-specific findings,and construct CCUS domain knowledge map.This will help researchers gain an overall understanding of CCUS studies and promote the industry-college-research cooperation in respect to CCUS.Based on the Web of Science(WOS)database platform and CitNet-Explorer software,the present study explore the international research progress,topic evolution track,research hotspot and research trend of CCUS technology since its birth nearly 30 years ago,using bibliometric method,citation network visualization analysis method and cluster analysis method.Through the analysis of literature citation network,it is found that:16 CCUS topics,6 hotspots have been studied in the last three decades.The topics of CCUS studies present an evolution path from CCUS technology security and economicfeasibility analysis to CCUS technological popularization,and then CCUS technological improvement and development.Cutting-edge CCUS looks at the process and infrastructure construction,cost effectiveness and development prospect analysis.CCUS focuses on improvement of process technologies and related infrastructure.
基金supported by the National Basic Research Program(973)of China(No.2012CB316400)
文摘Researchers across the globe have been increasingly interested in the manner in which important research topics evolve over time within the corpus of scientific literature. In a dataset of scientific articles, each document can be considered to comprise both the words of the document itself and its citations of other documents. In this paper, we propose a citationcontent-latent Dirichlet allocation(LDA) topic discovery method that accounts for both document citation relations and the content of the document itself via a probabilistic generative model. The citation-content-LDA topic model exploits a two-level topic model that includes the citation information for ‘father' topics and text information for sub-topics. The model parameters are estimated by a collapsed Gibbs sampling algorithm. We also propose a topic evolution algorithm that runs in two steps: topic segmentation and topic dependency relation calculation. We have tested the proposed citation-content-LDA model and topic evolution algorithm on two online datasets, IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI) and IEEE Computer Society(CS), to demonstrate that our algorithm effectively discovers important topics and reflects the topic evolution of important research themes. According to our evaluation metrics, citation-content-LDA outperforms both content-LDA and citation-LDA.
文摘Revealing and comparing the evolution process of hot topics in the field of Digital Library in China and abroad.[Methods]:Taking data in the field of Digital Library from core journals in CKNI and Web of Science from 1990 s to 2020,topics are extracted by LDA model and hot topics are selected based on life cycle theory.Topic evolution paths are generated to contrast evolution of hot topics between home and abroad which are grouped into dimensions of technology and application.It fails to analyze the lagging performance and reasons of research hot topics in the field of Digital Library at home and abroad.In technological dimension of Digital Library,the research content in China lags behind that at abroad.In terms of application dimension,Chinese application tends to focus on social sciences,while application at abroad tends to focus on natural sciences.The evolution of overall research focus is U-shaped,which gradually shifted from technological research to application research,and now turn back to technological dimension.Nowadays,there are also many emerging topics combined with big data technology.
基金the Chinese Academy of Sciences literature information capability construction project of 2020“Construction of strategic information research and consultation system in science and technology field”(Grant No.E290001)。
文摘Purpose:This article aims to describe the global research profile and the development trends of single cell research from the perspective of bibliometric analysis and semantic mining.Design/methodology/approach:The literatures on single cell research were extracted from Clarivate Analytic’s Web of Science Core Collection between 2009 and 2019.Firstly,bibliometric analyses were performed with Thomson Data Analyzer(TDA).Secondly,topic identification and evolution trends of single cell research was conducted through the LDA topic model.Thirdly,taking the post-discretized method which is used for topic evolution analysis for reference,the topics were also be dispersed to countries to detect the spatial distribution.Findings:The publication of single cell research shows significantly increasing tendency in the last decade.The topics of single cell research field can be divided into three categories,which respectively refers to single cell research methods,mechanism of biological process,and clinical application of single cell technologies.The different trends of these categories indicate that technological innovation drives the development of applied research.The continuous and rapid growth of the topic strength in the field of cancer diagnosis and treatment indicates that this research topic has received extensive attention in recent years.The topic distributions of some countries are relatively balanced,while for the other countries,several topics show significant superiority.Research limitations:The analyzed data of this study only contain those were included in the Web of Science Core Collection.Practical implications:This study provides insights into the research progress regarding single cell field and identifies the most concerned topics which reflect potential opportunities and challenges.The national topic distribution analysis based on the post-discretized analysis method extends topic analysis from time dimension to space dimension.Originality/value:This paper combines bibliometric analysis and LDA model to analyze the evolution trends of single cell research field.The method of extending post-discretized analysis from time dimension to space dimension is distinctive and insightful.
文摘Purpose: This study aims to reveal the landscape and trends of graphene research in the world by using data from Chemical Abstracts Service(CAS). Design/methodology/approach: Index data from CAS have been retrieved on 78,756 papers and 23,057 patents on graphene from 1985 to March 2016, and scientometric methods were used to analyze the growth and distribution of R&D output, topic distribution and evolution, and distribution and evolution of substance properties and roles.Findings: In recent years R&D in graphene keeps in rapid growth, while China, South Korea and United States are the largest producers in research but China is relatively weak in patent applications in other countries. Research topics in graphene are continuously expanding from mechanical, material, and electrical properties to a diverse range of application areas such as batteries, capacitors, semiconductors, and sensors devices. The roles of emerging substances are increasing in Preparation and Biological Study. More techniques have been included to improve the preparation processes and applications of graphene in various fields.Research limitations: Only data from CAS is used and some R&D activities solely reported through other channels may be missed. Also more detailed analysis need to be done to reveal the impact of research on development or vice verse, development dynamics among the players, and impact of emerging terms or substance roles on research and technology development.Practical implications: This will provide a valuable reference for scientists and developers, R&D managers, R&D policy makers, industrial and business investers to understand the landscape and trends of graphene research. Its methodologies can be applied to other fields or with data from other similar sources.Originality/value: The integrative use of indexing data on papers and patents of CAS and the systematic exploration of the distribution trends in output, topics, substance roles are distinctive and insightful.
基金Natural Science Foundation of Guangdong Province,Grant/Award Number:2021A1515011339。
文摘With the progress and development of computer technology,applying machine learning methods to cancer research has become an important research field.To analyze the most recent research status and trends,main research topics,topic evolutions,research collaborations,and potential directions of this research field,this study conducts a bibliometric analysis on 6206 research articles worldwide collected from PubMed between 2011 and 2021 concerning cancer research using machine learning methods.Python is used as a tool for bibliometric analysis,Gephi is used for social network analysis,and the Latent Dirichlet Allocation model is used for topic modeling.The trend analysis of articles not only reflects the innovative research at the intersection of machine learning and cancer but also demonstrates its vigorous development and increasing impacts.In terms of journals,Nature Communications is the most influential journal and Scientific Reports is the most prolific one.The United States and Harvard University have contributed the most to cancer research using machine learning methods.As for the research topic,“Support Vector Machine,”“classification,”and“deep learning”have been the core focuses of the research field.Findings are helpful for scholars and related practitioners to better understand the development status and trends of cancer research using machine learning methods,as well as to have a deeper understanding of research hotspots.
基金Supported by the Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information Security(AGK2019004)Songjiang District Science and Technology Research Project(19SJKJGG83)National Natural Science Foundation of China(61802251)。
文摘The Product Sensitive Online Dirichlet Allocation model(PSOLDA)proposed in this paper mainly uses the sentiment polarity of topic words in the review text to improve the accuracy of topic evolution.First,we use Latent Dirichlet Allocation(LDA)to obtain the distribution of topic words in the current time window.Second,the word2 vec word vector is used as auxiliary information to determine the sentiment polarity and obtain the sentiment polarity distribution of the current topic.Finally,the sentiment polarity changes of the topics in the previous and next time window are mapped to the sentiment factors,and the distribution of topic words in the next time window is controlled through them.The experimental results show that the PSOLDA model decreases the probability distribution by 0.1601,while Online Twitter LDA only increases by 0.0699.The topic evolution method that integrates the sentimental information of topic words proposed in this paper is better than the traditional model.
