CN104636424A - Method for building literature review framework based on atlas analysis - Google Patents
Method for building literature review framework based on atlas analysis Download PDFInfo
- Publication number
- CN104636424A CN104636424A CN201410714189.0A CN201410714189A CN104636424A CN 104636424 A CN104636424 A CN 104636424A CN 201410714189 A CN201410714189 A CN 201410714189A CN 104636424 A CN104636424 A CN 104636424A
- Authority
- CN
- China
- Prior art keywords
- analysis
- author
- frequency
- literature
- literature review
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method for building a literature review framework based on atlas analysis. The method is used for scientifically classifying and summarizing document literature. The document literature keywords and authors serve as the principal line, high-frequency keywords and authors are screened out in all searched targeted document literature through SATI software, a keyword co-occurrence matrix and an author co-occurrence matrix are built, study categories are analyzed and determined through factors in an SPSS, then the hotspot theme of each study category is summarized through classification and analysis on the high-frequency keywords, and a hotspot study field is determined; the number of published articles and the total citation frequency of the authors are counted, the h index of each author is worked out, then the author co-occurrence matrix is led into Ucinet and NetDraw software, the authority author is determined, and the study front is provided.
Description
Technical field
The present invention relates to the correlative technology field of documentation & info process, is a kind of method building literature review framework based on atlas analysis.
Background technology
Literature review collects a large amount of related data to a certain field, a certain specialty or problem in a certain respect, problem or research special topic, by analyzing, reading, arrange, refine the latest developments of current problem, problem or research special topic, academic opinion or suggestion, make a kind of scientific paper of comprehensive introduction and elaboration.Write literature review to need to search reading lot of documents, and carry out analysis and summary to document, this is very heavy for task the personnel of writing, and efficiency is low, is difficult to ensure comprehensively, system, produces literature review in time.Existence is selected the improper of literature reference and causes the deflection of disciplinary study; And the study hotspot that cause complete to keyword search and forward position reason unclear; Can not screen high-frequency key words thus the deficiency etc. of the aspects such as the metric philological approach of focus trend and frontier development can not be analyzed.
Summary of the invention
The invention provides a kind of method building literature review framework based on atlas analysis, summarize for classification documents and materials being carried out to science.Serve as theme with documents and materials keyword, author, first SATI software screening method is utilized to go out high-frequency key words and the author of all documents and materials, construct key words co-occurrence matrix, author's co-occurrence matrix, the factorial analysis in SPSS is utilized to determine to study classification afterwards, afterwards by summarizing each research class focus theme now to the cluster analysis of high-frequency key words, determine hot research field; The dispatch amount of author, Total cited number are added up, calculates the h index of every author, at the same time author's co-occurrence matrix is imported Ucinet, NetDraw software, determine authoritative author, its study frontier is provided.
The present invention is achieved like this.Build a method for literature review framework based on atlas analysis, it is characterized in that, comprise the following steps:
One, pertinent literature is obtained
Determine research theme, formulate search strategy, select the database resource of literature reference, deterministic retrieval word, sets up retrieval type, adjustment search strategy, the pertinent literature of screening hit;
Two, data acquisition and formation
1. result for retrieval is derived, save as txt plain text format;
2. the plain text format file obtained is imported SATI software, utilize SATI software screening method to go out high-frequency key words and the author of all documents and materials, construct key words co-occurrence matrix, author's co-occurrence matrix; Co-occurrence matrix is imported SPSS, in ochiai mode, co-occurrence matrix is converted to similar matrix;
3. the classification of the text-only file of derivation according to autograph, author is added up, obtain author's quoted frequency;
Three, data result is integrated and is analyzed
1. carry out the regional analysis of mean cited times;
2. research field analysis
1) factorial analysis
Similar matrix is imported SPSS, utilizes the principal component analysis (PCA) of factorial analysis, extract the principal ingredient of all variablees, obtain explained variance population variance table and rubble figure.
2) cluster analysis
Key words co-occurrence matrix is imported in SPSS18.0 software and selects " between group, linking (between-groups linkage) distance " to carry out cluster analysis, obtain cluster analysis dendrogram.According to the characteristic of variable, binding factor analysis extracts principal ingredient, high-frequency key words can be summarized as the research contents of several aspect, therefrom embodies the field of study hotspot.The result of cluster analysis and factorial analysis is basically identical, and both confirm mutually.
3. author h index, social network analysis
1) " author-dispatch-quoted frequency " table builds
According to dispatch number, quoted frequency, the average quoted frequency statistics of author, build " author-dispatch-quoted frequency " table, arrange from high to low by average quoted frequency;
2) " author-dispatch number-h index " table builds
All articles author delivered in a domain sort according to mean cited times, and when mean cited times is less than sequence number, the value of h index is exactly that the sequence number of place article subtracts 1.According to the retrieval list of every author, construct front tens place author h list.
3) author's social network analysis
Author's co-occurrence matrix is imported Ucinet, inputs NetDraw more afterwards, can clear derivation author community network network diagramming.If click " analysis " menu, can specifically quantize to draw centrality degree index of social network, hold certain disciplinary study focus and mutual relationship thereof from the angle of centrality analysis.
Four, literature review is write
Result based on atlas analysis is built into literature review, and the transition of high-frequency key words show the evolution of certain disciplinary study focus; Factorial analysis and cluster analysis draw the focus theme of research in this field; Social network analysis embodies core, focus and the development trend studied; The soluble research theme of term clustering analytic approach altogether.
The present invention is mainly based on the analysis of collection of illustrative plates, and the transition of high-frequency key words show the evolution of certain disciplinary study focus; Factorial analysis and cluster analysis draw the focus theme of research in this field; Social network analysis embodies core, focus and the development trend studied; The soluble research theme of term clustering analytic approach altogether.Utilize the summary that this method is write, there is the feature such as distinct systematicness, ageing, accuracy, logic, the historical background of research special topic, present Research and development trend can be reflected, there is higher information science and be worth.
This method efficiently solves the summary not having framework specification, and existence is selected the improper of literature reference and causes the deflection of disciplinary study; And the study hotspot that cause complete to keyword search and forward position reason unclear; Can not screen high-frequency key words thus the deficiency etc. of the aspects such as the metric philological approach of focus trend and frontier development can not be analyzed, for scholar provide a kind of content more comprehensively, the method for more clear, the thinking of theme Summary writing more efficiently.
Accompanying drawing explanation
Fig. 1 is schematic flow sheet of the present invention.
Embodiment
1. obtain pertinent literature (S01)
The database resource of 1.1 selection literature references
According to research theme, select database.Select CSSCI database as studied domestic special topic, CNKI knows net etc.; The international special topic of research is generally searching platform, Elsevier database, SPRINGER database with the Web of Science of American science technical information information institute (ISI).
1.2 formulate search strategy, screening hit pertinent literature
Deterministic retrieval word, sets up retrieval type, adjustment search strategy, the pertinent literature of screening hit.
2. data acquisition and formation (S02)
2.1 screening high-frequency key words
The searching document of Chinese database, can utilize CNKI platform, will export result for retrieval, saves as txt plain text format;
The result for retrieval of foreign language materials, derive document, the way of output is " complete record and incorporated by reference document ", saves as txt plain text format.
2.2 build keyword matrix
1) high-frequency key words is screened
Plain text result is imported soft SA TI, carries out successively changing, duplicate removal process, extract keyword and the frequency of occurrence of searching document, the keyword that the frequency of occurrences is lower can be left out, copy to Excel and carry out arrangement and carry out word frequency sequence.
2) keyword matrix is built
(1) build keyword and build existing matrix
Soft SA TI generates co-occurrence matrix automatically.Hitting counting high-frequency key words between two the word frequency simultaneously occurred in document, forming co-occurrence matrix.
(2) keyword similar matrix is built
Co-occurrence matrix is imported SPSS, in ochiai mode, co-occurrence matrix is converted to similar matrix, it is nearer that numerical value more represents the distance of two groups of keywords close to 1, and similarity is larger.
2.3 author's quoted frequency statistics
The classification of the plain text of derivation according to autograph, author is added up, draws in time domain the higher front tens place author that publishes thesis, arrange from high to low according to quoted frequency.
3. data result is integrated and is analyzed (S03)
The regional analysis of 3.1 mean cited times
Added up according to national region by searching document, within nearly ten years, certain disciplinary study is made " achievement in research mean cited times statistical form " with regard to dispatch total amount.
3.2 research field analyses
1) factorial analysis
Similar matrix is imported SPSS, utilizes the principal component analysis (PCA) of factorial analysis, extract the principal ingredient of all variablees, obtain explained variance population variance table and rubble figure.
2) cluster analysis
Key words co-occurrence matrix is imported in SPSS18.0 software and selects " between group, linking (between-groups linkage) distance " to carry out cluster analysis, obtain cluster analysis dendrogram.According to the characteristic of variable, binding factor analysis extracts principal ingredient, high-frequency key words can be summarized as the research contents of several aspect, therefrom embodies the field of study hotspot.The result of cluster analysis and factorial analysis is basically identical, and both confirm mutually.
3.3 author h indexes, social network analysis
1) " author-dispatch-quoted frequency " table builds
According to dispatch number, quoted frequency, the average quoted frequency statistics of author, build " author-dispatch-quoted frequency " table, arrange from high to low by average quoted frequency;
2) " author-dispatch number-h index " table builds
All articles author delivered in a domain sort according to mean cited times, and when mean cited times is less than sequence number, the value of h index is exactly that the sequence number of place article subtracts 1.According to the retrieval list of every author, construct front tens place author h list.H index (h-index) is a mixing quantizating index, objectively can reflect and weighs academic output and weigh academic.
3) author's social network analysis
Author's co-occurrence matrix is imported software Ucinet, afterwards analysis result is input to software NetDraw again, can clear derivation author community network network diagramming.If click " analysis " menu, can specifically quantize to draw centrality degree index of social network, hold certain disciplinary study focus and mutual relationship thereof from the angle of centrality analysis.Therefrom, angle value centrality degree index of social network is the number that is connected actual in another node, and the number of degrees mean more greatly the Central Position more core of this node.Middle centrad " refer to that a node is as the order number connecting intermediary, the number of degrees are larger, reflect that the Link role of this node is stronger.Centrad analysis can disclose authority figure and the study frontier of a certain research field.
4. write literature review (S04)
The structure of literature review framework, mainly based on the analysis of collection of illustrative plates, the transition of high-frequency key words show the evolution of certain disciplinary study focus; Factorial analysis and cluster analysis draw the focus theme of research in this field; Social network analysis embodies core, focus and the development trend studied; The soluble research theme of term clustering analytic approach altogether.
Along with going deep into of research, certain class keywords word frequency can change, and cannot get rid of the possibility that the lower keyword of current word frequency becomes study frontier in the future.Therefore, need the method performance analysis by literature review framework establishment, to guarantee that analysis result is ageing, accuracy.
Claims (7)
1. build a method for literature review framework based on atlas analysis, it is characterized in that, comprise the following steps:
Obtain pertinent literature
Data acquisition and formation
1. result for retrieval is derived, save as txt plain text format;
2. the plain text format file obtained is imported SATI software, utilize SATI software screening method to go out high-frequency key words and the author of all documents and materials, construct key words co-occurrence matrix, author's co-occurrence matrix; Co-occurrence matrix is imported SPSS, in ochiai mode, co-occurrence matrix is converted to similar matrix;
3. the classification of the text-only file of derivation according to autograph, author is added up, obtain author's quoted frequency;
Data result is integrated and is analyzed
1. the regional analysis of mean cited times
2. research field analysis
1) factorial analysis
Similar matrix is imported SPSS, utilizes the principal component analysis (PCA) of factorial analysis, extract the principal ingredient of all variablees, obtain explained variance population variance table and rubble figure;
2) cluster analysis
Key words co-occurrence matrix is imported in SPSS18.0 software and select " between group link distance " to carry out cluster analysis, obtain cluster analysis dendrogram;
3. author h index, social network analysis
1) " author-dispatch-quoted frequency " table builds
2) " author-dispatch number-h index " table builds
3) author's social network analysis
Author's co-occurrence matrix is imported Ucinet, inputs NetDraw afterwards, can clear derivation author community network network diagramming;
Write literature review
Result based on atlas analysis is built into literature review, and the transition of high-frequency key words show the evolution of certain disciplinary study focus; Factorial analysis and cluster analysis draw the focus theme of research in this field; Social network analysis embodies core, focus and the development trend studied; The soluble research theme of term clustering analytic approach altogether.
2. the method building literature review framework based on atlas analysis according to claim 1, it is characterized in that, described acquisition pertinent literature refers to determines research theme, formulate search strategy, select the database resource of literature reference, deterministic retrieval word, sets up retrieval type, adjustment search strategy, the pertinent literature of screening hit.
3. the method building literature review framework based on atlas analysis according to claim 1, it is characterized in that, the regional analysis of described mean cited times refers to be added up searching document according to national region, and within nearly ten years, certain disciplinary study is made " achievement in research mean cited times statistical form " with regard to dispatch total amount.
4. the method building literature review framework based on atlas analysis according to claim 1, it is characterized in that, according to the characteristic of variable, the analysis of cluster analysis binding factor extracts principal ingredient, high-frequency key words can be summarized as the research contents of several aspect, therefrom embody the field of study hotspot.
5. the method building literature review framework based on atlas analysis according to claim 1, it is characterized in that, described " author-dispatch-quoted frequency " table structure is dispatch number, quoted frequency, average quoted frequency statistics according to author, build " author-dispatch-quoted frequency " table, arrange from high to low by average quoted frequency.
6. the method building literature review framework based on atlas analysis according to claim 1, it is characterized in that, it is that all articles author delivered in a domain sort according to mean cited times that described " author-dispatch number-h index " table builds, when mean cited times is less than sequence number, the value of h index is exactly that the sequence number of place article subtracts 1; According to the retrieval list of every author, construct front tens place author h list.
7. the method building literature review framework based on atlas analysis according to claim 1, it is characterized in that, during described author's social network analysis, NetDraw can specifically quantize to draw centrality degree index of social network, holds certain disciplinary study focus and mutual relationship thereof from the angle of centrality analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410714189.0A CN104636424A (en) | 2014-12-02 | 2014-12-02 | Method for building literature review framework based on atlas analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410714189.0A CN104636424A (en) | 2014-12-02 | 2014-12-02 | Method for building literature review framework based on atlas analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104636424A true CN104636424A (en) | 2015-05-20 |
Family
ID=53215170
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410714189.0A Pending CN104636424A (en) | 2014-12-02 | 2014-12-02 | Method for building literature review framework based on atlas analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104636424A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372093A (en) * | 2015-07-24 | 2017-02-01 | 同方知网(北京)技术有限公司 | Academic index system and issuing method thereof |
| CN106557506A (en) * | 2015-09-28 | 2017-04-05 | 上海半坡网络技术有限公司 | A kind of literature search result processing method and system |
| CN106909606A (en) * | 2017-01-05 | 2017-06-30 | 南昌大学 | A kind of method that discipline information dynamic framework is made based on atlas analysis |
| CN106933846A (en) * | 2015-12-30 | 2017-07-07 | 中国医学科学院医学信息研究所 | The destructuring confluence analysis method of tumour related science document and science data |
| CN108475256A (en) * | 2016-02-05 | 2018-08-31 | 谷歌有限责任公司 | Feature insertion is generated from homologous factors |
| CN108595559A (en) * | 2018-04-12 | 2018-09-28 | 科技部科技评估中心 | The computational methods of technical research forward position index |
| CN108614867A (en) * | 2018-04-12 | 2018-10-02 | 科技部科技评估中心 | Frontline technology sex index computational methods based on scientific paper and system |
| CN108764323A (en) * | 2018-05-22 | 2018-11-06 | 安徽大学 | A kind of match wins user force detection method in platform economic networks |
| CN108899930A (en) * | 2018-07-09 | 2018-11-27 | 西华大学 | Wind-powered electricity generation station equivalent modeling method based on Principal Component Analysis Method and hierarchical clustering algorithm |
| CN109086399A (en) * | 2018-07-30 | 2018-12-25 | 中国人民解放军军事科学院系统工程研究院 | A kind of analysis of comprehensive contribution degree and integrated visual technique of expression |
| CN109255026A (en) * | 2018-08-23 | 2019-01-22 | 云南师范大学 | A method of it is analyzed based on Co-word analysis and the learning demand of clustering |
| CN109299090A (en) * | 2018-09-03 | 2019-02-01 | 平安科技（深圳）有限公司 | Fund Method of Knowledge Reasoning, system, computer equipment and storage medium |
| CN109493978A (en) * | 2018-11-12 | 2019-03-19 | 北京懿医云科技有限公司 | Disease research hot spot method for digging and device, storage medium, electronic equipment |
| CN109800288A (en) * | 2019-01-22 | 2019-05-24 | 杭州师范大学 | A kind of the scientific research analysis of central issue and prediction technique of knowledge based map |
-
2014
- 2014-12-02 CN CN201410714189.0A patent/CN104636424A/en active Pending
Non-Patent Citations (4)
| Title |
|---|
| 张士靖 等: "基于CSSCI的知识服务领域高被引作者的可视化研究", 《情报杂志》 * |
| 李敏 等: "国内中学教育研究现状及热点探究-基于CNKI的文献计量分析", 《理论探索》 * |
| 钱蓉 等: "CT或MRI应用于胰腺假性囊肿的文献计量学分析", 《中国普外基础与临床杂志》 * |
| 韩立娜 等: "我国产业升级研究述评——基于文献计量和社会网络分析", 《合肥工业大学学报（社会科学版）》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372093A (en) * | 2015-07-24 | 2017-02-01 | 同方知网(北京)技术有限公司 | Academic index system and issuing method thereof |
| CN106557506B (en) * | 2015-09-28 | 2019-09-13 | 上海半坡网络技术有限公司 | A kind of literature search result processing method and system |
| CN106557506A (en) * | 2015-09-28 | 2017-04-05 | 上海半坡网络技术有限公司 | A kind of literature search result processing method and system |
| CN106933846A (en) * | 2015-12-30 | 2017-07-07 | 中国医学科学院医学信息研究所 | The destructuring confluence analysis method of tumour related science document and science data |
| CN108475256A (en) * | 2016-02-05 | 2018-08-31 | 谷歌有限责任公司 | Feature insertion is generated from homologous factors |
| CN108475256B (en) * | 2016-02-05 | 2022-04-08 | 谷歌有限责任公司 | Generating feature embedding from co-occurrence matrices |
| CN106909606A (en) * | 2017-01-05 | 2017-06-30 | 南昌大学 | A kind of method that discipline information dynamic framework is made based on atlas analysis |
| CN108595559A (en) * | 2018-04-12 | 2018-09-28 | 科技部科技评估中心 | The computational methods of technical research forward position index |
| CN108614867A (en) * | 2018-04-12 | 2018-10-02 | 科技部科技评估中心 | Frontline technology sex index computational methods based on scientific paper and system |
| CN108614867B (en) * | 2018-04-12 | 2022-03-15 | 科技部科技评估中心 | Academic paper-based technology frontier index calculation method and system |
| CN108595559B (en) * | 2018-04-12 | 2022-03-01 | 科技部科技评估中心 | Calculation method for leading edge index of technical research |
| CN108764323A (en) * | 2018-05-22 | 2018-11-06 | 安徽大学 | A kind of match wins user force detection method in platform economic networks |
| CN108899930A (en) * | 2018-07-09 | 2018-11-27 | 西华大学 | Wind-powered electricity generation station equivalent modeling method based on Principal Component Analysis Method and hierarchical clustering algorithm |
| CN109086399A (en) * | 2018-07-30 | 2018-12-25 | 中国人民解放军军事科学院系统工程研究院 | A kind of analysis of comprehensive contribution degree and integrated visual technique of expression |
| CN109086399B (en) * | 2018-07-30 | 2019-09-10 | 中国人民解放军军事科学院系统工程研究院 | A kind of analysis of comprehensive contribution degree and integrated visual technique of expression |
| CN109255026B (en) * | 2018-08-23 | 2021-06-25 | 云南师范大学 | Learning demand analysis method based on common word analysis and cluster analysis |
| CN109255026A (en) * | 2018-08-23 | 2019-01-22 | 云南师范大学 | A method of it is analyzed based on Co-word analysis and the learning demand of clustering |
| CN109299090A (en) * | 2018-09-03 | 2019-02-01 | 平安科技（深圳）有限公司 | Fund Method of Knowledge Reasoning, system, computer equipment and storage medium |
| CN109299090B (en) * | 2018-09-03 | 2023-05-30 | 平安科技（深圳）有限公司 | Foundation centrality calculating method, system, computer equipment and storage medium |
| CN109493978B (en) * | 2018-11-12 | 2021-05-25 | 北京懿医云科技有限公司 | Disease research hotspot mining method and device, storage medium and electronic equipment |
| CN109493978A (en) * | 2018-11-12 | 2019-03-19 | 北京懿医云科技有限公司 | Disease research hot spot method for digging and device, storage medium, electronic equipment |
| CN109800288B (en) * | 2019-01-22 | 2020-12-15 | 杭州师范大学 | Scientific research hotspot analysis and prediction method based on knowledge graph |
| CN109800288A (en) * | 2019-01-22 | 2019-05-24 | 杭州师范大学 | A kind of the scientific research analysis of central issue and prediction technique of knowledge based map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104636424A (en) | Method for building literature review framework based on atlas analysis | |
| CN103678670B (en) | Micro-blog hot word and hot topic mining system and method | |
| CN102314519B (en) | Information searching method based on public security domain knowledge ontology model | |
| CN104778209B (en) | A kind of opining mining method for millions scale news analysis | |
| CN102298642B (en) | Method and system for extracting text information | |
| CN106104519B (en) | Phrase is to collection device and computer-readable storage medium | |
| CN103823890B (en) | A kind of microblog hot topic detection method for special group and device | |
| CN101833579B (en) | Method and system for automatically detecting academic misconduct literature | |
| CN104965931A (en) | Big data based public opinion analysis method | |
| CN103186662A (en) | System and method for extracting dynamic public sentiment keywords | |
| CN104699767B (en) | A kind of extensive Ontology Mapping Method towards Chinese language | |
| CN101702167A (en) | Method for extracting attribution and comment word with template based on internet | |
| CN104077417A (en) | Figure tag recommendation method and system in social network | |
| CN106104524A (en) | Complex predicate template collection device and be used for its computer program | |
| CN105138577A (en) | Big data based event evolution analysis method | |
| CN105631018A (en) | Article feature extraction method based on topic model | |
| CN104408083A (en) | Socialized media analyzing system | |
| CN109783815A (en) | A kind of various dimensions network public-opinion big data comparative analysis method | |
| Uchitpe et al. | Predicting the future of project management research | |
| CN102779119B (en) | A kind of method of extracting keywords and device | |
| CN104965930A (en) | Big data based emergency evolution analysis method | |
| Pouromid et al. | ParsBERT post-training for sentiment analysis of tweets concerning stock market | |
| CN109543001A (en) | A kind of scientific and technological entry abstracting method characterizing Scientific Articles research contents | |
| KR20120038575A (en) | Method of automatic patent document categorization adjusting association rules and frequent itemset | |
| Al-Anzi et al. | A micro-word based approach for arabic sentiment analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150520 |
|
| WD01 | Invention patent application deemed withdrawn after publication |