CN110309322A - A kind of tutor's influence power appraisal procedure based on two subnetwork of tutor-student - Google Patents

A kind of tutor's influence power appraisal procedure based on two subnetwork of tutor-student Download PDF

Info

Publication number
CN110309322A
CN110309322A CN201910485980.1A CN201910485980A CN110309322A CN 110309322 A CN110309322 A CN 110309322A CN 201910485980 A CN201910485980 A CN 201910485980A CN 110309322 A CN110309322 A CN 110309322A
Authority
CN
China
Prior art keywords
student
index
data
papers
score
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.)
Withdrawn
Application number
CN201910485980.1A
Other languages
Chinese (zh)
Inventor
夏锋
郑文青
任静
刘嘉莹
孔祥杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dalian University of Technology
Original Assignee
Dalian University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Dalian University of Technology filed Critical Dalian University of Technology
Priority to CN201910485980.1A priority Critical patent/CN110309322A/en
Publication of CN110309322A publication Critical patent/CN110309322A/en
Withdrawn legal-status Critical Current

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
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/382—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using citations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Educational Administration (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Technology (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present invention provides a kind of tutor's influence power appraisal procedures based on two subnetwork of tutor-student, belong to computer software fields.This method calculates student's overall target score by multi-index evaluation and the cyberrelationship established between tutor and student is analyzed.This method handles Microsoft's data set and Web of Science factors affecting periodicals data set, extract each evaluation index of student, overall merit marking is carried out to these indexs using integrated evaluating method, these scores are adjusted by the academic age and obtain final Students ' Comprehensive score, then two subnetwork of tutor-student is established, and the comprehensive score of student is brought into two subnetworks, the influence power of tutor is calculated by way of random walk, it finally brings tutor into be adjusted at the academic age, to obtain the influence index of tutor.

Description

Instructor-student binary network-based instructor influence evaluation method
Technical Field
The invention belongs to the field of computer software, and relates to a mentor influence evaluation method based on a mentor-student binary network.
Background
The development of computer science technology is faster and faster, and high-end technology is rapidly developed and continuously innovated. Research on computer science is being conducted, and by analyzing big data using computer science, it is expected to acquire new knowledge and technology from it, which are not discovered by everyone at present.
The data volume of each field is explosively increased due to big data, academic data corresponding to the academic field are various, and Microsoft data sets, journal factor data sets provided by Web of Science and the like used in the invention are all in the category of the academic field. Deep learner information is mined from the data, and the learners and the relationship thereof can be studied more deeply.
At present, most research contents for evaluation indexes of influence of scholars are developed around the number of papers, the number of collaborations, the hindex of scholars and the like of scholars, and few researches for evaluating the influence of scholars on students are performed according to the development conditions of the scholars and the students. The most important of knowledge and research is just inheritance. Research, light is difficult for one to understand and develop extremely deeply. In order to make the research continue to develop, the research is often carried forward and the later is promoted, so that the later is the student. Therefore, it is far from sufficient to evaluate the influence of a scholars and rely on the amount of personal papers, and the guide proposes the evaluation index to make up for the deficiency. The influence of a student as a mentor is evaluated through various indexes of the student.
Disclosure of Invention
The invention provides a teacher influence evaluation method based on a teacher-student binary network, which solves the problem that the student influence evaluation is only developed around the number of the students ' papers, the number of the students ' collaborations, the student's hindex and the like at present, and provides a new selection scheme for the students to select the teacher.
The technical scheme of the invention is as follows:
a teacher influence evaluation method based on a teacher-student binary network comprises the following steps:
s1: obtaining effective data and carrying out data preprocessing;
the valid data comprises: the data of the students, the data corresponding to the papers and the students, the paper data, the citation data, the year of publication of the papers, the influence factor data of periodicals and the relationship data of teachers and students;
the pretreatment comprises the following steps: 1. number of the theory: extracting student information from the student data, and extracting the quantity of the papers of the student and published papers from the data corresponding to the papers and the students; 2. the introduced amount is as follows: obtaining the total quoted amount of the student paper according to the quoted data; h-index: calculating the quoted amount of the published papers of the scholars according to the quoted data, and arranging the quoted amount from high to low, wherein when the nth paper is less than or equal to the quoted amount and the n +1 th paper is greater than the quoted amount, n is the h-index of the scholars; 4. academic age: determining the academic age of the scholars according to the publication year data of the papers by subtracting the publication year of the first paper from the latest year in the data records; 5. published papers journal impact factor: extracting corresponding information of the papers and periodicals in the paper data, extracting the influence factors of the periodicals where the papers are located corresponding to the influence factor data of the periodicals, corresponding the papers and the student ids through corresponding data of the papers and the students, taking out the paper of a journal factor TOP3 in the student's paper, and averaging the paper to represent the paper publication level of the student, wherein the average number of journal factors of all papers published by the student is not enough for three papers;
s2: and (3) scoring the paper number, the quoted amount, the h-index and the published paper journal influence factor of the scholars in the S1 by using a multi-index comprehensive evaluation method, wherein the method specifically comprises the following steps:
s2.1: a normalized initial matrix is constructed. The method is characterized in that n students needing to be evaluated are arranged, each student has four indexes of h-index, quoted quantity, number of papers and published papers and periodicals influence factor, and then the original data construction matrix is as follows:
wherein x isn1、xn2、xn3、xn4Respectively representing h-index, quoted amount, number of papers and periodicals of the nth student, and influence factor indexes of published papers and periodicals;
constructing a weighting matrix, and carrying out vector normalization on the attributes, namely dividing each datum by the norm of the current column vector, wherein the formula is as follows:
wherein x isijJ index representing the ith student; i is the ith student and takes values from 1 to n, j is an evaluation index and takes values from 1 to 4;
obtaining a normalized normalization matrix Z:
s2.2: determination of the optimum Z+And worst Z-Two schemes are adopted.
Best mode solution Z+Is composed of the maximum value of each column of elements, and the formula is as follows:
worst case scenario Z-Is composed of the maximum value of each column of elements, and the formula is as follows:
s2.3: and calculating the closeness degree of each evaluation index to the optimal scheme and the worst scheme, wherein the formula is as follows:
wherein,the degree of closeness of each evaluation index to the optimal solution is represented,indicates the degree of closeness of each evaluation index to the worst case,for the weight of the jth index, an entropy method is adopted to determine the weight, which is specifically as follows:
(1) the method is characterized in that a ratio normalization method is adopted to normalize the original data construction matrix X, and the ratio normalization formula is as follows:
(2) calculating the entropy value of each index:
wherein,when p isijWhen equal to 0, let pij lnpij＝0
(3) Calculating a weight coefficient h of each index according to the entropy value of each index calculated in the step (2)jThe larger the calculated weight is, the larger the information quantity represented by the index is, the larger the function of the index on comprehensive evaluation is, and the calculation formula is as follows:
s2.4: calculating the degree of closeness R of each index and the optimal schemeiNamely, the comprehensive evaluation score of the student. The formula is as follows:wherein R is more than or equal to 0iNot more than 1, and Ri→ 1, a closer to 1 indicates a greater influence of the evaluation on the subject being evaluated;
s3: r calculated in S2iThe score of the final student is obtained by processing the following formula
Wherein R isiRepresents the comprehensive evaluation score of the student calculated in S2; t isiRepresents the academic age of the student; a is a fixed parameter, and a is 2, so as to avoid the condition that the academic age of the student is 0, which results in the denominator of the formula being 0; g is a gravity factor for pulling down the score of the student;
s4: establishing a teacher-student binary network by the teacher relation data in the S1; there are two kinds of nodes in the network, the instructor node tpAnd student node siEach node tpPossibly with one or more nodes siAre connected to each other, and siPossibly with one or more nodes tpAre connected. Let node tpIs given an initial score ofNode siIs given an initial score of
S5: for the bipartite network in S4, the instructor is scored by random walks, and the model is as follows:
s5.1: update the mentor's RW value according to the following formula:
in which RW(tp) Is the RW value, N, obtained by the instructor in the modeltIs the number of instructors in the model, p represents the number of instructors in the bipartite network, siIs the current instructor tpStudent, RW(s)i) Is the student siRW value in model, C(s)i) Is to guide the student siD is 0.85, C (t)p) Is a tutor tpThe number of students who have been instructed. As can be seen from this formula, the student's RW score is evenly assigned to his mentor.
S5.2: the student's score is updated according to the following formula:
in which RW(s)i) Is the RW value obtained by the student in the dichotomous network,is the student score calculated in S3, tpIs the leading teacher of the current student, RW (t)p) Is the instructor tpRw value, C (t) in a bipartite networkp) The number of students, C(s), guided by the instructori) To guide studentsiThe number of instructors. From this formula, it can be seen that the instructor's RW score is evenly assigned to his student.
S6: RW (t) calculated in S5i) The final instructor's score is obtained by processing according to the following formula
Wherein, RW (t)p) Representing the comprehensive evaluation score of the instructor calculated in S5;representing the academic age of the instructor.
The invention has the beneficial effects that: from the perspective of students, the invention provides a teacher influence evaluation method based on a teacher-student binary network. Different from the traditional evaluation of the influence of the scholars only according to single indexes such as the number of literary works, the number of cooperative works, the hindex and the like of the scholars, the students as important components of the output of the scholars play a certain role in the evaluation of the influence of the scholars, and the student influence evaluation method provides a basis for the guidance of the scholars, the evaluation of the influence of the scholars, the evaluation of rewards, the financing, the promotion and the like.
Drawings
Fig. 1 is a flowchart of a mentor influence evaluation method based on a mentor-student bipartite network.
Fig. 2 is a process diagram of a mentor influence evaluation method based on a mentor-student binary network.
Fig. 3 is a schematic diagram of an established instructor-student bipartite network.
Fig. 4 is a graph comparing the top ten results after multi-index comprehensive evaluation and addition of academic age adjustment to students with the results before they were not added to academic age adjustment.
FIG. 5 is a graph comparing the results of a mentor who randomly walks a mentor-student bipartite network and joins the top ten ranked after academic age adjustment with the results before they do not join academic age adjustment.
Detailed Description
A teacher influence evaluation method based on a teacher-student binary network comprises the following specific implementation steps:
s1: acquiring scholars data, data corresponding to papers and scholars, papers data, citation data, papers publication year data and periodical influence factor data from a Microsoft data set and a periodical influence factor data set provided by Web of Science;
the pretreatment comprises the following steps: 1. number of the theory: extracting student information from the student data, and extracting the quantity of the papers of the student and published papers from the data corresponding to the papers and the students; 2. the introduced amount is as follows: obtaining the total quoted amount of the student paper according to the quoted data; h-index: calculating the quoted amount of the published papers of the scholars according to the quoted data, and arranging the quoted amount from high to low, wherein when the nth paper is less than or equal to the quoted amount and the n +1 th paper is greater than the quoted amount, n is the h-index of the scholars; 4. academic age: determining the academic age of the scholars according to the publication year data of the papers by subtracting the publication year of the first paper from the latest year in the data records; 5. published papers journal impact factor: extracting corresponding information of the papers and periodicals in the paper data, extracting the influence factors of the periodicals where the papers are located corresponding to the influence factor data of the periodicals, corresponding the papers and the student ids through corresponding data of the papers and the students, taking out the paper of a journal factor TOP3 in the student's paper, and averaging the paper to represent the paper publication level of the student, wherein the average number of journal factors of all papers published by the student is not enough for three papers;
s2: scoring the indexes of the students in the S1 by using a multi-index comprehensive evaluation method;
s3: the comprehensive evaluation method of S2 includes the steps of:
s3.1: a normalized initial matrix is constructed. There are 142305 students to be evaluated, and each student has four indexes of h-index, quoted amount, number of papers and periodical factors, so the normalized matrix is:
s3.2: the optimal and worst case scenarios are determined by the following equations:
best mode solution Z-Is composed of the maximum value of each column of elements, and the formula is as follows:
the optimal scheme is as follows:
hindex：0.017342；papernumber：0.120618；citednumber：0.187061；factor：0.040827
the worst scheme is as follows:
Hindex：0.00000；papernumber：0.00038；citednumber：0.00000；factor：0.00000
s3.3: and calculating the closeness degree of each evaluation index to the optimal scheme and the worst scheme, wherein the formula is as follows:
whereinThe weight of j (j is 1,2,3,4) index is determined by adopting entropy method;
s3.4: calculating the degree of closeness R of each index and the optimal schemeiThe formula is as follows:
s3.3 and S3.4 gave the following results:
s4: for the entropy method determination weight in S3.3, the steps are as follows:
s4.1: the original matrix is normalized by a simple ratio normalization method,the results were:
s4.2: calculating the entropy value of each index:
the entropy results of the indexes are as follows:
h index: 0.977721, respectively; number of the theory: 0.944046, respectively; the introduced amount is as follows: 0.873898, respectively; journal impact factor: 0.956626
S4.3: calculating a weight coefficient of each index according to the entropy of each index calculated in S4.2, wherein the larger the calculated weight is, the larger the information quantity represented by the index is, the larger the function of the index on comprehensive evaluation is, and the calculation formula is as follows:
the result of each index weight coefficient is:
h index: 0.089942, respectively; number of the theory: 0.225886, respectively; the introduced amount is as follows: 0.509071, respectively; journal impact factor: 0.175102
S5: r calculated in S3iThe Score of the final student is obtained by processing according to the following formulaiTo prevent the score from being too small, here we will use RiMultiplying by 1000, and specifically analyzing specific problems;
the results obtained were:
s6: establishing a teacher-student binary network by the teacher relation data in the S1;
s7: and (4) bringing the final scores of the students calculated in the step (S5) into a teacher-student binary network, and scoring the teacher in a random walk mode, wherein the model is as follows:
s7.1: update the mentor's RW value according to the following formula:
s7.2: the student's score is updated according to the following formula:
s8: RW (t) calculated in S8i) The Score of the final instructor is obtained by processing according to the following formulat：
The results of S7 and S8 were compared as follows:

Claims (1)

1. a teacher influence evaluation method based on a teacher-student binary network is characterized by comprising the following steps of:
s1: obtaining effective data and carrying out data preprocessing;
the valid data comprises: the data of the students, the data corresponding to the papers and the students, the paper data, the citation data, the year of publication of the papers, the influence factor data of periodicals and the relationship data of teachers and students;
the pretreatment comprises the following steps: 1. number of the theory: extracting student information from the student data, and extracting the quantity of the papers of the student and published papers from the data corresponding to the papers and the students; 2. the introduced amount is as follows: obtaining the total quoted amount of the student paper according to the quoted data; h-index: calculating the quoted amount of the published papers of the scholars according to the quoted data, and arranging the quoted amount from high to low, wherein when the nth paper is less than or equal to the quoted amount and the n +1 th paper is greater than the quoted amount, n is the h-index of the scholars; 4. academic age: determining the academic age of the scholars according to the publication year data of the papers by subtracting the publication year of the first paper from the latest year in the data records; 5. published papers journal impact factor: extracting corresponding information of the papers and periodicals in the paper data, extracting the influence factors of the periodicals where the papers are located corresponding to the influence factor data of the periodicals, corresponding the papers and the student ids through corresponding data of the papers and the students, taking out the paper of a journal factor TOP3 in the student's paper, and averaging the paper to represent the paper publication level of the student, wherein the average number of journal factors of all papers published by the student is not enough for three papers;
s2: and (3) scoring the paper number, the quoted amount, the h-index and the published paper journal influence factor of the scholars in the S1 by using a multi-index comprehensive evaluation method, wherein the method specifically comprises the following steps:
s2.1: constructing a normalized initial matrix; the method is characterized in that n students needing to be evaluated are arranged, each student has four indexes of h-index, quoted quantity, number of papers and published papers and periodicals influence factor, and then the original data construction matrix is as follows:
wherein x isn1、xn2、xn3、xn4Respectively representing h-index, quoted amount, number of papers and periodicals of the nth student, and influence factor indexes of published papers and periodicals;
constructing a weighting matrix, and carrying out vector normalization on the attributes, namely dividing each datum by the norm of the current column vector, wherein the formula is as follows:
wherein x isijJ index representing the ith student; i is the ith student and takes values from 1 to n, j is an evaluation index and takes values from 1 to 4;
obtaining a normalized normalization matrix Z:
s2.2: determination of the optimum Z+And worst Z-Two schemes are adopted;
best mode solution Z+Is composed of the maximum value of each column of elements, and the formula is as follows:
worst case scenario Z-Is composed of the maximum value of each column of elements, and the formula is as follows:
s2.3: and calculating the closeness degree of each evaluation index to the optimal scheme and the worst scheme, wherein the formula is as follows:
wherein,the degree of closeness of each evaluation index to the optimal solution is represented,indicates the degree of closeness of each evaluation index to the worst case,for the weight of the jth index, an entropy method is adopted to determine the weight, which is specifically as follows:
(1) the method is characterized in that a ratio normalization method is adopted to normalize the original data construction matrix X, and the ratio normalization formula is as follows:
(2) calculating the entropy value of each index:
wherein,when p isijWhen equal to 0, let pijlnpij＝0
(3) Calculating a weight coefficient h of each index according to the entropy value of each index calculated in the step (2)jThe larger the calculated weight is, the larger the information quantity represented by the index is, the larger the function of the index on comprehensive evaluation is, and the calculation formula is as follows:
s2.4: calculating the degree of closeness R of each index and the optimal schemeiNamely, the comprehensive evaluation score of the student; the formula is as follows:wherein R is more than or equal to 0iNot more than 1, and Ri→ 1, a closer to 1 indicates a greater influence of the evaluation on the subject being evaluated;
s3: r calculated in S2iThe score of the final student is obtained by processing the following formula
Wherein R isiRepresents the comprehensive evaluation score of the student calculated in S2; t isiRepresents the academic age of the student; a is a fixed parameter, and a is 2, so as to avoid the condition that the academic age of the student is 0, which results in the denominator of the formula being 0; g is the cause of gravityA child for pulling down the score of the student;
s4: establishing a teacher-student binary network by the teacher relation data in the S1; there are two kinds of nodes in the network, the instructor node tpAnd student node siEach node tpPossibly with one or more nodes siAre connected to each other, and siPossibly with one or more nodes tpConnecting; let node tpIs given an initial score ofNode siIs given an initial score of
S5: for the bipartite network in S4, the instructor is scored by random walks, and the model is as follows:
s5.1: update the mentor's RW value according to the following formula:
in which RW (t)p) Is the RW value, N, obtained by the instructor in the modeltIs the number of instructors in the model, p represents the number of instructors in the bipartite network, siIs the current instructor tpStudent, RW(s)i) Is the student siRW value in model, C(s)i) Is to guide the student siD is 0.85, C (t)p) Is a tutor tpThe number of students who have been instructed; as can be seen from this formula, the student's RW score is evenly assigned to his mentor;
s5.2: the student's score is updated according to the following formula:
in which RW(s)i) Is the RW value obtained by the student in the dichotomous network,is the student score calculated in S3, tpIs the leading teacher of the current student, RW (t)p) Is the instructor tpRw value, C (t) in a bipartite networkp) The number of students, C(s), guided by the instructori) To guide studentsiThe number of instructors; from this formula, it can be seen that the instructor's RW score is evenly assigned to his student;
s6: RW (t) calculated in S5i) The final instructor's score is obtained by processing according to the following formula
Wherein, RW (t)p) Representing the comprehensive evaluation score of the instructor calculated in S5;representing the academic age of the instructor.
CN201910485980.1A 2019-06-05 2019-06-05 A kind of tutor's influence power appraisal procedure based on two subnetwork of tutor-student Withdrawn CN110309322A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910485980.1A CN110309322A (en) 2019-06-05 2019-06-05 A kind of tutor's influence power appraisal procedure based on two subnetwork of tutor-student

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910485980.1A CN110309322A (en) 2019-06-05 2019-06-05 A kind of tutor's influence power appraisal procedure based on two subnetwork of tutor-student

Publications (1)

Publication Number Publication Date
CN110309322A true CN110309322A (en) 2019-10-08

Family

ID=68075054

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910485980.1A Withdrawn CN110309322A (en) 2019-06-05 2019-06-05 A kind of tutor's influence power appraisal procedure based on two subnetwork of tutor-student

Country Status (1)

Country Link
CN (1) CN110309322A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110991924A (en) * 2019-12-13 2020-04-10 电子科技大学 Structural equation model-based high-level thesis publication number influence factor evaluation method
CN111027868A (en) * 2019-12-13 2020-04-17 电子科技大学 Structural equation model-based academic dissertation quality influence factor evaluation method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110991924A (en) * 2019-12-13 2020-04-10 电子科技大学 Structural equation model-based high-level thesis publication number influence factor evaluation method
CN111027868A (en) * 2019-12-13 2020-04-17 电子科技大学 Structural equation model-based academic dissertation quality influence factor evaluation method

Similar Documents

Publication Publication Date Title
CN108804689B (en) Question-answering platform-oriented label recommendation method integrating user hidden connection relation
CN103886054B (en) Personalization recommendation system and method of network teaching resources
CN111813921A (en) Topic recommendation method, electronic device and computer-readable storage medium
Gao Establishment of college English teachers’ teaching ability evaluation based on Clementine data mining
CN113851020A (en) Self-adaptive learning platform based on knowledge graph
Intisar et al. Cluster analysis to estimate the difficulty of programming problems
CN114201684A (en) Knowledge graph-based adaptive learning resource recommendation method and system
CN110309322A (en) A kind of tutor's influence power appraisal procedure based on two subnetwork of tutor-student
Chan et al. Leveraging social connections to improve peer assessment in MOOCs
Su et al. A physical education teacher motivation from the self-evaluation framework
Song et al. Pluggable reputation systems for peer review: A web-service approach
CN118469774A (en) Course recommendation method based on attention mechanism and knowledge graph
Siblini et al. Using a weighted semantic network for lexical semantic relatedness
CN110070232A (en) The method for introducing the various dimensions prediction student performance of teachers ' teaching style
Cuéllar-Rojas et al. Bibliometric analysis and systematic literature review of the intelligent tutoring systems
Kang et al. The feasibility of practical vocational education in higher education institutions
Zhang Construction and Application of Physical Education Classroom Teaching Model Integrating MOOC and Flipped Classroom
Grivokostopoulou et al. Estimating the difficulty of exercises on search algorithms using a neuro-fuzzy approach
Can et al. Using mathematics in teaching science self-efficacy scale–umsss: a validity and reliability study
CN110826590B (en) Learner relationship strength measurement method and device integrating learning characteristics and learning network structural characteristics
Aran et al. Analyzing the views of teachers and prospective teachers on information and communication technology via descriptive data mining
Lintang et al. Implementation of the simple multi attribute ranking technique method as a model for decision making in determining the talents and interests of children in continuing education
CN108596461B (en) Intelligent system and method for training effect evaluation
CN110990583A (en) Course map construction method based on network embedding
Susliansyah et al. Decision Making on Student Academic Achievement Assessment Using the Topsis Method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication

Application publication date: 20191008

WW01 Invention patent application withdrawn after publication