Skip to content
BY-NC-ND 3.0 license Open Access Published by De Gruyter Open Access June 16, 2017

Fuzzy comprehensive evaluation model of interuniversity collaborative learning based on network

  • Ma Wenhui EMAIL logo and Wang Yu
From the journal Open Physics

Abstract

Learning evaluation is an effective method, which plays an important role in the network education evaluation system. But most of the current network learning evaluation methods still use traditional university education evaluation system, which do not take into account of web-based learning characteristics, and they are difficult to fit the rapid development of interuniversity collaborative learning based on network. Fuzzy comprehensive evaluation method is used to evaluate interuniversity collaborative learning based on the combination of fuzzy theory and analytic hierarchy process. Analytic hierarchy process is used to determine the weight of evaluation factors of each layer and to carry out the consistency check. According to the fuzzy comprehensive evaluation method, we establish interuniversity collaborative learning evaluation mathematical model. The proposed scheme provides a new thought for interuniversity collaborative learning evaluation based on network.

PACS: 01.40.Ha

1 Introduction

The enhancement of the higher education quality needs teaching reform and innovation. The development of information technology has provided the powerful support for the way to improve study. Collaborative study of interuniversity based on network is a new exploration of high education reform [1]. It is one of the most important interuniversity collaborative aspect among universities, a new learning method to promote the teaching quality and the students’ full development in teaching domain, and an extension of web-collaborative study without changing the present teaching mode [2]. It is also a special practice in a collaborative study, which enlarges the collaborative objects and enables the learners to build broader knowledge foundation and have even larger mutual learning space [3].

In the late 20th century, information technology represented by a computer got rapid development. Multimedia technology and network technology further promote the human purposeful interaction and collaboration between social groups. Computer supported cooperative work provides a new collaborative learning enlightenment. Computer supported collaborative learning (CSCL) uses computer technology, especially multimedia and network to assist learning [4]. This is a cross research field based on a collaborative learning and computer supported cooperative work. In CSCL research practice, there are many excellent learning support platforms based on network environment. Web-based collaborative learning is an extension of the CSCL, which refers to the use of Internet network technology to support collaborative learning and is also called WebCL abroad [5]. In this sense, WebCL is a subset of CSCL. It includes E-mail, multimedia conference system, collaborative document editing, remote collaborative learning system, etc [6, 7]. The inter-university collaborative learning based on network is a realization of CSCL on network platform, so that the theory and principles of CSCL can completely guide the practice of the present study.

Interuniversity collaborative learning based on network uses Internet to perform common curriculum learning activities and focuses on the difference between various university learning aspects [8]. It learns this difference and uses it in the study process, thus deepening on the understanding of knowledge and mutual understanding, or providing comprehensive experiment project development [9]. Through collaborative team efforts, it jointly solves the problem similar to the real situation. In the learning activities with these characteristics, partners who participate in the learning, show a kind of coordinate, co-operation relation, which is called the interuniversity collaborative learning based on network.

Yao Hui-lin [10] investigated cross-disciplinary collaborative teaching model for specific courses. Y. Liu [11] analyzed educational evaluation results based on decision tree algorithm. H. Xiaorong [12] presented network-course learning effect evaluation model based on three-layer Bayesian network. A web-based framework for user-centred evaluation of end-user experience in adaptive and personalized E-Learning systems was proposed by C. Mulwa [13]. Y. Bin [14] put forward a kind of network course evaluation method based on BP neural network and the CELTS-22. Evaluation of an online continuing education program from the perspective of new graduate nurses is presented by S. Karaman [15]. Effects of online college student’s Internet self-efficacy on learning motivation and performance is investigated by C. S. Chang [16]. In the next section, interuniversity collaborative learning network model is put forward. In section 3, fuzzy comprehensive evaluation for network based interuniversity collaborative learning is investigated. In the end, some conclusions are given.

2 Interuniversity collaborative learning network model

Web-based interuniversity collaborative learning platform is actually a comprehensive teaching system based on Internet. The construction of the system can use C/S (Client/Server) mode and B/S (Browser/Server) mode. C/S mode needs to install the client software and server software, so this system is used on the fixed machine [15]. A machine that allows students to access the Internet, which is not fixed, can be a computer room, a dormitory, Internet cafes, and so on. Although C/S mode is powerful, having security access and fast network communication, it is not applicable in this study [16] and B/S mode does not need specific client program, it only needs to use the browser. We can request the WEB server via HTTP, which is convenient and flexible, thus it is widely used at present.

The design of the B/S mode finally ascribes to WEB site design. Interuniversity collaborative learning based on network site has three layers of architecture, which are: user layer, application layer, and data service layer. Interuniversity collaborative learning network model is shown in Figure 1. The user uses the WEB browser and sends the request to a WEB server. The server executes the program and returns the corresponding different permissions of the user interface to the user. The application layer is a part of the developers to realize various functions for users. It is located on the server side, and accepts all kinds of requests from the browser, executes program, or performs the operation in connection with the database. Then the results are sent back to the user [17]. This level of platform highlights the use of particular intelligent information. It records the user’s learning process, and reminds learners what to do according to certain rules. The data service layer provides data support for the application layer. It records a large amount of data information such as the learners, teachers, learning process and so on [18]. It is used to query, update, and delete through the interface between database and the application.

Figure 1 Interuniversity collaborative learning network model
Figure 1

Interuniversity collaborative learning network model

3 Fuzzy comprehensive evaluation for network based interuniversity collaborative learning

Fuzzy comprehensive evaluation adopts fuzzy mathematical theory to obtain quantitative evaluation result in view of the complexity of teaching evaluation object and fuzziness of the evaluation index. The evaluation result has certain objectivity. The process of fuzzy comprehensive evaluation is shown in Figure 2.

Figure 2 Fuzzy comprehensive evaluation for network based interuniversity collaborative learning
Figure 2

Fuzzy comprehensive evaluation for network based interuniversity collaborative learning

Step 1. Set up evaluation factor set

  1. The first level of evaluation factor set U = (U1, U2, U3, U4) is set up, which represents initial state, learning attitude, exchange and cooperation, and resource utilization.

  2. Set up the second level of evaluation factor set U1 = (u11, u12, u13, u14), U2 = (u21, u22,. . ., u29), U3 = (u31,u32,. . ., u37), U4 = (u41, u42,. . ., u46).

Step 2. Determine the evaluation set. V = (v1, v2,..., vn), vi(i = 1, 2,..., n) represents all possible evaluation result.

We select five grades as evaluation level of student network learning, which is excellent, good, medium, pass, and fail. The corresponding evaluation sets is V=excellent, good, medium, pass, fail. V = {v1, v2, v3, v4, v5}. The score of v1 is from 90 to 100, the score of v2 is from 80 to 90, the score of v3 is from 70 to 80, the score of v4 is from 60 to 70 and the score of v5 is from 0 to 60.

Step 3. Determine weight of evaluation index

Weight is used to measure the role and status of an index in the whole learning evaluation index system. After the indexes are established, we consider its relative importance in the index system. If weight of an index is larger, its value change has large impact on the evaluation results. For different evaluation results, we should scientifically determine the index weight to reasonably carry out the analysis and evaluation. Because, there may be many evaluation indexes, in the selection of index, a kind of attribute reduction method based on difference matrix [19] is adopted to choose the most suitable indexes. The difference matrix is mij. S = (U, CD, V, f) represents the information system decision table, Urepresents comment domain, V represents set of attribute value, f : U × AV is an information function, C and D represents condition attribute and decision attribute respectively.

mij={aC:f(xi,a)f(xj,a)}, when f(xi,D)f(xj,D),otherwise

Firstly, difference matrix of the decision table is worked out. Secondly, the weight value w(ak) of each attribute ak is calculated. We also work out the number of element containing ak in the difference matrix labeled as card(ak). R ← ∅, W ← 0. Thirdly, for k from 1 to n that represents the number of attribute, if w(ak) > W, Ww(ak). If w(ak) = W and card(ak) is larger Ww(ak). Fourthly, RR ∪ {ak} and the element containing ak in the difference matrix is deleted. Fifthly, if the difference matrix is not empty, calculate the each left w(ak) and turn to step 3.

Analytic hierarchy process combines the expert’s experience knowledge with mathematical method. When judging matrix is established, the two comparing methods are used, which greatly reduce the uncertainty factors. According to 1 to 9 scale method, index relative important degree value is assigned and comparative value can be obtained. Based on comparative value, judgment matrix can be obtained. If there are n elements, we obtain a matrix of n x n after the two comparing as shown in Table 1.

Table 1

Comparative table

A1A2A3An
A1  1a12a13a1n
A2a21  1a23a2n
A3a31a32  1a3n
 ⋯ ⋯ ⋯ ⋯ ⋱ ⋯
Anan1an2an3 ⋯   1

Suppose the weight factor vector of evaluation set is A = (a1, a2, . . .,an), ai represents the weight of evaluation factor ui in the total evaluation factor. ai ≥ 0, Σ ai = 1. According to the idea of AHP method, we develop the two comparative matrix of network learning behavior evaluation factors by means of expert meeting. The weight of the first level of index is described as follows.

  1. Calculate the sum of each column.

  2. Each item in the matrix is divided by its corresponding column sum, then the standard two comparative matrix is obtained.

  3. Calculate the arithmetic average of each row of the standard two comparative matrix and this average value is called the weight. It is impossible to judge exactly right in the two compared matrices, sometimes there will be error or even contradiction. The higher the judgment order, the more difficult the determination is, and the deviation will increase. In fact, almost all of the two compared matrices have a certain degree of inconsistency. In order to solve the problem of the consistency, the AHP provides a way to measure the degree of consistency. If the degree of consistency cannot meet the requirements, we should review and modify the two compared matrices. Judgment matrix and weight of index in the first level is shown in Table 2.

Table 2

Judgment matrix and weight of index in the first level

Uu1u2u3u4ai
u111/31/71/50.057
u2311/41/30.131
u374130.540
u4531/310.272

CI=λmaxnn1 is defined as consistency index, n represents the number of compared index and λmax represents maximum characteristic root of judgment matrix. The weighted vector is [0.232, 0.528, 2.279, 1.130]. λmax = (0.232/0.057 + 0.528/0.131 + 2.279/0.540 + 1.130/0.272)/4 = 4.119

CR = 0.044 < 0.1 means that judgment matrix has the characteristic of consistency and the weight is reasonable. The second level of index and corresponding weight is worked out in the same way. 16 teachers evaluate one student comprehensively, the obtained survey statistics is shown in Table 3.

Table 3

The survey statistics table of interuniversity collaborative learning evaluation

the

first

level
weightthe

second

level
weightEvaluation level
u10.057u110.54836421
u120.28126611
u130.05628420
u140.11526431
u20.131u210.17736322
u220.17725450
u230.03415640
u240.03436421
u250.09514632
u260.03417521
u270.09515451
u280.17756311
u290.17767300
u30.540u310.24645610
u320.14203454
u330.14225432
u340.24617521
u350.04136520
u360.04125342
u370.14245610
u40.272u410.03702464
u420.22456311
u430.08734621
u440.08745421
u450.47817431
u460.08715640

u11 represents whether the learners current level has the condition for acquiring new learning content. u12 represents whether the learners can adapt to study under interuniversity collaborative learning. u13 represents learning condition of the learner. u14 represents learning motivation. u21 represents the case whether a student can complete learning task according to curriculum plane. u22 represents the case in which a student takes part in network teaching activities actively. u23 represents the case in which a students is likely to interact with other partners. u24 represents the case in which a students can complete some challenging tasks. u25 represents the autonomous learning ability. u26 represents the autonomous learning note. u27 represents a student, who can take part in the necessary tutorial. u28 represents a student, who can timely submit course assignments. u29 represents the case in which a student has been cheating. u31 represents the case in which a student usually asks a teacher. u32 represents the case in which a student often announces opinion corresponding to curriculum in the discussion area. u33 represents the case in which a student can extract useful information from others opinion. u34 represents the case in which a student often talk questions with teachers or students. u35 represents the case in which a student proposes constructive advice for teacher’s work. u36 represents the case in which a student can answer the questions timely. u37 represents the case in which a student can complete subject with other actively learning partners. u41 represents the case in which a student uploads valuable resource on the system platform. u42 represents the case in which a student queries information in the resource library. u43 represents the case in which a student often makes notes. u44 represents the case in which a student can choose all kinds of resources to study. u45 represents the case in which a student has strong information ability. u46 represents the case in which a student can use his knowledge to solve actual problem.

Process of network based interuniversity collaborative learning evaluation is shown in Figure 3. According to Table 3, we can obtain fuzzy evaluation matrix of the second level of index,R1(2),R2(2),R3(2)andR4(2). According to fuzzy evaluation matrix Ri(2)(i=1,2,,n) and corresponding weight set Wi(2), we obtain evaluation result set of each factor in the second level of index.

Ai(2)=(Wi(2))TRi(2)
Figure 3 Process of network based interuniversity collaborative learning evaluation
Figure 3

Process of network based interuniversity collaborative learning evaluation

Then we get fuzzy evaluation matrix of the first level of index R(1)=(A1(2),A2(2),A3(2),A4(2))T. According to A(1) = (W(1))T· R(1), we work out the comprehensive evaluation result set for the student.

After normalization, A(1) = (0.149, 0.342, 0.282, 0.159, 0.068). Then weighted average method is used to determine the comprehensive evaluation results. We need to assign level parameter to each evaluation level, and then level parameter matrix is obtained. The fuzzy comprehensive evaluation result is S = A(1) · VT. V = (90, 80, 70, 60, 50). S = A(1) · VT = (0.149, 0.342, 0.282, 0.159, 0.068) · VT = 73.

4 Conclusion

Highly developed modern education technology and widely applied modern information technology made education via internet an important teaching method and teaching system. Interuniversity collaborative learning based on network as a new type mode of network education, and its evaluation is paid more and more attention. There are few researches in evaluation of interuniversity collaborative learning based on network. Most of them neglect personality of collaborative learning; and they do not form an integrated index system, the evaluation is not scientific and all-round. Resolving these problems is a long time research. A reasonable evaluation method of interuniversity collaborative learning based on network is put forward, which includes process’s evaluation, result’s evaluation, quantitative evaluation and qualitative evaluation. It is able to provide a new thought for interuniversity collaborative learning evaluation based on network.

Acknowledgement

This work is supported by network based diversified interuniversity collaboration promoting effective learning research (SFGG-201329).

References

[1] Collazos C.A., Guerrero L.A., Pino J.A., Ochoa S.F., A method for evaluating computer-supported collaborative learning processes, International Journal of Computer Application in Technology, 2004, 19(3), 151-161.10.1504/IJCAT.2004.004044Search in Google Scholar

[2] Israel J., Aiken R. M., Supporting Collaborative Learning With An Intelligent Web-Based System, IJ Artificial Intelligence in Education, 2007, 17(1), 3-40.Search in Google Scholar

[3] Dikkers A.G., Whiteside A.L., Lewis S., Virtual High School Teacher and Student Reactions to the Social Presence Model, Journal of Interactive Online Learning, 2013,12(3):156-170.Search in Google Scholar

[4] Li B., You N., Du Y.H., LAV Path Planning by Enhanced Fireworks Algorithm on Prior Knowledge, Applied Mathematics and Nonlinear Sciences, 2016, 1(1),65-78.10.21042/AMNS.2016.1.00006Search in Google Scholar

[5] Marín F., Alhama F., Solano J., Meroño P.A., Sánchez J.F., Multiscale Simulations of Dry Friction Using Network Simulation Method, Applied Mathematics and Nonlinear Sciences, 2016, 1(2), 559-580.10.21042/AMNS.2016.2.00044Search in Google Scholar

[6] Goda Y., et al., Conversation with a Chatbot before an Online EFL Group Discussion and the Effects on Critical Thinking, Information and Systems in Education, 2014,13(1), 1-7.10.12937/ejsise.13.1Search in Google Scholar

[7] Clariana R.N., Engelmann T., Yu W., Using Centrality of Concept Maps as a Measure of Problem Space States in Computer- Supported Collaborative Problem Solving, Educational Technology Research and Development, 2013, 61(3), 423-442.10.1007/s11423-013-9293-6Search in Google Scholar

[8] PIP J.R., Yudelson M., Koedinger K.R., A Measurement Model of Microgenetic Transfer for Improving Instructional Outcomes, International Journal of Artificial Intelligence in Education, 2015, 25(3):346-37910.1007/s40593-015-0039-ySearch in Google Scholar

[9] Jing-ying Z., Hai G., Ling-fen W., Hai-yu S., Web-based collaborative learning & practice- taking software analysis and design course for instance, Journal of Dalian Nationalities University, 2009, 1, 92-94.Search in Google Scholar

[10] Hui-lin Y., Lian-feng Y., The study of cross-disciplinary collaborative teaching model for specific courses”, Education for Chinese After-school, 2009, 9,19-20.Search in Google Scholar

[11] Liu Y., Yu J. L., A Qualitative Analysis and Statistics of Educational Evaluation Results Based on Decision Tree Algorithm, Advanced Materials Research, 2012, 433, 319-323.10.4028/www.scientific.net/AMR.433-440.319Search in Google Scholar

[12] Matsuda N., Cohen W.W., Koedinger K.R., Teaching the Teacher: Tutoring SimStudent Leads to More Effective Cognitive Tutor Authoring, International Journal of Artificial Intelligence in Education, 2015, 25(1):1-34.10.1007/s40593-014-0020-1Search in Google Scholar

[13] Chughtai M.W., Ghani I., Selamat A., Jeong S.R., Goal-Based Framework for Multi-User Personalized Similarities in e-Learning Scenarios, International Journal of Technology & Education Marketing 2014, 4(1):1-14.10.4018/ijtem.2014010101Search in Google Scholar

[14] Bin Y., Zhigui L., Network Course Evaluation Study Based on BP Neural Network and the CELTS-22, Microcomputer and applications, 2009, 20, 115-118.Search in Google Scholar

[15] Karaman S., KucukS., Aydemir M., Evaluation of an online continuing education program from the perspective of new graduate nurses, Nurse education today, 2014, 34(5), 836-841.10.1016/j.nedt.2013.09.006Search in Google Scholar PubMed

[16] Chang C. S., Liu E. Z. F., Sung H. Y., Lin C. H., Chen N. S., Cheng S. S., Effects of online college student’s Internet self-efficacy on learning motivation and performance, Innovations in education and teaching international, 2014, 51(4), 366-377.10.1080/14703297.2013.771429Search in Google Scholar

[17] Zhen H., Yun H., Model of Learning Design and Research of Network Learning Behavior Analysis Platform, Software Guide, 2010, 3, 195-197.Search in Google Scholar

[18] Matheson R., Wilkinson S., Gilhooly E., Promoting critical thinking and collaborative working through assessment: combining patchwork text and online discussion boards, Innovations in Education and Teaching International, 2012, 49, 257-267.10.1080/14703297.2012.703023Search in Google Scholar

[19] Bhatt R.B., Gopal M., On fuzzy-rough sets approach to feature selection, Pattern Recognition Letters, 2005, 26(7), 965-975.10.1016/j.patrec.2004.09.044Search in Google Scholar

Received: 2016-12-2
Accepted: 2017-1-11
Published Online: 2017-6-16

© 2017 Ma Wenhui and Wang Yu

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Downloaded on 28.3.2024 from https://www.degruyter.com/document/doi/10.1515/phys-2017-0047/html
Scroll to top button