AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
In the fuzzy tree-structured learning activity model, a fuzzy category tree is defined to specify the categories that each learning activity roughly belongs to, and the fuzzy category similarity measure is developed to evaluate the semantic similarity between learning activities

A Fuzzy Tree Matching-based Personalized e-Learning Recommender System

Fuzzy Systems, IEEE Transactions  , no. 99 (2015): 1

Cited by: 71|Views2
EI WOS

Abstract

—The rapid development of e-learning systems provides learners with great opportunities to access learning activities online, and this greatly supports and enhances learning practices. However, an issue reduces the success of application of e-learning systems: too many learning activities (such as various leaning materials, subjects, and ...More

Code:

Data:

0
Introduction
  • E-LEARNING systems are becoming increasingly popular in educational establishments due to the development of web-based information and communication technologies.
  • The study presented in this paper is innovative since it is the first to use fuzzy tree-structured data model to model learning activities and learner profiles.
  • The fuzzy tree-structured learning activity model and learner profile model are presented in Sections IV and V, respectively.
Highlights
  • E-LEARNING systems are becoming increasingly popular in educational establishments due to the development of web-based information and communication technologies
  • To deal with the above special requirements in e-learning recommender systems, this study proposes a fuzzy tree matching-based hybrid recommendation approach
  • This paper has outlined the development of a fuzzy tree matching-based hybrid recommendation approach for an elearning system
  • A fuzzy tree similarity measure is presented to evaluate the similarity between learning activities or learners
  • In the fuzzy tree-structured learning activity model, a fuzzy category tree is defined to specify the categories that each learning activity roughly belongs to, and the fuzzy category similarity measure is developed to evaluate the semantic similarity between learning activities
  • In the fuzzy tree- [13] structured learner profile model, a fuzzy required category tree is defined for learners to express their requirements
Results
  • Development of the fuzzy tree matching-based hybrid recommendation approach for learning activities is presented in Section VI.
  • This section will define a fuzzy tree-structured data model, which is used to represent tree-structured learning activities or learner profiles.
  • Similar to the learning activity tree, the learner profile tree nodes are assigned a label attribute and a category attribute, which are used to calculate the node concept similarity.
  • This section outlines the development of a fuzzy tree matching-based hybrid recommendation approach for learning activities.
  • G. Step 7: Generate the Recommendations: The predicted ratings of all the alternative learning activities of learner are calculated.
  • The authors present the performance evaluation results of the proposed fuzzy tree matching-based hybrid recommendation approach, which includes the experiment design and the result analysis.
  • This section outlines the design and implementation of the fuzzy tree matching-based e-learning recommender system (TeLRS) prototype according to the proposed recommendation approach.
  • Fig. 13 shows the profile editing page of Learner 4, in which the ea e required categories construct a tree structure and the required levels are expressed by linguistic terms.
  • 2) The matching degrees of the alternative learning activities to the learners are calculated, as shown in Table III.
  • The developed fuzzy tree matching-based personalized elearning recommender system has the following six features: (1) tree structured data -- it deals with tree structured learning activities and learner profiles; (2) fuzzy learning activity -- it handles the fuzzy categories of learning activities; (3) fuzzy learner requirement -- a d e ea e f e ement; (4) pedagogical constraint -- it considers the pedagogical constraints; (5) matching knowledge -- it utilizes the learning requirement matching knowledge; (6) semantic and CF
  • It can be seen from Table VIII that compared with other elearning recommender systems, the developed TeLRS can deal with more complex data in real world e-learning applications, such as tree-structured data and fuzzy data, and it fully utilizes the domain knowledge in e-learning area.
Conclusion
  • The approach develops both a fuzzy treestructured learning activity model and a fuzzy tree-structured learner profile model.
  • A fuzzy tree similarity measure is presented to evaluate the similarity between learning activities or learners.
  • The recommendation approach takes advantage of both the CF and [14]
Summary
  • E-LEARNING systems are becoming increasingly popular in educational establishments due to the development of web-based information and communication technologies.
  • The study presented in this paper is innovative since it is the first to use fuzzy tree-structured data model to model learning activities and learner profiles.
  • The fuzzy tree-structured learning activity model and learner profile model are presented in Sections IV and V, respectively.
  • Development of the fuzzy tree matching-based hybrid recommendation approach for learning activities is presented in Section VI.
  • This section will define a fuzzy tree-structured data model, which is used to represent tree-structured learning activities or learner profiles.
  • Similar to the learning activity tree, the learner profile tree nodes are assigned a label attribute and a category attribute, which are used to calculate the node concept similarity.
  • This section outlines the development of a fuzzy tree matching-based hybrid recommendation approach for learning activities.
  • G. Step 7: Generate the Recommendations: The predicted ratings of all the alternative learning activities of learner are calculated.
  • The authors present the performance evaluation results of the proposed fuzzy tree matching-based hybrid recommendation approach, which includes the experiment design and the result analysis.
  • This section outlines the design and implementation of the fuzzy tree matching-based e-learning recommender system (TeLRS) prototype according to the proposed recommendation approach.
  • Fig. 13 shows the profile editing page of Learner 4, in which the ea e required categories construct a tree structure and the required levels are expressed by linguistic terms.
  • 2) The matching degrees of the alternative learning activities to the learners are calculated, as shown in Table III.
  • The developed fuzzy tree matching-based personalized elearning recommender system has the following six features: (1) tree structured data -- it deals with tree structured learning activities and learner profiles; (2) fuzzy learning activity -- it handles the fuzzy categories of learning activities; (3) fuzzy learner requirement -- a d e ea e f e ement; (4) pedagogical constraint -- it considers the pedagogical constraints; (5) matching knowledge -- it utilizes the learning requirement matching knowledge; (6) semantic and CF
  • It can be seen from Table VIII that compared with other elearning recommender systems, the developed TeLRS can deal with more complex data in real world e-learning applications, such as tree-structured data and fuzzy data, and it fully utilizes the domain knowledge in e-learning area.
  • The approach develops both a fuzzy treestructured learning activity model and a fuzzy tree-structured learner profile model.
  • A fuzzy tree similarity measure is presented to evaluate the similarity between learning activities or learners.
  • The recommendation approach takes advantage of both the CF and [14]
Tables
  • Table1: LINGUISTIC TERMS AND RELATED TRIANGULAR FUZZY NUMBERS
  • Table2: THE CF SIMILARITY BETWEEN LEARNERS
  • Table3: LEARNER-SUBJECT RATING MATRIX
  • Table4: THE SEMANTIC SIMILARITY BETWEEN LEARNERS
  • Table5: THE TOTAL SIMILARITY BETWEEN LEARNERS
  • Table6: THE MATCHING DEGREES OF THE LEARNING ACTIVITIES TO THE
  • Table7: THE PREDICTED RATINGS
Download tables as Excel
Related work
  • In this section, the related works on recommendation approaches and e-learning recommender systems are reviewed.

    A. Recommendation Approaches

    Recommendation techniques have attracted much attention and many recommendation approaches have been proposed. In general, the most commonly used three recommendation approaches are collaborative filtering (CF), content-based (CB) and knowledge-based (KB) techniques [19]. The CF technique helps people make choices based on the opinions of other people who share similar interests [20]. It can be further divided into user-based and item-based CF approaches. CB techniques recommend items that are similar to those previously preferred by a specific user [21]. KB techniques offer items to users based on knowledge about the users and items [22]. Each technique has its limitations, such as the item content dependency problem and over-specialization problem for CB [9, 21]; and the cold start and sparsity problems for CF [9]. To gain higher performance and avoid the drawbacks of the typical recommendation approaches, a hybrid recommendation approach can be developed by combining the best features of two or more recommendation approaches into one hybrid approach [23]. A variety of recommendation techniques, such as data mining [24, 25], agents [26] and reasoning, have been developed and applied into recommender systems [27, 28]. Many advanced recommendation approaches, such as social network-based recommender systems [29], fuzzy recommender systems [11, 30], context aware-based recommender systems [31] and group recommender systems [32], have also been proposed recently.
Funding
  • This work was supported in part by the Australian Research Council (ARC) under discovery grant DP110103733
Study subjects and analysis
users: 2113
Therefore, without loss of generality, the MovieLens dataset was used in this experiment. There are 2113 users in the dataset, and each user rated at least 20 movies. There are 20 movie genres in the MovieLens dataset, including Action, Adventure, Animation, Children, Comedy, Crime, Documentary, Drama, Fantasy, Film-Noir, Horror, IMAX, Musical, Mystery, Romance, Sci-Fi, Short, Thriller, War and Western

kinds of users: 3
The application in the web server contains three layers: the presentation layer, business logic layer and data access layer. The presentation layer is responsible for generating the requested web pages and handling the user interface logic and events for the three kinds of users. The business logic layer realizes the business services and the core recommendation algorithm

learners: 5
A Case Study. In the e-learning recommender system, there are five learners (Lea e 1, , Lea e 5) a d e b ec (S1-. Business Intelligence, , S8-Business Process Design)

Reference
  • recommender systems for learners in lifelong learning networks: the requirements, techniques and model," International Journal of
    Google ScholarLocate open access versionFindings
  • Learning Technology, vol. 3, pp. 404-423, 2008.
    Google ScholarFindings
  • O. R. Za aeadJ. L, "Web a e f a be e ebbased learning environment," in Proceedings of Conference on
    Google ScholarLocate open access versionFindings
  • Advanced Technology for Education, 2001, pp. 60-64.
    Google ScholarFindings
  • J. Lu, "Personalized e-learning material recommender system," in Proceedings of the 2nd International Conference on Information
    Google ScholarLocate open access versionFindings
  • Technology for Application (ICITA 2004), 2004, pp. 374-379.
    Google ScholarFindings
  • M. Salehi and I. N. Kamalabadi, "Hybrid recommendation approach for learning material based on sequential pattern of the acce ed aeaade ea e efe e ce ee," Knowledge-Based Systems, vol. 48, pp. 57-69, 2013.
    Google ScholarLocate open access versionFindings
  • IERI Procedia, vol. 2, pp. 565-570, 2012.
    Google ScholarFindings
  • 2012, 2012, pp. 129-138.
    Google ScholarFindings
  • Naval Research Logistics Quarterly, vol. 2, pp. 83-97, 1955.
    Google ScholarLocate open access versionFindings
  • distance computation through fast bipartite matching," in Graph-Based Representations in Pattern Recognition. vol. 6658, X. Jiang, M. Ferrer, and A. Torsello, Eds., ed: Springer Berlin Heidelberg, 2011, pp. 102-111.
    Google ScholarFindings
  • Engineering, vol. 17, pp. 734-749, 2005.
    Google ScholarFindings
  • J. Lu, Q. Shambour, Y. Xu, Q. Lin, and G. Zhang, "BizSeeker: a hybrid semantic recommendation system for personalized government-to-business e-services," Internet Research, vol. 20, pp.
    Google ScholarLocate open access versionFindings
  • J. Lu, Q. Shambour, Y. Xu, Q. Lin, and G. Zhang, "A web-based personalized business partner recommendation system using fuzzy semantic techniques," Computational Intelligence, vol. 29, pp. 37-
    Google ScholarLocate open access versionFindings
  • X. Guo and J. Lu, "Intelligent e-government services with personalized recommendation techniques," International Journal of Intelligent Systems, vol. 22, pp. 401-417, 2007.
    Google ScholarLocate open access versionFindings
  • A. Zenebe, L. Zhou, and A. F. Norcio, "User preferences discovery using fuzzy models," Fuzzy Sets and Systems, vol. 161, pp. 3044-
    Google ScholarLocate open access versionFindings
  • A. Zenebe and A. F. Norcio, "Representation, similarity measures and aggregation methods using fuzzy sets for content-based recommender systems," Fuzzy Sets and Systems, vol. 160, pp. 76-
    Google ScholarLocate open access versionFindings
  • Fuzzy Sets and Systems, vol. 136, pp. 133-149, 2003.
    Google ScholarFindings
  • linguistic multi-criteria group decision support system for fabric hand evaluation," Fuzzy Optimization and Decision Making, vol. 8, pp. 395-413, 2009/12/01 2009.
    Google ScholarLocate open access versionFindings
  • J. Ma, J. Lu, and G. Zhang, "Decider: A fuzzy multi-criteria group decision support system," Knowledge-Based Systems, vol. 23, pp.
    Google ScholarLocate open access versionFindings
  • D. Wu, G. Zhang, and J. Lu, "A fuzzy preference tree-based recommender system for personalized business-to-business eservices," IEEE Transactions on Fuzzy Systems, vol. 23, pp. 29-43, 2015.
    Google ScholarLocate open access versionFindings
  • R. Burke, "Hybrid recommender systems: survey and experiments," User Modeling and User-Adapted Interaction, vol.
    Google ScholarLocate open access versionFindings
  • 12, pp. 331-370, 2002.
    Google ScholarFindings
  • Web. vol. 4321, P. Brusilovsky, A. Kobsa, and W. Nejdl, Eds., ed: Springer Berlin Heidelberg, 2007, pp. 291-324.
    Google ScholarFindings
  • M. Pazzani and D. Billsus, "Content-based recommendation systems," in The Adaptive Web. vol. 4321, P. Brusilovsky, A.
    Google ScholarFindings
  • Kobsa, and W. Nejdl, Eds., ed: Springer Berlin Heidelberg, 2007, pp. 325-341.
    Google ScholarFindings
  • Encyclopedia of Library and Information Systems, vol. 69, pp.
    Google ScholarLocate open access versionFindings
  • Springer-Verlag, Berlin Heidelberg, 2007, pp. 377-408.
    Google ScholarFindings
  • Support Systems, vol. 35, pp. 231-243, 2003.
    Google ScholarFindings
  • S. W. Changchien and T.-C. Lu, "Mining association rules procedure to support on-line recommendation by customers and products fragmentation," Expert Systems with Applications, vol.
    Google ScholarLocate open access versionFindings
  • 20, pp. 325-335, 2001.
    Google ScholarFindings
  • Expert Systems with Applications, vol. 22, pp. 275-284, 2002.
    Google ScholarLocate open access versionFindings
  • Applications, vol. 25, pp. 387-400, 2003.
    Google ScholarFindings
  • Duri, Personalization of supermarket product recommendations: Springer, 2001.
    Google ScholarFindings
  • J. He and W. Chu, "A social network-based recommender system (SNRS)," in Data Mining for Social Network Data. vol. 12, N.
    Google ScholarLocate open access versionFindings
  • Memon, J. J. Xu, D. L. Hicks, and H. Chen, Eds., ed: Springer US, 2010, pp. 47-74.
    Google ScholarFindings
  • Z. Zhang, H. Lin, K. Liu, D. Wu, G. Zhang, and J. Lu, "A hybrid fuzzy-based personalized recommender system for telecom products/services," Information Sciences, vol. 235, pp. 117-129, 2013.
    Google ScholarLocate open access versionFindings
  • Rokach, B. Shapira, and P. B. Kantor, Eds., ed: Springer US, 2011, pp. 217-253.
    Google ScholarFindings
  • J. Masthoff, "Group recommender systems: combining individual models," in Recommender Systems Handbook, F. Ricci, L. Rokach, B. Shapira, and P. B. Kantor, Eds., ed: Springer US, 2011, pp. 677-
    Google ScholarFindings
  • 702. O. R. Zaiane, "Building a recommender agent for e-learning systems," in Proceedings of 2002 International Conference on Computers in Education, 2002, pp. 55-59
    Google ScholarLocate open access versionFindings
  • Knowledge-Based Systems, vol. 22, pp. 261-265, 2009.
    Google ScholarFindings
  • D. Wu, G. Zhang, J. Lu, and W. A. Halang, "A similarity measure on tree structured business data," in ACIS 2012: Location, Professor Jie Lu is the Associate Dean Research (Acting) of Faculty of Engineering and Information Technology, and the Director of the location, location: Proceedings of the 23rd Australasian
    Google ScholarLocate open access versionFindings
  • Conference on Information Systems 2012, 2012, pp. 1-10.
    Google ScholarLocate open access versionFindings
  • D. Wu, G. Zhang, and J. Lu, "A fuzzy tree similarity measure and its application in telecom product recommendation," in 2013 IEEE
    Google ScholarLocate open access versionFindings
  • Decision Systems and e-Service Intelligence Research Laboratory in the Centre for Quantum Computation & Intelligent Systems (SMC), Manchester, 2013, pp. 3483-3488.
    Google ScholarLocate open access versionFindings
  • D. Wu, G. Zhang, and J. Lu, "A fuzzy tree similarity based recommendation approach for telecom products," in 2013 Joint
    Google ScholarLocate open access versionFindings
  • Sydney (UTS). She received her PhD from the Curtin University of (IFSA/NAFIPS), Edmonton, Canada, 2013, pp. 813-818.
    Google ScholarFindings
  • Technology in 2000. Her main research interests lie in the area
    Google ScholarFindings
  • Applications, vol. 38, pp. 15049-15056, 2011.
    Google ScholarFindings
  • Springer-Verlag, Berlin Heidelberg, 2008.
    Google ScholarFindings
  • K. Riesen and H. Bunke, "Approximate graph edit distance conference proceedings. She has won five Australian Research computation by means of bipartite graph matching," Image and Council (ARC) discovery grants. She received the first UTS
    Google ScholarLocate open access versionFindings
  • Vision Computing, vol. 27, pp. 950-959, 2009.
    Google ScholarFindings
  • Communications of the ACM, vol. 26, pp. 832-843, 1983.
    Google ScholarLocate open access versionFindings
  • Integration in 2010. She serves as Editor-In-Chief for
    Google ScholarFindings
  • Sensory Evaluation: Methodologies and Applications, pp. 51-70, 2004.
    Google ScholarFindings
  • Dr. Guangquan Zhang is an dealing with fuzzy preferences for alternatives and individual judgments for selection criteria," Group Decision and Negotiation, vol. 12, pp. 501-515, 2003.
    Google ScholarLocate open access versionFindings
  • Sciences, vol. 179, pp. 2299-2308, 2009.
    Google ScholarFindings
  • Faculty of Engineering and Information Technology at University of Technology Sydney. He has authored and co-authored 246 publications including four monographs, four text books, 13 book chapters and 119 refereed international journal papers. Dr. Zhang has served as an advisory board member, or a member of the editorial board for several international journals, co-chaired several international conferences/workshops in the area of fuzzy decision-making and knowledge engineering, such as FLINS08, FLINS10, ISKE09.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments
小科