ISSN 0253-2778

CN 34-1054/N

open
Free to Publish. Free to Read.
Open AccessOpen Access JUSTC Original Paper

A method of knowledge item recommendation based on Skill-LFM

  • 1.

    Research, CVTE, Guangzhou 510000

  • 2.

    DMIR, GDUT, Guangzhou 510000

  • 3.

    Guangdong branch, China Telecom, Guangzhou 510000

Cite this:
https://doi.org/10.3969/j.issn.0253-2778.2018.09.010
  • Received Date: 28 May 2018
  • Accepted Date: 18 September 2018
  • Rev Recd Date: 18 September 2018
  • Publish Date: 30 September 2018
    Abstract

  • Abstract

    At present, the users of knowledge base mainly get the required knowledge items through search, which relies on the search engine to solve the information overload problem. It is inefficient for real-time online services, and has no integrity and continuity of offline knowledge learning. Therefore, it is proposed that knowledge items should be actively recommended to users by the knowledge base system according to their level of skills, to improve the efficiency of decision making, and also to help users establish a complete knowledge learning system. A collaborative filtering recommendation method is proposed to predict every user's preference on knowledge items, based on the historical behavior of a user on the knowledge items, and the knowledge learning ability of this user. This method combines latent factor model with skill, named Skill-LFM, where the difficulties of knowledge items are taken as potential factors, and users' ability level is considered to give personalized recommendations. Tested on the data from a call center knowledge base, the proposed Skill-LFM outperforms the baseline latent factor model in terms of lower RMSE. Considering the characteristics of the application domain and the historical behavior data of the knowledge base, this paper demonstrates the possibility of further improving knowledge item recommendation through integrating user and knowledge item context information.

    Abstract

    At present, the users of knowledge base mainly get the required knowledge items through search, which relies on the search engine to solve the information overload problem. It is inefficient for real-time online services, and has no integrity and continuity of offline knowledge learning. Therefore, it is proposed that knowledge items should be actively recommended to users by the knowledge base system according to their level of skills, to improve the efficiency of decision making, and also to help users establish a complete knowledge learning system. A collaborative filtering recommendation method is proposed to predict every user's preference on knowledge items, based on the historical behavior of a user on the knowledge items, and the knowledge learning ability of this user. This method combines latent factor model with skill, named Skill-LFM, where the difficulties of knowledge items are taken as potential factors, and users' ability level is considered to give personalized recommendations. Tested on the data from a call center knowledge base, the proposed Skill-LFM outperforms the baseline latent factor model in terms of lower RMSE. Considering the characteristics of the application domain and the historical behavior data of the knowledge base, this paper demonstrates the possibility of further improving knowledge item recommendation through integrating user and knowledge item context information.
    • FullText(HTML)
  • loading
    • References(35)
  • [1]
    ULLMAN J D. Principles of Database and Knowledge-Base Systems [M]. New York: Computer Science Press, 1988.
    [2]
    ALAVI M, LEIDNER D E. Knowledge management and knowledge management systems: Conceptual foundations and research issues[J]. MIS Quarterly, 2001, 25(1): 107-136.
    [3]
    GIBONEY J S, BROWN S A, LOWRY P B, et al. User acceptance of knowledge-based system recommendations: explanations, arguments, and fit[J]. Decision Support Systems, 2015, 72(C):1-10.
    [4]
    VELSQUEZ J D, PALADE V. Building a knowledge base for implementing a web-based computerized recommendation system[J]. International Journal on Artificial Intelligence Tools, 2007, 16(5): 793-828.
    [5]
    KOREN Y, BELL R, VOLINSKY C. Matrix factorization techniques for recommender systems[J]. Computer, 2009, 42(8): 30-37.
    [6]
    SARWAR B, KARYPIS G, KONSTAN J, et al. Application of dimensionality reduction in recommender systems[EB/OL]. ACM WebKDD-2000, [2018-11-17] http://glaros.dtc.umn.edu/gkhome/node/122.
    [7]
    SARWAR B, KARYPIS G, KONSTAN J, et al. Item-based collaborative filtering recommendation algorithms[C]// International Conference on World Wide Web. Hong Kong, China: ACM Press, 2001: 285-295.
    [8]
    LINDEN G, SMITH B, YORK J. Amazon.com recommendations: item-to-item collaborative filtering[J]. IEEE Internet Computing, 2003, 7(1):76-80.
    [9]
    ZENG C, XING C X, ZHOU L Z. Survey of personalization technology[J]. Journal of Software, 2002, 13(10): 1952-1961.
    [10]
    RICCI F, ROKACH L, SHAPIRA B, et al. Recommender Systems Handbook [M]. Springer, 2011.
    [11]
    ADOMAVICIUS G, TUZHILIN A. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions[J]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(6): 734-749.
    [12]
    BENNETT J, LANNING S, NETFLIX N. The Netflix Prize[C]// KDD Cup and Workshop in Conjunction with KDD. 2009.
    [13]
    MASSA P, AVESANI P. Trust-aware recommender systems[C]// Proceedings of the Conference on Recommender Systems. Minnesota, USA: ACM Press, 2007: 17-24.
    [14]
    GOLDBERG D, NICHOLS D, OKI B M, et al. Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM, 1992, 35(12): 61-70.
    [15]
    BURKE R. Hybrid recommender systems: Survey and experiments[J]. User Modeling and User-Adapted Interaction, 2002, 12(4): 331-370.
    [16]
    KOREN Y. Factorization meets the neighborhood: A multifaceted collaborative filtering model[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Las Vegas, USA: ACM Press, 2008: 426-434.
    [17]
    KOREN Y. Collaborative filtering with temporal dynamics[J]. Communications of the ACM, 2010, 53(4): 89-97.
    [18]
    JAMALI M, ESTER M. A matrix factorization technique with trust propagation for recommendation in social networks[C]// ACM Conference on Recommender Systems. Barcelona, Spain: ACM Press, 2010: 135-142.
    [19]
    CHEN T, ZHANG W, LU Q, et al. SVDFeature: A toolkit for feature-based collaborative filtering[J]. Journal of Machine Learning Research, 2012, 13(1): 3619-3622.
    [20]
    OSMANLI O N, 倫SMAIL HAKKI TOROSLU. Using tag similarity in SVD-based recommendation systems[C]// International Conference on Application of Information and Communication Technologies. Baku, Azerbaijan: IEEE Press, 2011: 1-4.
    [21]
    XU Z, CHANG X, XU F, et al. L1/2 regularization: A thresholding representation theory and a fast solver[J]. IEEE Transactions on Neural Networks & Learning Systems, 2012, 23(7): 1013-1027.
    [22]
    RUDER S. An overview of gradient descent optimization algorithms[J]. Machine Learning, 2016: arXiv:1609.04747 [cs.LG].
    [23]
    SALAKHUTDINOV R, MNIH A. Probabilistic matrix factorization[C]// International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2007: 1257-1264.
    [24]
    LEE D D, SEUNG H S. Algorithms for non-negative matrix factorization[C]// International Conference on Neural Information Processing Systems. MIT Press, 2000:535-541.
    [25]
    SHARIFI Z, REZGHI M, NASIRI M. A new algorithm for solving data sparsity problem based-on Non negative matrix factorization in recommender systems[C]// International Conference on Computer and Knowledge Engineering. Mashhad, Iran: IEEE Press, 2014:56-61.
    [26]
    LUO X, ZHOU M, XIA Y, et al. An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems[J]. IEEE Transactions on Industrial Informatics, 2014, 10(2): 1273-1284.
    [27]
    WANG L, MENG X, ZHANG Y, et al. Applying HOSVD to alleviate the sparsity problem in context-aware recommender systems[J]. Chinese Journal of Electronics, 2013, 22(4): 773-778.
    [28]
    KUTTY S, CHEN L, NAYAK R. A people-to-people recommendation system using tensor space models[C]// ACM Symposium on Applied Computing. Trento, Italy: ACM Press, 2012: 187-192.
    [29]
    KARATZOGLOU A, AMATRIAIN X, BALTRUNAS L, et al. Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering[C]// ACM Conference on Recommender Systems. Barcelona, Spain: ACM Press, 2010: 79-86.
    [30]
    CREMONESI P, TURRIN R, TURRIN R. Performance of recommender algorithms on top-n recommendation tasks[C]// ACM Conference on Recommender Systems. Barcelona, Spain: ACM Press, 2010: 39-46.
    [31]
    WILLMOTT C J, MATSUURA K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance [J]. Climate Research, 2005, 30(1): 79-82.
    [32]
    CHAI T, DRAXLER R R. Root mean square error (RMSE) or mean absolute error (MAE)?[J]. Geoscientific Model Development, 2014, 7(3):1247-1250.
    [33]
    TAK, CS G, SZY I, et al. Matrix factorization and neighbor based algorithms for the netflix prize problem[C]// ACM Conference on Recommender Systems. Lausanne, Switzerland: ACM Press, 2008: 267-274.
    [34]
    OTT P. Incremental Matrix Factorization for Collaborative Filtering[M]// Science, Technology and Design 01/2008, Anhalt University of Applied Sciences.
    [35]
    LEE D D, SEUNG H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401(6755): 788791.)
    • Supplements(0)
    • Related Articles
    • Track Citations
  • 加载中

Catalog

    |
    Get Citation
    PDF
    XML
    [1]
    ULLMAN J D. Principles of Database and Knowledge-Base Systems [M]. New York: Computer Science Press, 1988.
    [2]
    ALAVI M, LEIDNER D E. Knowledge management and knowledge management systems: Conceptual foundations and research issues[J]. MIS Quarterly, 2001, 25(1): 107-136.
    [3]
    GIBONEY J S, BROWN S A, LOWRY P B, et al. User acceptance of knowledge-based system recommendations: explanations, arguments, and fit[J]. Decision Support Systems, 2015, 72(C):1-10.
    [4]
    VELSQUEZ J D, PALADE V. Building a knowledge base for implementing a web-based computerized recommendation system[J]. International Journal on Artificial Intelligence Tools, 2007, 16(5): 793-828.
    [5]
    KOREN Y, BELL R, VOLINSKY C. Matrix factorization techniques for recommender systems[J]. Computer, 2009, 42(8): 30-37.
    [6]
    SARWAR B, KARYPIS G, KONSTAN J, et al. Application of dimensionality reduction in recommender systems[EB/OL]. ACM WebKDD-2000, [2018-11-17] http://glaros.dtc.umn.edu/gkhome/node/122.
    [7]
    SARWAR B, KARYPIS G, KONSTAN J, et al. Item-based collaborative filtering recommendation algorithms[C]// International Conference on World Wide Web. Hong Kong, China: ACM Press, 2001: 285-295.
    [8]
    LINDEN G, SMITH B, YORK J. Amazon.com recommendations: item-to-item collaborative filtering[J]. IEEE Internet Computing, 2003, 7(1):76-80.
    [9]
    ZENG C, XING C X, ZHOU L Z. Survey of personalization technology[J]. Journal of Software, 2002, 13(10): 1952-1961.
    [10]
    RICCI F, ROKACH L, SHAPIRA B, et al. Recommender Systems Handbook [M]. Springer, 2011.
    [11]
    ADOMAVICIUS G, TUZHILIN A. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions[J]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(6): 734-749.
    [12]
    BENNETT J, LANNING S, NETFLIX N. The Netflix Prize[C]// KDD Cup and Workshop in Conjunction with KDD. 2009.
    [13]
    MASSA P, AVESANI P. Trust-aware recommender systems[C]// Proceedings of the Conference on Recommender Systems. Minnesota, USA: ACM Press, 2007: 17-24.
    [14]
    GOLDBERG D, NICHOLS D, OKI B M, et al. Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM, 1992, 35(12): 61-70.
    [15]
    BURKE R. Hybrid recommender systems: Survey and experiments[J]. User Modeling and User-Adapted Interaction, 2002, 12(4): 331-370.
    [16]
    KOREN Y. Factorization meets the neighborhood: A multifaceted collaborative filtering model[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Las Vegas, USA: ACM Press, 2008: 426-434.
    [17]
    KOREN Y. Collaborative filtering with temporal dynamics[J]. Communications of the ACM, 2010, 53(4): 89-97.
    [18]
    JAMALI M, ESTER M. A matrix factorization technique with trust propagation for recommendation in social networks[C]// ACM Conference on Recommender Systems. Barcelona, Spain: ACM Press, 2010: 135-142.
    [19]
    CHEN T, ZHANG W, LU Q, et al. SVDFeature: A toolkit for feature-based collaborative filtering[J]. Journal of Machine Learning Research, 2012, 13(1): 3619-3622.
    [20]
    OSMANLI O N, 倫SMAIL HAKKI TOROSLU. Using tag similarity in SVD-based recommendation systems[C]// International Conference on Application of Information and Communication Technologies. Baku, Azerbaijan: IEEE Press, 2011: 1-4.
    [21]
    XU Z, CHANG X, XU F, et al. L1/2 regularization: A thresholding representation theory and a fast solver[J]. IEEE Transactions on Neural Networks & Learning Systems, 2012, 23(7): 1013-1027.
    [22]
    RUDER S. An overview of gradient descent optimization algorithms[J]. Machine Learning, 2016: arXiv:1609.04747 [cs.LG].
    [23]
    SALAKHUTDINOV R, MNIH A. Probabilistic matrix factorization[C]// International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2007: 1257-1264.
    [24]
    LEE D D, SEUNG H S. Algorithms for non-negative matrix factorization[C]// International Conference on Neural Information Processing Systems. MIT Press, 2000:535-541.
    [25]
    SHARIFI Z, REZGHI M, NASIRI M. A new algorithm for solving data sparsity problem based-on Non negative matrix factorization in recommender systems[C]// International Conference on Computer and Knowledge Engineering. Mashhad, Iran: IEEE Press, 2014:56-61.
    [26]
    LUO X, ZHOU M, XIA Y, et al. An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems[J]. IEEE Transactions on Industrial Informatics, 2014, 10(2): 1273-1284.
    [27]
    WANG L, MENG X, ZHANG Y, et al. Applying HOSVD to alleviate the sparsity problem in context-aware recommender systems[J]. Chinese Journal of Electronics, 2013, 22(4): 773-778.
    [28]
    KUTTY S, CHEN L, NAYAK R. A people-to-people recommendation system using tensor space models[C]// ACM Symposium on Applied Computing. Trento, Italy: ACM Press, 2012: 187-192.
    [29]
    KARATZOGLOU A, AMATRIAIN X, BALTRUNAS L, et al. Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering[C]// ACM Conference on Recommender Systems. Barcelona, Spain: ACM Press, 2010: 79-86.
    [30]
    CREMONESI P, TURRIN R, TURRIN R. Performance of recommender algorithms on top-n recommendation tasks[C]// ACM Conference on Recommender Systems. Barcelona, Spain: ACM Press, 2010: 39-46.
    [31]
    WILLMOTT C J, MATSUURA K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance [J]. Climate Research, 2005, 30(1): 79-82.
    [32]
    CHAI T, DRAXLER R R. Root mean square error (RMSE) or mean absolute error (MAE)?[J]. Geoscientific Model Development, 2014, 7(3):1247-1250.
    [33]
    TAK, CS G, SZY I, et al. Matrix factorization and neighbor based algorithms for the netflix prize problem[C]// ACM Conference on Recommender Systems. Lausanne, Switzerland: ACM Press, 2008: 267-274.
    [34]
    OTT P. Incremental Matrix Factorization for Collaborative Filtering[M]// Science, Technology and Design 01/2008, Anhalt University of Applied Sciences.
    [35]
    LEE D D, SEUNG H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401(6755): 788791.)
    Recommended articles
    TrendMD
    Volume 48 Issue 9 page: 755-761
    Cover

    Article Metrics

    Article views (49) PDF downloads(101)
    Proportional views

    Copyright © Editorial Office of JUSTC, All Rights Reserved. 皖ICP备05002528号

    Supported by: Beijing Renhe Information Technology Co. Ltd    

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return