Credibility Evaluation Algorithm Based on Deep Learning

Liu Mengling; Li Zhendong

doi:doi:10.11648/j.acm.20170604.19

| Peer-Reviewed

Credibility Evaluation Algorithm Based on Deep Learning

Liu Mengling, Li Zhendong

Published in Applied and Computational Mathematics (Volume 6, Issue 4)

Received: 13 August 2017 Published: 17 August 2017

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

The credibility of a recommendation system is a hot focus nowadays in the field of personalized recommendation research. However, it is difficult to carry out effective credibility evaluation for the users in the presence of a false recommendation system, say nothing of eliminating suspicious users and further more improve the security and reliability of the system. This paper proposed a new method of reliability assessment based on deep learning. According to the users’ rating database, community of users with average scores is constructed and traditional credibility algorithm is used to calculate the initial credibility of the users. With the average users' reliability value as a criterion, the second assessment to the credibility based on deep learning algorithm is applied to other users, the results of which are arranged in ascending order. Then suspicious users ranking top-L will be removed and a trustfully adjacent group for the target users will be created. Experiments show that the improved algorithm can optimize the recommendation system with better security, accuracy and reliability as well.

Published in	Applied and Computational Mathematics (Volume 6, Issue 4)
DOI	10.11648/j.acm.20170604.19
Page(s)	208-214
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2017. Published by Science Publishing Group

Keywords

Reliability, Average User, Deep Learning, Accuracy

References

[1]	Qin Jiwei, Zheng Qinghua, et al., “A collaborative recommendation algorithm based on ratings and trust,” Joumal of Xi’an Jiaotong University, 2013, 47 (4), pp. 100-104.
[2]	Liu Shengzong, Liao Zhifang, Wu Yanfeng, “A Collaborative Filtering Algorithm Combined with User Rating Credibility and Similarity,” Journal of Chinese Computer Systems, 2014, 35 (5), pp. 973-977.
[3]	Miao Xinjie, The Research and Application of Collaborative Filtering Algorithm. Nanjing: Nanjing University of Information Science & Technology, 2014.
[4]	R. Salakhutdinov, A. Mnih, and G. Hinton. Restricted boltzmann machines for collaborative filtering. In Proceedings of the 24th international conference on Machine learning, pp. 791–798. ACM, 2007.
[5]	L. K. Saul, T. Jaakkola, and M. I. Jordan, Mean field theory for sigmoid belief networks. Arxiv preprint cs/9603102, 1996.
[6]	Zhou Tao, Ren Jie, Medo M, et al., “Bipartite network projection and personal recommendation,” Physical Review E, 2007, 76 (4 Pt 2): 046115.
[7]	Victor P, Verbiest N, Cornelis C, et al., “Enhancing the trust-based recommendation process with explicit distrust,” ACM Transactions on the Web (TWEB), 2013, 7 (2), pp. 61-80.
[8]	Hinton G, Salakhutdinov R, “Reducing the dimensionality of data with neural network,” Science, 2006, 313 (504), Doi: 10, 1126/science, 1127647.
[9]	Geoffrey E. Hinton, Simon Osindero, Yee-Whye The, “A Fast Learning Algorithm For Deep Belief Nets,” Neural Computation 18, 2006, pp. 1527-1554.
[10]	Ruslan Salakhutdinov, Andriy Mnih, Geoffrey Hinton, “Restricted Boltzmann Machines for Collaborative Filtering,” Proceedings of the 24th International Conference on Machine Learning, Corvallis, OR, 2007.
[11]	Yu Kai, Jia Lei, Chen Yuqiang, “Deep Learning: Promote the dream of artificial intelligence,” Programmer, 2013 (6), pp. 22-27.
[12]	Wang Shengzhu, Li Yong-zhong, “Intrusion detection algorithm based on deep learning and semi-supervised learning,” Information Technology, 2017 (1), pp. 101-104, 108.
[13]	Chen Hong, Wan Guangxue, “Intrusion detection method of deep belief network model based on optimization of data processing,” Journal of Computer Applications, 2017, 37 (6), pp. 1636-1643, 1656.

Cite This Article

Plain Text BibTeX RIS

APA Style

Liu Mengling, Li Zhendong. (2017). Credibility Evaluation Algorithm Based on Deep Learning. Applied and Computational Mathematics, 6(4), 208-214. https://doi.org/10.11648/j.acm.20170604.19

Copy | Download

ACS Style

Liu Mengling; Li Zhendong. Credibility Evaluation Algorithm Based on Deep Learning. Appl. Comput. Math. 2017, 6(4), 208-214. doi: 10.11648/j.acm.20170604.19

Copy | Download

AMA Style

Liu Mengling, Li Zhendong. Credibility Evaluation Algorithm Based on Deep Learning. Appl Comput Math. 2017;6(4):208-214. doi: 10.11648/j.acm.20170604.19

Copy | Download

@article{10.11648/j.acm.20170604.19,
  author = {Liu Mengling and Li Zhendong},
  title = {Credibility Evaluation Algorithm Based on Deep Learning},
  journal = {Applied and Computational Mathematics},
  volume = {6},
  number = {4},
  pages = {208-214},
  doi = {10.11648/j.acm.20170604.19},
  url = {https://doi.org/10.11648/j.acm.20170604.19},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.acm.20170604.19},
  abstract = {The credibility of a recommendation system is a hot focus nowadays in the field of personalized recommendation research. However, it is difficult to carry out effective credibility evaluation for the users in the presence of a false recommendation system, say nothing of eliminating suspicious users and further more improve the security and reliability of the system. This paper proposed a new method of reliability assessment based on deep learning. According to the users’ rating database, community of users with average scores is constructed and traditional credibility algorithm is used to calculate the initial credibility of the users. With the average users' reliability value as a criterion, the second assessment to the credibility based on deep learning algorithm is applied to other users, the results of which are arranged in ascending order. Then suspicious users ranking top-L will be removed and a trustfully adjacent group for the target users will be created. Experiments show that the improved algorithm can optimize the recommendation system with better security, accuracy and reliability as well.},
 year = {2017}
}

Copy | Download

TY  - JOUR
T1  - Credibility Evaluation Algorithm Based on Deep Learning
AU  - Liu Mengling
AU  - Li Zhendong
Y1  - 2017/08/17
PY  - 2017
N1  - https://doi.org/10.11648/j.acm.20170604.19
DO  - 10.11648/j.acm.20170604.19
T2  - Applied and Computational Mathematics
JF  - Applied and Computational Mathematics
JO  - Applied and Computational Mathematics
SP  - 208
EP  - 214
PB  - Science Publishing Group
SN  - 2328-5613
UR  - https://doi.org/10.11648/j.acm.20170604.19
AB  - The credibility of a recommendation system is a hot focus nowadays in the field of personalized recommendation research. However, it is difficult to carry out effective credibility evaluation for the users in the presence of a false recommendation system, say nothing of eliminating suspicious users and further more improve the security and reliability of the system. This paper proposed a new method of reliability assessment based on deep learning. According to the users’ rating database, community of users with average scores is constructed and traditional credibility algorithm is used to calculate the initial credibility of the users. With the average users' reliability value as a criterion, the second assessment to the credibility based on deep learning algorithm is applied to other users, the results of which are arranged in ascending order. Then suspicious users ranking top-L will be removed and a trustfully adjacent group for the target users will be created. Experiments show that the improved algorithm can optimize the recommendation system with better security, accuracy and reliability as well.
VL  - 6
IS  - 4
ER  -

Copy | Download

Author Information

Liu Mengling

Department of Mathematical Sciences, Tsinghua University, Beijing, China
Li Zhendong

School of Information and Control, Nanjing University of Information Science & Technology, Nanjing, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Liu Mengling, Li Zhendong. (2017). Credibility Evaluation Algorithm Based on Deep Learning. Applied and Computational Mathematics, 6(4), 208-214. https://doi.org/10.11648/j.acm.20170604.19

Copy | Download

ACS Style

Liu Mengling; Li Zhendong. Credibility Evaluation Algorithm Based on Deep Learning. Appl. Comput. Math. 2017, 6(4), 208-214. doi: 10.11648/j.acm.20170604.19

Copy | Download

AMA Style

Liu Mengling, Li Zhendong. Credibility Evaluation Algorithm Based on Deep Learning. Appl Comput Math. 2017;6(4):208-214. doi: 10.11648/j.acm.20170604.19

Copy | Download

@article{10.11648/j.acm.20170604.19,
  author = {Liu Mengling and Li Zhendong},
  title = {Credibility Evaluation Algorithm Based on Deep Learning},
  journal = {Applied and Computational Mathematics},
  volume = {6},
  number = {4},
  pages = {208-214},
  doi = {10.11648/j.acm.20170604.19},
  url = {https://doi.org/10.11648/j.acm.20170604.19},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.acm.20170604.19},
  abstract = {The credibility of a recommendation system is a hot focus nowadays in the field of personalized recommendation research. However, it is difficult to carry out effective credibility evaluation for the users in the presence of a false recommendation system, say nothing of eliminating suspicious users and further more improve the security and reliability of the system. This paper proposed a new method of reliability assessment based on deep learning. According to the users’ rating database, community of users with average scores is constructed and traditional credibility algorithm is used to calculate the initial credibility of the users. With the average users' reliability value as a criterion, the second assessment to the credibility based on deep learning algorithm is applied to other users, the results of which are arranged in ascending order. Then suspicious users ranking top-L will be removed and a trustfully adjacent group for the target users will be created. Experiments show that the improved algorithm can optimize the recommendation system with better security, accuracy and reliability as well.},
 year = {2017}
}

Copy | Download

TY  - JOUR
T1  - Credibility Evaluation Algorithm Based on Deep Learning
AU  - Liu Mengling
AU  - Li Zhendong
Y1  - 2017/08/17
PY  - 2017
N1  - https://doi.org/10.11648/j.acm.20170604.19
DO  - 10.11648/j.acm.20170604.19
T2  - Applied and Computational Mathematics
JF  - Applied and Computational Mathematics
JO  - Applied and Computational Mathematics
SP  - 208
EP  - 214
PB  - Science Publishing Group
SN  - 2328-5613
UR  - https://doi.org/10.11648/j.acm.20170604.19
AB  - The credibility of a recommendation system is a hot focus nowadays in the field of personalized recommendation research. However, it is difficult to carry out effective credibility evaluation for the users in the presence of a false recommendation system, say nothing of eliminating suspicious users and further more improve the security and reliability of the system. This paper proposed a new method of reliability assessment based on deep learning. According to the users’ rating database, community of users with average scores is constructed and traditional credibility algorithm is used to calculate the initial credibility of the users. With the average users' reliability value as a criterion, the second assessment to the credibility based on deep learning algorithm is applied to other users, the results of which are arranged in ascending order. Then suspicious users ranking top-L will be removed and a trustfully adjacent group for the target users will be created. Experiments show that the improved algorithm can optimize the recommendation system with better security, accuracy and reliability as well.
VL  - 6
IS  - 4
ER  -

Copy | Download