Recommender system is a tool that provides personalized service to help users to find their desired content. Context-aware
recommendations personalize the search for such desired content by considering the contextual information. In many recommendation
aspects, incorporating the context of users has been shown to improve the quality of recommendations. In this work, we propose a
model that improves the user experience of finding the content they desire by analyzing their contextual information. By conducting an
empirical analysis of a dataset from last.fm, we demonstrate the extraction of latent preferences for recommending items under a given
context and study how contextual information can be exploited to improve the prediction accuracy of recommender systems.
Additionally, we use an optimization function to further minimize the root mean square error (RMSE) measure of the resulted
prediction capability of the latent preference models. Finally, we proposed a latent collaborative preference model to predict the final
rating of users to items by combining the extracted latent preference models. The experimental results achieved in this work shows our
context-aware latent collaborative model can improve the prediction accuracy of recommender systems as compared to state of the art
non-context aware approaches.
Published In:IJCSN Journal Volume 6, Issue 5
Date of Publication : October2017
Pages : 625-634
Figures :04
Tables : 02
Solomon Demissie Seifu : received a bachelor degree in the field of
computer science and information technology with distinction in 2006
from Adama Science and Technology University (Ethiopia), then he
hold a Masters degree in the field of Information Science in 2010
from Addis Ababa University (Ethiopia), and in 2015 he again
received a Master of Technology (M.Tech) degree in Computer
Science and Technology from Andhra University, India. He has
published 2 papers in international Journals. He worked as Lecturer
at the University of Debre Berhan (Ethiopia). His field of teaching
includes programming languages like C, C++, Java etc, networking,
Database and operating systems. His research interests include data
mining and machine learning, recommender systems, cloud
computing, and software engineering.
M. Shashi : is a Professor and Chairperson of Board of Studies of the
Department of Computer Science & Systems Engineering, A.U.
College of Engineering(A), Andhra University, Visakhapatnam,
Andhra Pradesh. She received the AICTE Career Award in 1996,
Best Ph.D thesis prize from Andhra University in the year 1994 and
AP State Best teacher award in 2016. 13 Ph.D.’s were awarded
under her guidance. She co-authored more than 60 technical
research papers in International Journals and 50 International
Conferences and delivered many invited talks in such academic
events. She is a member of IEEE Computational Intelligence group,
Fellow of Institute of Engineers (India) and life member of Computer
Society of India.. Her current research interests include Data
warehousing and Mining, Data Analytics, Artificial Intelligence, Soft
Computing and Machine Learning.
In this paper, we demonstrated the potential of using
user’s contextual information and analyzing the use of a
contextual tag to improve the prediction accuracy and
enhance its quality. Through our experiment we showed
how we explore the latent preferences based on the user,
item, and context dimensions; i.e., latent user’s
preferences towards contexts, latent contexts preferences
towards items, as well as latent user’s preferences towards
items. Additionally, we demonstrated a prediction
performance improvement on latent preference models via
optimization process.
[1] A. Shepitsen, J. Gemmell, B. Mobasher, and R. Burke,
“Personalized recommendation in social tagging systems
using hierarchical clustering”, ACM Conference on
Recommender Systems, 2008, pp. 259–266.
[2] Cosimo Palmisano, Alexander Tuzhilin, and Michele
Gorgoglione, “Using context to improve predictive
modeling of customers in personalization applications”,
IEEE Transactions on Knowledge and Data Engineering,
vol. 11, 2008, pp.1535–1549.
[3] C. J. van Rijsbergen, Information Retrieval, 2nd ed.
London, United Kingdom: Butterworths, 1979.
[4] Desrosiers C., and Karypis, A comprehensive survey of
neighborhood-based recommendation methods, In
Recommender systems handbook. Springer. pp. 107-144,
2011.
[5] G. Adomavicius and A. Tuzhilin, “Toward the next
generation of recommender systems: a survey of the
state-of-the-art and possible extensions”, IEEE
Knowledge and Data Engineering, vol.17, 2005, pp. 734
-749.
[6] G. Adomavicius and A. Tuzhilin, Context-Aware
Recommender Systems, Recommender Systems
Handbook: A Complete Guide for Research Scientists
and Practitioners, L. Rokach, B. Shapira, P. Kantor, and
F. Ricci, Ed. Springer, 2011.
[7] G. Karypis, “Evaluation of item-based top-n
recommendation algorithms”, in Proc. 10th Int. Conf.
Inf. Knowl. Manage., 2001, pp. 247–254.
[8] H. Liu, Z. Hu, A. Mian, H. Tian, and X. Zhu, “A new
user similarity model to improve the accuracy of
collaborative filtering”, Knowl.-Based Syst., vol. 56,
2014, pp. 156–166.
[9] H. Zhu, E. Chen, H. Xiong, K. Yu, H. Cao, and J. Tian,
“Mining mobile user preferences for personalized
context-aware recommendation”, ACM Trans. Intell.
Syst. Technol., vol. 5, no. 4, 2014, p. 58.
[10] I. Konstas, V. Stathopoulos, and J. M Jose, “On social
networks and collaborative recommendation”, ACM
SIGIR Conference on Research and Development in
Information Retrieval, 2009, pp. 195–202.
[11] J. Breese, D. Heckerman, and C. Kadie, “Empirical
analysis of predictive algorithms for collaborative
filtering”, in Proc. 14th Ann. Conf. Uncertainty Artif.
Intell., 1998, pp. 43–52.
[12] J. L. Herlocker, J. a. Konstan, L. G. Terveen, and J. T.
Riedl, “Evaluating collaborative filtering recommender
systems”, ACM Trans. Inf. Syst., vol. 22, no. 1, Jan.
2004, pp. 5–53.
[13] J.-M. Chen, M.-C. Chen, and Y. S. Sun, “A tag based
learning approach to knowledge acquisition for
constructing prior knowledge and enhancing student
reading comprehension”, Comput. Education, vol. 70,
2014, pp. 256–268.
[14] J. S. Breese, D. Heckerman, and C. Kadie (1998),
"Empirical analysis of predictive algorithms for
collaborative filtering", In Proceedings of the Fourteenth
conference on Uncertainty in artificial intelligence
(UAI'98), 2013, pp. 43-52.
[15] J. Peng, D.D. Zeng, H. Zhao, and F. Wang,
“Collaborative filtering in social tagging systems based
on joint item-tag recommendations”, ACM International
Conference on Information and Knowledge Management,
2010, pp. 809–818.
[16] J. Su, H. Yeh, P. Yu, and V. Tseng, “Music
recommendation using content and context information
mining”, Intell. Syst., vol. 25, no. 1, 2010, pp. 16–26.
[17] K. H. L. Tso-Sutter, L. B. Marinho, and L. Schmidt-
Thieme, “Tag-aware recommender systems by fusion of
collaborative filtering algorithms”, ACM SIGAPP
Symposium on Applied computing, 2008, pp. 1995–
1999.
[18] K. Yu, B. Zhang, H. Zhu, H. Cao, and J. Tian, “Towards
personalized context-aware recommendation by mining
context logs through topic models”, in Proc. 16th Pacific-
Asia Conf. Adv. Knowl. Discovery Data Mining, 2012,
pp. 431–443.
[19] Kim, H.-N., Rawashdeh, M., Alghamdi, A., & El
Saddik, A., “Folksonomy-based personalized search and
ranking in social media services”, Information Systems,
vol. 37, no. 1, 2012, pp. 61–76.
[20] Mohammed F. Alhamid, Majdi Rawashdeh, Haiwei
Dong, M. Anwar Hossain , Abdulmotaleb El Saddik,
“Exploring latent preferences for context-aware
personalized recommendation systems”, IEEE
Transactions on Human-Machine Systems, vol.46 n.4, ,
August 2016, pp. 615-623.
[21] M. F. Alhamid, M. Rawashdeh, H. Al Osman, M. S.
Hossain, and A. El Saddik, “Towards context-sensitive
collaborative media recommender system”, Multimedia
Tools Appl., vol. 74, 2015, pp. 11399–11428.
[22] M. Deshpande and G. Karypis, “Item-based top-N
recommendation algorithms”, ACM Trans. Inf. Syst.,
vol. 22, no. 1, 2004, pp. 143–177.
[23] M. Jamali and M. Ester, “TrustWalker: a random walk
model for combining trust-based and item-based
recommendation”, ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining,
2009, pp. 397–406.
[24] Q. Qi, Z. Chen, J. Liu, C. Hui, and Q. Wu, “Using
inferred tag ratings to improve user-based collaborative
filtering”, ACM SIGAPP Symposium on Applied
Computing, 2012, pp. 2008–2013.
[25] Shi, Y., Larson, M., & Hanjalic, A., “Mining contextual
movie similarity with matrix factorization for contextaware
recommendation”, ACM Transactions on
Intelligent Systems and Technology, vol. 4, no. 1, 2013,
pp.1–19. [26] Shin, D., Lee, J.-W., Yeon, J., & Lee, S.-G., “Contextaware
recommendation by aggregating user context”, In
Proceedings of the IEEE conference on commerce and
enterprise computing, 2009, pp. 423–430.
[27] T. Bertin-Mahieu, Daniel P.W. Ellis, B. Whitman, and
P. Lamere, “The million song dataset”, In Proceedings of
the ISMIR, 2011.
[28] Thollot, R., “Dynamic situation monitoring and contextaware
BI recommendations”, Ph.D. dissertation, Ecole
Centrale Paris, 2012.
[29] V. Zanardi and L. Capra, “Social ranking: uncovering
relevant content using tag-based recommender systems”,
in Proc. ACM Conf. Recommender Syst., 2008, pp. 51–
58.
[30] Y. Koren, R. Bell, and C. Volinsky, “Matrix
factorization techniques for recommender systems”,
IEEE Comput., vol. 42, no. 8, Aug. 2009, pp. 30-37.