摘要People in the Internet era have to cope with information overload and expend great effort on finding what they need. Recent experiments indicate that recommendations based on users' past activities are usually less favored than those based on social relationships, and thus many researchers have proposed adaptive algorithms on social recommendation. However, in those methods, quite a number of users have little chance to recommend information, which might prevent valuable information from spreading. We present an improved algorithm that allows more users to have enough followers to spread information. Experimental results demonstrate that both recommendation precision and spreading effectiveness of our method can be improved significantly.
Abstract：People in the Internet era have to cope with information overload and expend great effort on finding what they need. Recent experiments indicate that recommendations based on users' past activities are usually less favored than those based on social relationships, and thus many researchers have proposed adaptive algorithms on social recommendation. However, in those methods, quite a number of users have little chance to recommend information, which might prevent valuable information from spreading. We present an improved algorithm that allows more users to have enough followers to spread information. Experimental results demonstrate that both recommendation precision and spreading effectiveness of our method can be improved significantly.
CHEN Duan-Bing**,GAO Hui. An Improved Adaptive model for Information Recommending and Spreading[J]. 中国物理快报, 2012, 29(4): 48901-048901.
CHEN Duan-Bing**,GAO Hui. An Improved Adaptive model for Information Recommending and Spreading. Chin. Phys. Lett., 2012, 29(4): 48901-048901.
[1] Al sawalha M M and Noorani M S M 2011 Chin. Phys. Lett. 28 110507[2] Meng Q K 2011 Chin. Phys. Lett. 28 118901[3] Resnick P and Varian H R 1997 Commun. ACM 40 56[4] Herlocker J L, Konstan J A, Terveen L G and Riedl J T 2004 ACM Trans. Inf. Syst. 22 5[5] Adomavicius G and Tuzhilin A 2005 IEEE Trans. Knowl. Data. Eng. 17 734[6] Linden G, Smith B and York J 2003 IEEE Internet Comput. 7 76[7] Breese J S, Heckerman D and Kadie C 1998 Proc. 14th Conference on Uncertainty in Artificial Intelligence p 43[8] Hofmann T 2004 ACM Trans. Inf. Syst. 22 89[9] Maslov S and Zhang Y C 2001 Phys. Rev. Lett. 87 248701[10] Koren Y, Bell R and Volinsky C 2009 Comput. 42 30[11] Pan X, Deng G S and Liu J G 2010 Chin. Phys. Lett. 27 068903[12] Shang M S and Zhang Z K 2009 Chin. Phys. Lett. 26 118903[13] Zhou T, Kuscsik Z, Liu J G, Medo M, Wakeling J R and Zhang Y C 2010 Proc. Natl. Acad. Sci. USA 107 4511[14] Liu J G, Zhou T and Guo Q 2011 Phys. Rev. E 84 037101[15] Huang J, Cheng X Q, Shen H W, Zhou T and Jin X 2012 Proc. 5th ACM WSDM (Washington, USA 8–12 February 2012)[16] Leskovec J, Adamic L A and Huberman B A 2007 ACM Trans. Web 1 5[17] Medo M, Zhang Y C and Zhou T 2009 Eur. Phys. Lett. 88 38005[18] Wei D, Zhou T, Cimini G, Wu P, Liu W and Zhang Y C 2011 Physica A 390 2117[19] Cimini G, Medo M, Zhou T, Wei D and Zhang Y C 2011 Eur. Phys. J. B 80 201[20] Sinha R and Swearingen K 2001 Proc. DELOS NSF Workshop on Personalisation and Recommender Systems in Digital Libraries (Dublin: City University 18-20 June 2001)[21] Golbeck J 2008 Science 321 1640[22] Zhou T, Liu J G, Bai W J, Chen G and Wang B H 2006 Phys. Rev. E 74 056109[23] Sun M, Chen Y, Cao L and Wang X F 2012 Chin. Phys. Lett. 29 020503[24] Zhu C P, Wang L, Liu X T and Yan Z J 2012 Chin. Phys. Lett. 29 010504[25] Newman M E J, Forrest S and Balthrop J 2002 Phys. Rev. E 66 035101[26] Fagiolo G 2007 Phys. Rev. E 76 026107[27] Hu H B and Wang X F 2008 Physica A 387 3769[28] Newman M E J 2002 Phys. Rev. Lett. 89 208701[29] Tang J, Qu L C and Luo J M 2011 Chin. Phys. Lett. 28 100501
2012, Vol. 29 
