doi: 10.4304/jsw.9.8.2223-2231
Applying Bi-directional Link Mining in Personalized Recommendation
- 1 Institute of Information Science and Engineering, Shandong Normal University, Jinan, China; Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology, Jinan, China
- 2 Department of Earth Sciences, ZheJiang University, Hangzhou, China
Abstract
Recently, many researchers have been attractedin link prediction which is an effective technique to be usedin graph based models analysis. By using link predictionmethod we can understand associations between nodes. Tothe best of our knowledge, most of previous works in thisarea have not explored the prediction of links in dynamicMulti-dimension Networks and have not explored theprediction of links which could disappear in the future. Weargue that these kinds of links are important. At least theycan do complement for current link prediction processes inorder to plan better for the future. In this paper, we proposea link prediction model, which is capable of predicting bidirectionlinks that might exist and may disappear in thefuture in dynamic Multi-dimension Networks. Firstly, wepresent the definition of multi-dimensional networks,reduction dimension networks and dynamic networks. Thenwe put forward some algorithms which build MultidimensionNetworks, reduction dimension networks anddynamic networks. After that, we give bi-direction linkprediction algorithms in dynamic multi-dimension weightednetworks. At the end, algorithms above are applied inrecommendation networks. Experimental results show thatthese algorithms can improve the link predictionperformance in dynamic multi-dimensional weightednetworks.
Keywords
- bi-directional link mining
- multi-dimens
How to Cite
Hong Wang and Yanshen Sun, "Applying Bi-directional Link Mining in Personalized Recommendation," Journal of Software, vol. 9, no. 8, pp. 2223-2231, 2014. https://doi.org/ 10.4304/jsw.9.8.2223-2231
Copyright & License
Copyright © 2014 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).