Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend Recommendation

Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend Recommendation

Online friend recommendation is a fast developing topic in web mining. In this paper, we used SVD matrix factorization to model user and item feature vector and used stochastic gradient descent to amend parameter and improve accuracy. To tackle cold start problem and data sparsity, we used KNN model...

Full description

Bibliographic Details
Main Authors: Qu Li, Min Yao, Jianhua Yang, Ning Xu
Format: Article
Language:English
Published: Hindawi Limited 2014-01-01
Series:The Scientific World Journal
Online Access:http://dx.doi.org/10.1155/2014/162148
id doaj-145d705501bb42fe8715b5bf66670ed8
record_format Article
spelling doaj-145d705501bb42fe8715b5bf66670ed82020-11-25T00:53:46ZengHindawi LimitedThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/162148162148Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend RecommendationQu Li0Min Yao1Jianhua Yang2Ning Xu3College of Computer Science, Zhejiang University, Hangzhou 310027, ChinaCollege of Computer Science, Zhejiang University, Hangzhou 310027, ChinaCollege of Computer Science, Zhejiang University, Hangzhou 310027, ChinaCollege of Computer Science, Zhejiang University, Hangzhou 310027, ChinaOnline friend recommendation is a fast developing topic in web mining. In this paper, we used SVD matrix factorization to model user and item feature vector and used stochastic gradient descent to amend parameter and improve accuracy. To tackle cold start problem and data sparsity, we used KNN model to influence user feature vector. At the same time, we used graph theory to partition communities with fairly low time and space complexity. What is more, matrix factorization can combine online and offline recommendation. Experiments showed that the hybrid recommendation algorithm is able to recommend online friends with good accuracy.http://dx.doi.org/10.1155/2014/162148
collection DOAJ
language English
format Article
sources DOAJ
author Qu Li
Min Yao
Jianhua Yang
Ning Xu
spellingShingle Qu Li
Min Yao
Jianhua Yang
Ning Xu
Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend Recommendation
The Scientific World Journal
author_facet Qu Li
Min Yao
Jianhua Yang
Ning Xu
author_sort Qu Li
title Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend Recommendation
title_short Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend Recommendation
title_full Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend Recommendation
title_fullStr Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend Recommendation
title_full_unstemmed Genetic Algorithm and Graph Theory Based Matrix Factorization Method for Online Friend Recommendation
title_sort genetic algorithm and graph theory based matrix factorization method for online friend recommendation
publisher Hindawi Limited
series The Scientific World Journal
issn 2356-6140
1537-744X
publishDate 2014-01-01
description Online friend recommendation is a fast developing topic in web mining. In this paper, we used SVD matrix factorization to model user and item feature vector and used stochastic gradient descent to amend parameter and improve accuracy. To tackle cold start problem and data sparsity, we used KNN model to influence user feature vector. At the same time, we used graph theory to partition communities with fairly low time and space complexity. What is more, matrix factorization can combine online and offline recommendation. Experiments showed that the hybrid recommendation algorithm is able to recommend online friends with good accuracy.
url http://dx.doi.org/10.1155/2014/162148
work_keys_str_mv AT quli geneticalgorithmandgraphtheorybasedmatrixfactorizationmethodforonlinefriendrecommendation
AT minyao geneticalgorithmandgraphtheorybasedmatrixfactorizationmethodforonlinefriendrecommendation
AT jianhuayang geneticalgorithmandgraphtheorybasedmatrixfactorizationmethodforonlinefriendrecommendation
AT ningxu geneticalgorithmandgraphtheorybasedmatrixfactorizationmethodforonlinefriendrecommendation
_version_ 1725236506568687616

Similar Items