A Collaborative Filtering Algorithm based on Citation Information

DOI

10.2991/lemcs-15.2015.188How to use a DOI?

Keywords

Collaborative Filtering; Citation Information; Citation Network; Recommendation System

Abstract

Objective: With the rapid growing number of published scientific papers in the age of big data, users often find themselves difficult to select useful information from such massive academic information. This paper aims at the problems of collaborative filtering techniques in scientific citation data.Methods: This paper proposes an improved machine learning algorithm, that is designed to predict user ratings of academic theses by using Fisher Linear Regression combined with information of confidence scores, preference scores, the number of cooperative users in science citation data and the actual citation scores.Results: Multiple features considered in the algorithm have a positive impact on the recommendation results.Conclusion: This paper proposed a collaborative filtering recommendation algorithm combined with citation data analysis in order to improve the accuracy of predicted results. The experiments have shown that the proposed algorithm is proved to be effective and improve the accuracy of recommendation

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Tian Bai
AU  - Ye Wang
AU  - Lan Huang
AU  - Binzhao Ding
AU  - Jingbo Ning
PY  - 2015/07
DA  - 2015/07
TI  - A Collaborative Filtering Algorithm based on Citation Information
BT  - Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science
PB  - Atlantis Press
SP  - 952
EP  - 956
SN  - 1951-6851
UR  - https://doi.org/10.2991/lemcs-15.2015.188
DO  - 10.2991/lemcs-15.2015.188
ID  - Bai2015/07
ER  -