Cargando…

A serendipity-biased Deepwalk for collaborators recommendation

Scientific collaboration has become a common behaviour in academia. Various recommendation strategies have been designed to provide relevant collaborators for the target scholars. However, scholars are no longer satisfied with the acquainted collaborator recommendations, which may narrow their horiz...

Descripción completa

Detalles Bibliográficos
Autores principales: Xu, Zhenzhen, Yuan, Yuyuan, Wei, Haoran, Wan, Liangtian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924530/
https://www.ncbi.nlm.nih.gov/pubmed/33816831
http://dx.doi.org/10.7717/peerj-cs.178
_version_ 1783659109004869632
author Xu, Zhenzhen
Yuan, Yuyuan
Wei, Haoran
Wan, Liangtian
author_facet Xu, Zhenzhen
Yuan, Yuyuan
Wei, Haoran
Wan, Liangtian
author_sort Xu, Zhenzhen
collection PubMed
description Scientific collaboration has become a common behaviour in academia. Various recommendation strategies have been designed to provide relevant collaborators for the target scholars. However, scholars are no longer satisfied with the acquainted collaborator recommendations, which may narrow their horizons. Serendipity in the recommender system has attracted increasing attention from researchers in recent years. Serendipity traditionally denotes the faculty of making surprising discoveries. The unexpected and valuable scientific discoveries in science such as X-rays and penicillin may be attributed to serendipity. In this paper, we design a novel recommender system to provide serendipitous scientific collaborators, which learns the serendipity-biased vector representation of each node in the co-author network. We first introduce the definition of serendipitous collaborators from three components of serendipity: relevance, unexpectedness, and value, respectively. Then we improve the transition probability of random walk in DeepWalk, and propose a serendipity-biased DeepWalk, called Seren2vec. The walker jumps to the next neighbor node with the proportional probability of edge weight in the co-author network. Meanwhile, the edge weight is determined by the three indices in definition. Finally, Top-N serendipitous collaborators are generated based on the cosine similarity between scholar vectors. We conducted extensive experiments on the DBLP data set to validate our recommendation performance, and the evaluations from serendipity-based metrics show that Seren2vec outperforms other baseline methods without much loss of recommendation accuracy.
format Online
Article
Text
id pubmed-7924530
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-79245302021-04-02 A serendipity-biased Deepwalk for collaborators recommendation Xu, Zhenzhen Yuan, Yuyuan Wei, Haoran Wan, Liangtian PeerJ Comput Sci Data Mining and Machine Learning Scientific collaboration has become a common behaviour in academia. Various recommendation strategies have been designed to provide relevant collaborators for the target scholars. However, scholars are no longer satisfied with the acquainted collaborator recommendations, which may narrow their horizons. Serendipity in the recommender system has attracted increasing attention from researchers in recent years. Serendipity traditionally denotes the faculty of making surprising discoveries. The unexpected and valuable scientific discoveries in science such as X-rays and penicillin may be attributed to serendipity. In this paper, we design a novel recommender system to provide serendipitous scientific collaborators, which learns the serendipity-biased vector representation of each node in the co-author network. We first introduce the definition of serendipitous collaborators from three components of serendipity: relevance, unexpectedness, and value, respectively. Then we improve the transition probability of random walk in DeepWalk, and propose a serendipity-biased DeepWalk, called Seren2vec. The walker jumps to the next neighbor node with the proportional probability of edge weight in the co-author network. Meanwhile, the edge weight is determined by the three indices in definition. Finally, Top-N serendipitous collaborators are generated based on the cosine similarity between scholar vectors. We conducted extensive experiments on the DBLP data set to validate our recommendation performance, and the evaluations from serendipity-based metrics show that Seren2vec outperforms other baseline methods without much loss of recommendation accuracy. PeerJ Inc. 2019-03-04 /pmc/articles/PMC7924530/ /pubmed/33816831 http://dx.doi.org/10.7717/peerj-cs.178 Text en ©2019 Xu et al. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Data Mining and Machine Learning
Xu, Zhenzhen
Yuan, Yuyuan
Wei, Haoran
Wan, Liangtian
A serendipity-biased Deepwalk for collaborators recommendation
title A serendipity-biased Deepwalk for collaborators recommendation
title_full A serendipity-biased Deepwalk for collaborators recommendation
title_fullStr A serendipity-biased Deepwalk for collaborators recommendation
title_full_unstemmed A serendipity-biased Deepwalk for collaborators recommendation
title_short A serendipity-biased Deepwalk for collaborators recommendation
title_sort serendipity-biased deepwalk for collaborators recommendation
topic Data Mining and Machine Learning
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924530/
https://www.ncbi.nlm.nih.gov/pubmed/33816831
http://dx.doi.org/10.7717/peerj-cs.178
work_keys_str_mv AT xuzhenzhen aserendipitybiaseddeepwalkforcollaboratorsrecommendation
AT yuanyuyuan aserendipitybiaseddeepwalkforcollaboratorsrecommendation
AT weihaoran aserendipitybiaseddeepwalkforcollaboratorsrecommendation
AT wanliangtian aserendipitybiaseddeepwalkforcollaboratorsrecommendation
AT xuzhenzhen serendipitybiaseddeepwalkforcollaboratorsrecommendation
AT yuanyuyuan serendipitybiaseddeepwalkforcollaboratorsrecommendation
AT weihaoran serendipitybiaseddeepwalkforcollaboratorsrecommendation
AT wanliangtian serendipitybiaseddeepwalkforcollaboratorsrecommendation