Most existing methods on research collaborator recommendation focus on promoting collaboration within a specific discipline and exploit a network structure derived from co-authorship or co-citation information. To find collaboration opportunities outside researchers' own fields of expertise and beyond their social network, we present an interdisciplinary collaborator recommendation method based on research content similarity. In the proposed method, we calculate textual features that reflect a researcher's interests using a research grant database. To find the most relevant researchers who work in other fields, we compare constructing a pairwise similarity matrix in a feature space and exploiting existing social networks with content-based similarity. We present a case study at the Graduate University for Advanced Studies in Japan in which actual collaborations across departments are used as ground truth. The results indicate that our content-based approach can accurately predict interdisciplinary collaboration compared with the conventional collaboration network-based approaches.
Masataka ARAKI
Doshisha University
Marie KATSURAI
Doshisha University
Ikki OHMUKAI
National Institute of Infomatics
Hideaki TAKEDA
National Institute of Infomatics
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Masataka ARAKI, Marie KATSURAI, Ikki OHMUKAI, Hideaki TAKEDA, "Interdisciplinary Collaborator Recommendation Based on Research Content Similarity" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 4, pp. 785-792, April 2017, doi: 10.1587/transinf.2016DAP0030.
Abstract: Most existing methods on research collaborator recommendation focus on promoting collaboration within a specific discipline and exploit a network structure derived from co-authorship or co-citation information. To find collaboration opportunities outside researchers' own fields of expertise and beyond their social network, we present an interdisciplinary collaborator recommendation method based on research content similarity. In the proposed method, we calculate textual features that reflect a researcher's interests using a research grant database. To find the most relevant researchers who work in other fields, we compare constructing a pairwise similarity matrix in a feature space and exploiting existing social networks with content-based similarity. We present a case study at the Graduate University for Advanced Studies in Japan in which actual collaborations across departments are used as ground truth. The results indicate that our content-based approach can accurately predict interdisciplinary collaboration compared with the conventional collaboration network-based approaches.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016DAP0030/_p
Copy
@ARTICLE{e100-d_4_785,
author={Masataka ARAKI, Marie KATSURAI, Ikki OHMUKAI, Hideaki TAKEDA, },
journal={IEICE TRANSACTIONS on Information},
title={Interdisciplinary Collaborator Recommendation Based on Research Content Similarity},
year={2017},
volume={E100-D},
number={4},
pages={785-792},
abstract={Most existing methods on research collaborator recommendation focus on promoting collaboration within a specific discipline and exploit a network structure derived from co-authorship or co-citation information. To find collaboration opportunities outside researchers' own fields of expertise and beyond their social network, we present an interdisciplinary collaborator recommendation method based on research content similarity. In the proposed method, we calculate textual features that reflect a researcher's interests using a research grant database. To find the most relevant researchers who work in other fields, we compare constructing a pairwise similarity matrix in a feature space and exploiting existing social networks with content-based similarity. We present a case study at the Graduate University for Advanced Studies in Japan in which actual collaborations across departments are used as ground truth. The results indicate that our content-based approach can accurately predict interdisciplinary collaboration compared with the conventional collaboration network-based approaches.},
keywords={},
doi={10.1587/transinf.2016DAP0030},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Interdisciplinary Collaborator Recommendation Based on Research Content Similarity
T2 - IEICE TRANSACTIONS on Information
SP - 785
EP - 792
AU - Masataka ARAKI
AU - Marie KATSURAI
AU - Ikki OHMUKAI
AU - Hideaki TAKEDA
PY - 2017
DO - 10.1587/transinf.2016DAP0030
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2017
AB - Most existing methods on research collaborator recommendation focus on promoting collaboration within a specific discipline and exploit a network structure derived from co-authorship or co-citation information. To find collaboration opportunities outside researchers' own fields of expertise and beyond their social network, we present an interdisciplinary collaborator recommendation method based on research content similarity. In the proposed method, we calculate textual features that reflect a researcher's interests using a research grant database. To find the most relevant researchers who work in other fields, we compare constructing a pairwise similarity matrix in a feature space and exploiting existing social networks with content-based similarity. We present a case study at the Graduate University for Advanced Studies in Japan in which actual collaborations across departments are used as ground truth. The results indicate that our content-based approach can accurately predict interdisciplinary collaboration compared with the conventional collaboration network-based approaches.
ER -