File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Measuring Social Proximity via Knowledge Graph Embedding
Title | Measuring Social Proximity via Knowledge Graph Embedding |
---|---|
Authors | |
Issue Date | 2020 |
Citation | Proceedings of International Conference on Information Systems (ICIS) 2020: Making Digital Inclusive: Blending the Local and the Global, Virtual Conference, India, 13-16 December 2020, paper no. 1976 How to Cite? |
Abstract | Social proximity is a widely adopted measure to assess the social closeness between two entities in various business contexts. Existing social proximity measures are mainly based on social networks with one type of relationships or nodes and cannot effectively support applications in heterogeneous networks. In this study, we develop a novel social proximity measure named “Entity Proximity” through a knowledge graph embedding approach, which models different entities and their relations within a graph in continuous vector spaces. Compared with a number of existing measures, entity proximity not only provides a finer-grained assessment of social proximity but also is able to incorporate different types of relations and entities at the same time. We validate the proposed measure in the business context of venture capital investment. The results show that entity proximity is better at capturing the effect of social proximity on investment decisions than existing measures. |
Description | Track: Advances in Research Methods - Complete Paper - paper no. 1976 |
Persistent Identifier | http://hdl.handle.net/10722/304407 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Xu, R | - |
dc.contributor.author | Chen, H | - |
dc.contributor.author | Zhao, J | - |
dc.date.accessioned | 2021-09-23T08:59:36Z | - |
dc.date.available | 2021-09-23T08:59:36Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Proceedings of International Conference on Information Systems (ICIS) 2020: Making Digital Inclusive: Blending the Local and the Global, Virtual Conference, India, 13-16 December 2020, paper no. 1976 | - |
dc.identifier.uri | http://hdl.handle.net/10722/304407 | - |
dc.description | Track: Advances in Research Methods - Complete Paper - paper no. 1976 | - |
dc.description.abstract | Social proximity is a widely adopted measure to assess the social closeness between two entities in various business contexts. Existing social proximity measures are mainly based on social networks with one type of relationships or nodes and cannot effectively support applications in heterogeneous networks. In this study, we develop a novel social proximity measure named “Entity Proximity” through a knowledge graph embedding approach, which models different entities and their relations within a graph in continuous vector spaces. Compared with a number of existing measures, entity proximity not only provides a finer-grained assessment of social proximity but also is able to incorporate different types of relations and entities at the same time. We validate the proposed measure in the business context of venture capital investment. The results show that entity proximity is better at capturing the effect of social proximity on investment decisions than existing measures. | - |
dc.language | eng | - |
dc.relation.ispartof | International Conference on Information Systems (ICIS) 2020 | - |
dc.title | Measuring Social Proximity via Knowledge Graph Embedding | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Chen, H: chen19@hku.hk | - |
dc.identifier.authority | Chen, H=rp02520 | - |
dc.identifier.hkuros | 325099 | - |
dc.identifier.spage | paper no. 1976 | - |
dc.identifier.epage | paper no. 1976 | - |