community2vec: Vector representations of online communities encode semantic relationships

Trevor Martin


Abstract
Vector embeddings of words have been shown to encode meaningful semantic relationships that enable solving of complex analogies. This vector embedding concept has been extended successfully to many different domains and in this paper we both create and visualize vector representations of an unstructured collection of online communities based on user participation. Further, we quantitatively and qualitatively show that these representations allow solving of semantically meaningful community analogies and also other more general types of relationships. These results could help improve community recommendation engines and also serve as a tool for sociological studies of community relatedness.
Anthology ID:
W17-2904
Volume:
Proceedings of the Second Workshop on NLP and Computational Social Science
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Dirk Hovy, Svitlana Volkova, David Bamman, David Jurgens, Brendan O’Connor, Oren Tsur, A. Seza Doğruöz
Venue:
NLP+CSS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
27–31
Language:
URL:
https://aclanthology.org/W17-2904
DOI:
10.18653/v1/W17-2904
Bibkey:
Cite (ACL):
Trevor Martin. 2017. community2vec: Vector representations of online communities encode semantic relationships. In Proceedings of the Second Workshop on NLP and Computational Social Science, pages 27–31, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
community2vec: Vector representations of online communities encode semantic relationships (Martin, NLP+CSS 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/W17-2904.pdf