Context sensitive topic models for author influence in document networks

Saurabh Kataria, Prasenjit Mitra, Cornelia Caragea, C. Lee Giles

Research output: Chapter in Book/Report/Conference proceedingConference contribution

29 Citations (Scopus)

Abstract

In a document network such as a citation network of scientific documents, web-logs, etc., the content produced by authors exhibits their interest in certain topics. In addition some authors influence other authors' interests. In this work, we propose to model the influence of cited authors along with the interests of citing authors. Moreover, we hypothesize that apart from the citations present in documents, the context surrounding the citation mention provides extra topical information about the cited authors. However, associating terms in the context to the cited authors remains an open problem. We propose novel document generation schemes that incorporate the context while simultaneously modeling the interests of citing authors and influence of the cited authors. Our experiments show significant improvements over baseline models for various evaluation criteria such as link prediction between document and cited author, and quantitatively explaining unseen text.

Original languageEnglish
Title of host publicationIJCAI International Joint Conference on Artificial Intelligence
Pages2274-2280
Number of pages7
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event22nd International Joint Conference on Artificial Intelligence, IJCAI 2011 - Barcelona, Catalonia, Spain
Duration: 16 Jul 201122 Jul 2011

Other

Other22nd International Joint Conference on Artificial Intelligence, IJCAI 2011
CountrySpain
CityBarcelona, Catalonia
Period16/7/1122/7/11

Fingerprint

Experiments

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Kataria, S., Mitra, P., Caragea, C., & Giles, C. L. (2011). Context sensitive topic models for author influence in document networks. In IJCAI International Joint Conference on Artificial Intelligence (pp. 2274-2280) https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-379

Context sensitive topic models for author influence in document networks. / Kataria, Saurabh; Mitra, Prasenjit; Caragea, Cornelia; Giles, C. Lee.

IJCAI International Joint Conference on Artificial Intelligence. 2011. p. 2274-2280.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kataria, S, Mitra, P, Caragea, C & Giles, CL 2011, Context sensitive topic models for author influence in document networks. in IJCAI International Joint Conference on Artificial Intelligence. pp. 2274-2280, 22nd International Joint Conference on Artificial Intelligence, IJCAI 2011, Barcelona, Catalonia, Spain, 16/7/11. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-379
Kataria S, Mitra P, Caragea C, Giles CL. Context sensitive topic models for author influence in document networks. In IJCAI International Joint Conference on Artificial Intelligence. 2011. p. 2274-2280 https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-379
Kataria, Saurabh ; Mitra, Prasenjit ; Caragea, Cornelia ; Giles, C. Lee. / Context sensitive topic models for author influence in document networks. IJCAI International Joint Conference on Artificial Intelligence. 2011. pp. 2274-2280
@inproceedings{ce5ba025158d406daaf7931f69bc1f5e,
title = "Context sensitive topic models for author influence in document networks",
abstract = "In a document network such as a citation network of scientific documents, web-logs, etc., the content produced by authors exhibits their interest in certain topics. In addition some authors influence other authors' interests. In this work, we propose to model the influence of cited authors along with the interests of citing authors. Moreover, we hypothesize that apart from the citations present in documents, the context surrounding the citation mention provides extra topical information about the cited authors. However, associating terms in the context to the cited authors remains an open problem. We propose novel document generation schemes that incorporate the context while simultaneously modeling the interests of citing authors and influence of the cited authors. Our experiments show significant improvements over baseline models for various evaluation criteria such as link prediction between document and cited author, and quantitatively explaining unseen text.",
author = "Saurabh Kataria and Prasenjit Mitra and Cornelia Caragea and Giles, {C. Lee}",
year = "2011",
doi = "10.5591/978-1-57735-516-8/IJCAI11-379",
language = "English",
isbn = "9781577355120",
pages = "2274--2280",
booktitle = "IJCAI International Joint Conference on Artificial Intelligence",

}

TY - GEN

T1 - Context sensitive topic models for author influence in document networks

AU - Kataria, Saurabh

AU - Mitra, Prasenjit

AU - Caragea, Cornelia

AU - Giles, C. Lee

PY - 2011

Y1 - 2011

N2 - In a document network such as a citation network of scientific documents, web-logs, etc., the content produced by authors exhibits their interest in certain topics. In addition some authors influence other authors' interests. In this work, we propose to model the influence of cited authors along with the interests of citing authors. Moreover, we hypothesize that apart from the citations present in documents, the context surrounding the citation mention provides extra topical information about the cited authors. However, associating terms in the context to the cited authors remains an open problem. We propose novel document generation schemes that incorporate the context while simultaneously modeling the interests of citing authors and influence of the cited authors. Our experiments show significant improvements over baseline models for various evaluation criteria such as link prediction between document and cited author, and quantitatively explaining unseen text.

AB - In a document network such as a citation network of scientific documents, web-logs, etc., the content produced by authors exhibits their interest in certain topics. In addition some authors influence other authors' interests. In this work, we propose to model the influence of cited authors along with the interests of citing authors. Moreover, we hypothesize that apart from the citations present in documents, the context surrounding the citation mention provides extra topical information about the cited authors. However, associating terms in the context to the cited authors remains an open problem. We propose novel document generation schemes that incorporate the context while simultaneously modeling the interests of citing authors and influence of the cited authors. Our experiments show significant improvements over baseline models for various evaluation criteria such as link prediction between document and cited author, and quantitatively explaining unseen text.

UR - http://www.scopus.com/inward/record.url?scp=84871102871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871102871&partnerID=8YFLogxK

U2 - 10.5591/978-1-57735-516-8/IJCAI11-379

DO - 10.5591/978-1-57735-516-8/IJCAI11-379

M3 - Conference contribution

AN - SCOPUS:84871102871

SN - 9781577355120

SP - 2274

EP - 2280

BT - IJCAI International Joint Conference on Artificial Intelligence

ER -