Cross-domain citation recommendation based on hybrid topic model and co-citation selection citation selection

Supaporn Tantanasiriwong, Sumanta Guha, Paul Janecek, Choochart Haruechaiyasak, Leif Azzopardi

Research output: Contribution to journalArticle

Abstract

Cross-domain recommendations are of growing importance in the research community. An application of particular interest is to recommend a set of relevant research papers as citations for a given patent. This paper proposes an approach for cross-domain citation recommendation based on the hybrid topic model and co-citation selection. Using the topic model, relevant terms from documents could be clustered into the same topics. In addition, the co-citation selection technique will help select citations based on a set of highly similar patents. To evaluate the performance, we compared our proposed approach with the traditional baseline approaches using a corpus of patents collected for different technological fields of biotechnology, environmental technology, medical technology and nanotechnology. Experimental results show our cross domain citation recommendation yields a higher performance in predicting relevant publication citations than all baseline approaches.

LanguageEnglish
Pages220-236
Number of pages17
JournalInternational Journal of Data Mining, Modelling and Management
Volume9
Issue number3
Early online date13 Sep 2017
DOIs
Publication statusE-pub ahead of print - 13 Sep 2017

Fingerprint

Citations
Recommendations
Environmental technology
Biotechnology
Nanotechnology
Patents
Baseline
Model
Topic model
Co-citation
High Performance
Evaluate
Experimental Results
Term

Keywords

  • analysis of variance
  • Anova
  • ccs
  • cdcr
  • co-citation selection
  • cross domain citation recommendation
  • cross domain recommender system
  • evaluation
  • information retrieval
  • keyphrase extraction tool
  • similarity measures
  • topic model

Cite this

Tantanasiriwong, Supaporn ; Guha, Sumanta ; Janecek, Paul ; Haruechaiyasak, Choochart ; Azzopardi, Leif. / Cross-domain citation recommendation based on hybrid topic model and co-citation selection citation selection. In: International Journal of Data Mining, Modelling and Management. 2017 ; Vol. 9, No. 3. pp. 220-236.
@article{ac5c0962b9ea418d841790aed0eefc08,
title = "Cross-domain citation recommendation based on hybrid topic model and co-citation selection citation selection",
abstract = "Cross-domain recommendations are of growing importance in the research community. An application of particular interest is to recommend a set of relevant research papers as citations for a given patent. This paper proposes an approach for cross-domain citation recommendation based on the hybrid topic model and co-citation selection. Using the topic model, relevant terms from documents could be clustered into the same topics. In addition, the co-citation selection technique will help select citations based on a set of highly similar patents. To evaluate the performance, we compared our proposed approach with the traditional baseline approaches using a corpus of patents collected for different technological fields of biotechnology, environmental technology, medical technology and nanotechnology. Experimental results show our cross domain citation recommendation yields a higher performance in predicting relevant publication citations than all baseline approaches.",
keywords = "analysis of variance, Anova, ccs, cdcr, co-citation selection, cross domain citation recommendation, cross domain recommender system, evaluation, information retrieval, keyphrase extraction tool, similarity measures, topic model",
author = "Supaporn Tantanasiriwong and Sumanta Guha and Paul Janecek and Choochart Haruechaiyasak and Leif Azzopardi",
year = "2017",
month = "9",
day = "13",
doi = "10.1504/IJDMMM.2017.086566",
language = "English",
volume = "9",
pages = "220--236",
journal = "International Journal of Data Mining, Modelling and Management",
issn = "1759-1163",
number = "3",

}

Cross-domain citation recommendation based on hybrid topic model and co-citation selection citation selection. / Tantanasiriwong, Supaporn; Guha, Sumanta; Janecek, Paul; Haruechaiyasak, Choochart; Azzopardi, Leif.

In: International Journal of Data Mining, Modelling and Management, Vol. 9, No. 3, 13.09.2017, p. 220-236.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Cross-domain citation recommendation based on hybrid topic model and co-citation selection citation selection

AU - Tantanasiriwong, Supaporn

AU - Guha, Sumanta

AU - Janecek, Paul

AU - Haruechaiyasak, Choochart

AU - Azzopardi, Leif

PY - 2017/9/13

Y1 - 2017/9/13

N2 - Cross-domain recommendations are of growing importance in the research community. An application of particular interest is to recommend a set of relevant research papers as citations for a given patent. This paper proposes an approach for cross-domain citation recommendation based on the hybrid topic model and co-citation selection. Using the topic model, relevant terms from documents could be clustered into the same topics. In addition, the co-citation selection technique will help select citations based on a set of highly similar patents. To evaluate the performance, we compared our proposed approach with the traditional baseline approaches using a corpus of patents collected for different technological fields of biotechnology, environmental technology, medical technology and nanotechnology. Experimental results show our cross domain citation recommendation yields a higher performance in predicting relevant publication citations than all baseline approaches.

AB - Cross-domain recommendations are of growing importance in the research community. An application of particular interest is to recommend a set of relevant research papers as citations for a given patent. This paper proposes an approach for cross-domain citation recommendation based on the hybrid topic model and co-citation selection. Using the topic model, relevant terms from documents could be clustered into the same topics. In addition, the co-citation selection technique will help select citations based on a set of highly similar patents. To evaluate the performance, we compared our proposed approach with the traditional baseline approaches using a corpus of patents collected for different technological fields of biotechnology, environmental technology, medical technology and nanotechnology. Experimental results show our cross domain citation recommendation yields a higher performance in predicting relevant publication citations than all baseline approaches.

KW - analysis of variance

KW - Anova

KW - ccs

KW - cdcr

KW - co-citation selection

KW - cross domain citation recommendation

KW - cross domain recommender system

KW - evaluation

KW - information retrieval

KW - keyphrase extraction tool

KW - similarity measures

KW - topic model

UR - http://www.scopus.com/inward/record.url?scp=85029524788&partnerID=8YFLogxK

U2 - 10.1504/IJDMMM.2017.086566

DO - 10.1504/IJDMMM.2017.086566

M3 - Article

VL - 9

SP - 220

EP - 236

JO - International Journal of Data Mining, Modelling and Management

T2 - International Journal of Data Mining, Modelling and Management

JF - International Journal of Data Mining, Modelling and Management

SN - 1759-1163

IS - 3

ER -