A paper recommendation system with readerbench: the graphical visualization of semantically related papers and concepts

Ionut Cristian Paraschiv, Mihai Dascalu, Philippe Dessus, Stefan Trausan-Matu, Danielle McNamara

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The task of tagging papers with semantic metadata in order to analyze their relatedness represents a good foundation for a paper recommender system. The analysis from this paper extends from previous research in order to create a graph of papers from a specific domain with the purpose of determining each article’s importance within the considered corpus of papers. Moreover, as non-latent representations are powerful when used in conjunction with latent ones, our system retrieves semantically close words, not present in the paper, in order to improve the retrieval of papers. Our previous analyses used the semantic representation of papers in different semantic models with the purpose of creating visual graphs based on the semantic relatedness links between the abstracts. The current analysis takes a step forward by proposing a model that can suggest which papers are of the highest relevance, share similar concepts, and are semantically related with the initial query. Our study is performed using paper abstracts in the field of information technology extracted from the Web of Science citation index. The research includes a use case and its corresponding results by using interactive and exploratory network graph representations.

Original languageEnglish (US)
Pages (from-to)445-451
Number of pages7
JournalLecture Notes in Educational Technology
Issue number9789812878663
DOIs
StatePublished - 2016

Fingerprint

Recommender systems
visualization
Visualization
Semantics
semantics
Metadata
Information technology
information technology
science

Keywords

  • Discourse analysis
  • Paper recommendation system
  • Scientometrics
  • Semantic similarity

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Education

Cite this

A paper recommendation system with readerbench : the graphical visualization of semantically related papers and concepts. / Paraschiv, Ionut Cristian; Dascalu, Mihai; Dessus, Philippe; Trausan-Matu, Stefan; McNamara, Danielle.

In: Lecture Notes in Educational Technology, No. 9789812878663, 2016, p. 445-451.

Research output: Contribution to journalArticle

Paraschiv, Ionut Cristian ; Dascalu, Mihai ; Dessus, Philippe ; Trausan-Matu, Stefan ; McNamara, Danielle. / A paper recommendation system with readerbench : the graphical visualization of semantically related papers and concepts. In: Lecture Notes in Educational Technology. 2016 ; No. 9789812878663. pp. 445-451.
@article{092d03e720104701936210dea1d062e9,
title = "A paper recommendation system with readerbench: the graphical visualization of semantically related papers and concepts",
abstract = "The task of tagging papers with semantic metadata in order to analyze their relatedness represents a good foundation for a paper recommender system. The analysis from this paper extends from previous research in order to create a graph of papers from a specific domain with the purpose of determining each article’s importance within the considered corpus of papers. Moreover, as non-latent representations are powerful when used in conjunction with latent ones, our system retrieves semantically close words, not present in the paper, in order to improve the retrieval of papers. Our previous analyses used the semantic representation of papers in different semantic models with the purpose of creating visual graphs based on the semantic relatedness links between the abstracts. The current analysis takes a step forward by proposing a model that can suggest which papers are of the highest relevance, share similar concepts, and are semantically related with the initial query. Our study is performed using paper abstracts in the field of information technology extracted from the Web of Science citation index. The research includes a use case and its corresponding results by using interactive and exploratory network graph representations.",
keywords = "Discourse analysis, Paper recommendation system, Scientometrics, Semantic similarity",
author = "Paraschiv, {Ionut Cristian} and Mihai Dascalu and Philippe Dessus and Stefan Trausan-Matu and Danielle McNamara",
year = "2016",
doi = "10.1007/978-981-287-868-7_53",
language = "English (US)",
pages = "445--451",
journal = "Lecture Notes in Educational Technology",
issn = "2196-4963",
publisher = "Springer International Publishing AG",
number = "9789812878663",

}

TY - JOUR

T1 - A paper recommendation system with readerbench

T2 - the graphical visualization of semantically related papers and concepts

AU - Paraschiv, Ionut Cristian

AU - Dascalu, Mihai

AU - Dessus, Philippe

AU - Trausan-Matu, Stefan

AU - McNamara, Danielle

PY - 2016

Y1 - 2016

N2 - The task of tagging papers with semantic metadata in order to analyze their relatedness represents a good foundation for a paper recommender system. The analysis from this paper extends from previous research in order to create a graph of papers from a specific domain with the purpose of determining each article’s importance within the considered corpus of papers. Moreover, as non-latent representations are powerful when used in conjunction with latent ones, our system retrieves semantically close words, not present in the paper, in order to improve the retrieval of papers. Our previous analyses used the semantic representation of papers in different semantic models with the purpose of creating visual graphs based on the semantic relatedness links between the abstracts. The current analysis takes a step forward by proposing a model that can suggest which papers are of the highest relevance, share similar concepts, and are semantically related with the initial query. Our study is performed using paper abstracts in the field of information technology extracted from the Web of Science citation index. The research includes a use case and its corresponding results by using interactive and exploratory network graph representations.

AB - The task of tagging papers with semantic metadata in order to analyze their relatedness represents a good foundation for a paper recommender system. The analysis from this paper extends from previous research in order to create a graph of papers from a specific domain with the purpose of determining each article’s importance within the considered corpus of papers. Moreover, as non-latent representations are powerful when used in conjunction with latent ones, our system retrieves semantically close words, not present in the paper, in order to improve the retrieval of papers. Our previous analyses used the semantic representation of papers in different semantic models with the purpose of creating visual graphs based on the semantic relatedness links between the abstracts. The current analysis takes a step forward by proposing a model that can suggest which papers are of the highest relevance, share similar concepts, and are semantically related with the initial query. Our study is performed using paper abstracts in the field of information technology extracted from the Web of Science citation index. The research includes a use case and its corresponding results by using interactive and exploratory network graph representations.

KW - Discourse analysis

KW - Paper recommendation system

KW - Scientometrics

KW - Semantic similarity

UR - http://www.scopus.com/inward/record.url?scp=84986555473&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986555473&partnerID=8YFLogxK

U2 - 10.1007/978-981-287-868-7_53

DO - 10.1007/978-981-287-868-7_53

M3 - Article

AN - SCOPUS:84986555473

SP - 445

EP - 451

JO - Lecture Notes in Educational Technology

JF - Lecture Notes in Educational Technology

SN - 2196-4963

IS - 9789812878663

ER -