Methodologies for Improved Tag Cloud Generation with Clustering

Martin Leginus, Peter Dolog, Ricardo Gomes Lage, Frederico Durao

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

5 Citations (Scopus)

Abstract

Tag clouds are useful means for navigation in the social web
systems. Usually the systems implement the tag cloud generation based
on tag popularity which is not always the best method. In this paper
we propose methodologies on how to combine clustering into the tag
cloud generation to improve coverage and overlap. We study several clustering algorithms to generate tag clouds. We show that by extending
cloud generation based on tag popularity with clustering we slightly improve coverage. We also show that if the cloud is generated by clustering
independently of the tag popularity baseline we minimize overlap and
increase coverage. In the first case we therefore provide more items for a
user to explore. In the second case we provide more diverse items for a
user to explore. We experiment with the methodologies on two different
datasets: Delicious and Bibsonomy. The methodologies perform slightly
better on bibsonomy due to its specific focus. The best performing is the
hierarchical clustering.
Original languageEnglish
Title of host publicationProceedings of the 12th international conference on Web Engineering
Number of pages15
PublisherSpringer
Publication date2012
Pages61–75
DOIs
Publication statusPublished - 2012
EventInternational conference on Web Engineering - Berlin, Germany
Duration: 23 Jul 201227 Jul 2012
Conference number: 12

Conference

ConferenceInternational conference on Web Engineering
Number12
CountryGermany
CityBerlin
Period23/07/201227/07/2012
SeriesLecture Notes in Computer Science
ISSN0302-9743

Fingerprint

Clustering algorithms
Navigation
Experiments

Keywords

  • tag clouds
  • clustering

Cite this

Leginus, M., Dolog, P., Lage, R. G., & Durao, F. (2012). Methodologies for Improved Tag Cloud Generation with Clustering. In Proceedings of the 12th international conference on Web Engineering (pp. 61–75). Springer. Lecture Notes in Computer Science https://doi.org/10.1007/978-3-642-31753-8_5
Leginus, Martin ; Dolog, Peter ; Lage, Ricardo Gomes ; Durao, Frederico. / Methodologies for Improved Tag Cloud Generation with Clustering. Proceedings of the 12th international conference on Web Engineering. Springer, 2012. pp. 61–75 (Lecture Notes in Computer Science).
@inproceedings{f3e37fefbaa8461aa5663346ef79c7b2,
title = "Methodologies for Improved Tag Cloud Generation with Clustering",
abstract = "Tag clouds are useful means for navigation in the social websystems. Usually the systems implement the tag cloud generation basedon tag popularity which is not always the best method. In this paperwe propose methodologies on how to combine clustering into the tagcloud generation to improve coverage and overlap. We study several clustering algorithms to generate tag clouds. We show that by extendingcloud generation based on tag popularity with clustering we slightly improve coverage. We also show that if the cloud is generated by clusteringindependently of the tag popularity baseline we minimize overlap andincrease coverage. In the first case we therefore provide more items for auser to explore. In the second case we provide more diverse items for auser to explore. We experiment with the methodologies on two differentdatasets: Delicious and Bibsonomy. The methodologies perform slightlybetter on bibsonomy due to its specific focus. The best performing is thehierarchical clustering.",
keywords = "tag clouds, clustering",
author = "Martin Leginus and Peter Dolog and Lage, {Ricardo Gomes} and Frederico Durao",
year = "2012",
doi = "10.1007/978-3-642-31753-8_5",
language = "English",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "61–75",
booktitle = "Proceedings of the 12th international conference on Web Engineering",
address = "Germany",

}

Leginus, M, Dolog, P, Lage, RG & Durao, F 2012, Methodologies for Improved Tag Cloud Generation with Clustering. in Proceedings of the 12th international conference on Web Engineering. Springer, Lecture Notes in Computer Science, pp. 61–75, International conference on Web Engineering, Berlin, Germany, 23/07/2012. https://doi.org/10.1007/978-3-642-31753-8_5

Methodologies for Improved Tag Cloud Generation with Clustering. / Leginus, Martin; Dolog, Peter; Lage, Ricardo Gomes; Durao, Frederico.

Proceedings of the 12th international conference on Web Engineering. Springer, 2012. p. 61–75 (Lecture Notes in Computer Science).

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Methodologies for Improved Tag Cloud Generation with Clustering

AU - Leginus, Martin

AU - Dolog, Peter

AU - Lage, Ricardo Gomes

AU - Durao, Frederico

PY - 2012

Y1 - 2012

N2 - Tag clouds are useful means for navigation in the social websystems. Usually the systems implement the tag cloud generation basedon tag popularity which is not always the best method. In this paperwe propose methodologies on how to combine clustering into the tagcloud generation to improve coverage and overlap. We study several clustering algorithms to generate tag clouds. We show that by extendingcloud generation based on tag popularity with clustering we slightly improve coverage. We also show that if the cloud is generated by clusteringindependently of the tag popularity baseline we minimize overlap andincrease coverage. In the first case we therefore provide more items for auser to explore. In the second case we provide more diverse items for auser to explore. We experiment with the methodologies on two differentdatasets: Delicious and Bibsonomy. The methodologies perform slightlybetter on bibsonomy due to its specific focus. The best performing is thehierarchical clustering.

AB - Tag clouds are useful means for navigation in the social websystems. Usually the systems implement the tag cloud generation basedon tag popularity which is not always the best method. In this paperwe propose methodologies on how to combine clustering into the tagcloud generation to improve coverage and overlap. We study several clustering algorithms to generate tag clouds. We show that by extendingcloud generation based on tag popularity with clustering we slightly improve coverage. We also show that if the cloud is generated by clusteringindependently of the tag popularity baseline we minimize overlap andincrease coverage. In the first case we therefore provide more items for auser to explore. In the second case we provide more diverse items for auser to explore. We experiment with the methodologies on two differentdatasets: Delicious and Bibsonomy. The methodologies perform slightlybetter on bibsonomy due to its specific focus. The best performing is thehierarchical clustering.

KW - tag clouds

KW - clustering

UR - http://www.scopus.com/inward/record.url?scp=84865127870&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-31753-8_5

DO - 10.1007/978-3-642-31753-8_5

M3 - Article in proceeding

T3 - Lecture Notes in Computer Science

SP - 61

EP - 75

BT - Proceedings of the 12th international conference on Web Engineering

PB - Springer

ER -

Leginus M, Dolog P, Lage RG, Durao F. Methodologies for Improved Tag Cloud Generation with Clustering. In Proceedings of the 12th international conference on Web Engineering. Springer. 2012. p. 61–75. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-642-31753-8_5