Overcoming the Imbalance Between Tag Recommendation Approaches and Real-World Folksonomy Structures with Cognitive-Inspired Algorithms

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In this paper, we study the imbalance between current state-of-the-art tag recommendation algorithms and the folksonomy structures of real-world social tagging systems. While algorithms such as FolkRank are designed for dense folksonomy structures, most social tagging systems exhibit a sparse nature. To overcome this imbalance, we show that cognitive-inspired algorithms, which model the tag vocabulary of a user in a cognitive-plausible way, can be helpful. Our present approach does this via implementing the activation equation of the cognitive architecture ACT-R, which determines the usefulness of units in human memory (e.g., tags). In this sense, our long-term research goal is to design hybrid recommendation approaches, which combine the advantages of both worlds in order to adapt to the current setting (i.e., sparse vs. dense ones).
LanguageEnglish
JournalarXiv.org e-Print archive
StatusPublished - 8 May 2018

Fingerprint

Chemical activation
Data storage equipment

Keywords

  • cs.IR

Cite this

@article{a2cb6a2b2b1d49719691df2a099037f9,
title = "Overcoming the Imbalance Between Tag Recommendation Approaches and Real-World Folksonomy Structures with Cognitive-Inspired Algorithms",
abstract = "In this paper, we study the imbalance between current state-of-the-art tag recommendation algorithms and the folksonomy structures of real-world social tagging systems. While algorithms such as FolkRank are designed for dense folksonomy structures, most social tagging systems exhibit a sparse nature. To overcome this imbalance, we show that cognitive-inspired algorithms, which model the tag vocabulary of a user in a cognitive-plausible way, can be helpful. Our present approach does this via implementing the activation equation of the cognitive architecture ACT-R, which determines the usefulness of units in human memory (e.g., tags). In this sense, our long-term research goal is to design hybrid recommendation approaches, which combine the advantages of both worlds in order to adapt to the current setting (i.e., sparse vs. dense ones).",
keywords = "cs.IR",
author = "Dominik Kowald and Elisabeth Lex",
note = "Presented at the European Symposium for Computational Social Sciences",
year = "2018",
month = "5",
day = "8",
language = "English",
journal = "arXiv.org e-Print archive",
publisher = "Cornell University Library",

}

TY - JOUR

T1 - Overcoming the Imbalance Between Tag Recommendation Approaches and Real-World Folksonomy Structures with Cognitive-Inspired Algorithms

AU - Kowald,Dominik

AU - Lex,Elisabeth

N1 - Presented at the European Symposium for Computational Social Sciences

PY - 2018/5/8

Y1 - 2018/5/8

N2 - In this paper, we study the imbalance between current state-of-the-art tag recommendation algorithms and the folksonomy structures of real-world social tagging systems. While algorithms such as FolkRank are designed for dense folksonomy structures, most social tagging systems exhibit a sparse nature. To overcome this imbalance, we show that cognitive-inspired algorithms, which model the tag vocabulary of a user in a cognitive-plausible way, can be helpful. Our present approach does this via implementing the activation equation of the cognitive architecture ACT-R, which determines the usefulness of units in human memory (e.g., tags). In this sense, our long-term research goal is to design hybrid recommendation approaches, which combine the advantages of both worlds in order to adapt to the current setting (i.e., sparse vs. dense ones).

AB - In this paper, we study the imbalance between current state-of-the-art tag recommendation algorithms and the folksonomy structures of real-world social tagging systems. While algorithms such as FolkRank are designed for dense folksonomy structures, most social tagging systems exhibit a sparse nature. To overcome this imbalance, we show that cognitive-inspired algorithms, which model the tag vocabulary of a user in a cognitive-plausible way, can be helpful. Our present approach does this via implementing the activation equation of the cognitive architecture ACT-R, which determines the usefulness of units in human memory (e.g., tags). In this sense, our long-term research goal is to design hybrid recommendation approaches, which combine the advantages of both worlds in order to adapt to the current setting (i.e., sparse vs. dense ones).

KW - cs.IR

M3 - Article

JO - arXiv.org e-Print archive

T2 - arXiv.org e-Print archive

JF - arXiv.org e-Print archive

ER -