Attention Please! A Hybrid Resource Recommender Mimicking Attention-Interpretation Dynamics

Paul Seitlinger, Dominik Kowald, Simone Kopeinik, Ilire Hasani-Mavriqi, Tobias Ley, Elisabeth Lex

Research output: Contribution to journalArticleResearch

Abstract

Classic resource recommenders like Collaborative Filtering (CF) treat users as being just another entity, neglecting non-linear user-resource dynamics shaping attention and interpretation. In this paper, we propose a novel hybrid recommendation strategy that refines CF by capturing these dynamics. The evaluation results reveal that our approach substantially improves CF and, depending on the dataset, successfully competes with a computationally much more expensive Matrix Factorization variant.
Original languageEnglish
JournalarXiv.org e-Print archive
Publication statusPublished - 30 Jan 2015

Fingerprint

Collaborative filtering
Factorization

Keywords

  • recommender systems
  • ressource recommendations
  • cognitive science
  • algorithm

ASJC Scopus subject areas

  • Computer Science(all)

Fields of Expertise

  • Information, Communication & Computing

Cite this

Attention Please! A Hybrid Resource Recommender Mimicking Attention-Interpretation Dynamics. / Seitlinger, Paul; Kowald, Dominik; Kopeinik, Simone; Hasani-Mavriqi, Ilire; Ley, Tobias; Lex, Elisabeth.

In: arXiv.org e-Print archive, 30.01.2015.

Research output: Contribution to journalArticleResearch

@article{46d10a95e7e3412f87452460c971744a,
title = "Attention Please! A Hybrid Resource Recommender Mimicking Attention-Interpretation Dynamics",
abstract = "Classic resource recommenders like Collaborative Filtering (CF) treat users as being just another entity, neglecting non-linear user-resource dynamics shaping attention and interpretation. In this paper, we propose a novel hybrid recommendation strategy that refines CF by capturing these dynamics. The evaluation results reveal that our approach substantially improves CF and, depending on the dataset, successfully competes with a computationally much more expensive Matrix Factorization variant.",
keywords = "recommender systems, ressource recommendations, cognitive science, algorithm",
author = "Paul Seitlinger and Dominik Kowald and Simone Kopeinik and Ilire Hasani-Mavriqi and Tobias Ley and Elisabeth Lex",
note = "Submitted to WWW'15 WebScience Track",
year = "2015",
month = "1",
day = "30",
language = "English",
journal = "arXiv.org e-Print archive",
publisher = "Cornell University Library",

}

TY - JOUR

T1 - Attention Please! A Hybrid Resource Recommender Mimicking Attention-Interpretation Dynamics

AU - Seitlinger, Paul

AU - Kowald, Dominik

AU - Kopeinik, Simone

AU - Hasani-Mavriqi, Ilire

AU - Ley, Tobias

AU - Lex, Elisabeth

N1 - Submitted to WWW'15 WebScience Track

PY - 2015/1/30

Y1 - 2015/1/30

N2 - Classic resource recommenders like Collaborative Filtering (CF) treat users as being just another entity, neglecting non-linear user-resource dynamics shaping attention and interpretation. In this paper, we propose a novel hybrid recommendation strategy that refines CF by capturing these dynamics. The evaluation results reveal that our approach substantially improves CF and, depending on the dataset, successfully competes with a computationally much more expensive Matrix Factorization variant.

AB - Classic resource recommenders like Collaborative Filtering (CF) treat users as being just another entity, neglecting non-linear user-resource dynamics shaping attention and interpretation. In this paper, we propose a novel hybrid recommendation strategy that refines CF by capturing these dynamics. The evaluation results reveal that our approach substantially improves CF and, depending on the dataset, successfully competes with a computationally much more expensive Matrix Factorization variant.

KW - recommender systems

KW - ressource recommendations

KW - cognitive science

KW - algorithm

M3 - Article

JO - arXiv.org e-Print archive

JF - arXiv.org e-Print archive

ER -