Similarity for News Recommender Systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The accuracy of content-based recommender systems tends to depend on the way similarity is defined. In this paper, we will explore different ways to measure similarity for a news recommender system based on news headlines. We will compare human judgements of similarity with Lin’s taxonomy-based measure and the WASP measure that uses annotated corpus data. The main aim of this work is to better understand similarity, so that it can be used to explain recommendations to users.
Original languageEnglish
Title of host publicationWorkshop on Recommender Systems and Intelligent User Interfaces
Subtitle of host publication2nd international workshop on web personalisation,recommender iystems and intelligent iser interfaces
EditorsGulden Uchyigit
Publication statusPublished - 2006

Fingerprint

Recommender systems
Taxonomies

Keywords

  • similarity
  • recommender systems

Cite this

Tintarev, N., & Masthoff, J. (2006). Similarity for News Recommender Systems. In G. Uchyigit (Ed.), Workshop on Recommender Systems and Intelligent User Interfaces: 2nd international workshop on web personalisation,recommender iystems and intelligent iser interfaces

Similarity for News Recommender Systems. / Tintarev, Nava; Masthoff, Judith.

Workshop on Recommender Systems and Intelligent User Interfaces: 2nd international workshop on web personalisation,recommender iystems and intelligent iser interfaces. ed. / Gulden Uchyigit. 2006.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tintarev, N & Masthoff, J 2006, Similarity for News Recommender Systems. in G Uchyigit (ed.), Workshop on Recommender Systems and Intelligent User Interfaces: 2nd international workshop on web personalisation,recommender iystems and intelligent iser interfaces.
Tintarev N, Masthoff J. Similarity for News Recommender Systems. In Uchyigit G, editor, Workshop on Recommender Systems and Intelligent User Interfaces: 2nd international workshop on web personalisation,recommender iystems and intelligent iser interfaces. 2006
Tintarev, Nava ; Masthoff, Judith. / Similarity for News Recommender Systems. Workshop on Recommender Systems and Intelligent User Interfaces: 2nd international workshop on web personalisation,recommender iystems and intelligent iser interfaces. editor / Gulden Uchyigit. 2006.
@inproceedings{9d526ec823f8480197e084cf301bb24e,
title = "Similarity for News Recommender Systems",
abstract = "The accuracy of content-based recommender systems tends to depend on the way similarity is defined. In this paper, we will explore different ways to measure similarity for a news recommender system based on news headlines. We will compare human judgements of similarity with Lin’s taxonomy-based measure and the WASP measure that uses annotated corpus data. The main aim of this work is to better understand similarity, so that it can be used to explain recommendations to users.",
keywords = "similarity, recommender systems",
author = "Nava Tintarev and Judith Masthoff",
note = "In conjunction with the International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems, AH 2006, Dublin, Ireland, June 20-23, 2006",
year = "2006",
language = "English",
editor = "Gulden Uchyigit",
booktitle = "Workshop on Recommender Systems and Intelligent User Interfaces",

}

TY - GEN

T1 - Similarity for News Recommender Systems

AU - Tintarev, Nava

AU - Masthoff, Judith

N1 - In conjunction with the International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems, AH 2006, Dublin, Ireland, June 20-23, 2006

PY - 2006

Y1 - 2006

N2 - The accuracy of content-based recommender systems tends to depend on the way similarity is defined. In this paper, we will explore different ways to measure similarity for a news recommender system based on news headlines. We will compare human judgements of similarity with Lin’s taxonomy-based measure and the WASP measure that uses annotated corpus data. The main aim of this work is to better understand similarity, so that it can be used to explain recommendations to users.

AB - The accuracy of content-based recommender systems tends to depend on the way similarity is defined. In this paper, we will explore different ways to measure similarity for a news recommender system based on news headlines. We will compare human judgements of similarity with Lin’s taxonomy-based measure and the WASP measure that uses annotated corpus data. The main aim of this work is to better understand similarity, so that it can be used to explain recommendations to users.

KW - similarity

KW - recommender systems

M3 - Conference contribution

BT - Workshop on Recommender Systems and Intelligent User Interfaces

A2 - Uchyigit, Gulden

ER -