When media gets wise: Collaborative filtering with mobile media agents

Mattias Jacobsson; Mattias Rost; Lars Erik Holmquist

doi:10.1145/1111449.1111514

When media gets wise: Collaborative filtering with mobile media agents

Mattias Jacobsson^*, Mattias Rost, Lars Erik Holmquist

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

20 Citations (Scopus)

Abstract

We present a model where media (e.g. music files) are autonomous entities that carry their own individual information. Our goal is to turn such files into autonomous, rule-following agents capable of building their own identities from interactions with other agents and users, We are exploring how collaborative filtering-like behaviour could emerge out of large ensembles of interacting agents, which are distributed over mobile devices in social networks. We have implemented a first version of the model in the form of a music player application for mobile devices, called Push!Music. This system takes advantage of active recommendations as well as implicit user activity to build a profile for each media file.

Original language	English
Title of host publication	IUI '06 Proceedings of the 11th international conference on Intelligent user interfaces
Publisher	ACM
Pages	291-293
Number of pages	3
Volume	2006
ISBN (Electronic)	9781595932877
DOIs	https://doi.org/10.1145/1111449.1111514
Publication status	Published - 29 Jan 2006
Externally published	Yes
Event	IUI 06 - 2006 International Conference on Intelligent User Interfaces - Sydney, Australia Duration: 29 Jan 2005 → 1 Feb 2005

Conference

Conference	IUI 06 - 2006 International Conference on Intelligent User Interfaces
Country/Territory	Australia
City	Sydney
Period	29/01/05 → 1/02/05

Keywords

Active Recommendation
Distributed Collaborative Filtering
Emergence
Media Agents
Media Ecologies

Access to Document

10.1145/1111449.1111514

Cite this

@inproceedings{8cc603a33665467ab24ca9f961a26726,

title = "When media gets wise: Collaborative filtering with mobile media agents",

abstract = "We present a model where media (e.g. music files) are autonomous entities that carry their own individual information. Our goal is to turn such files into autonomous, rule-following agents capable of building their own identities from interactions with other agents and users, We are exploring how collaborative filtering-like behaviour could emerge out of large ensembles of interacting agents, which are distributed over mobile devices in social networks. We have implemented a first version of the model in the form of a music player application for mobile devices, called Push!Music. This system takes advantage of active recommendations as well as implicit user activity to build a profile for each media file.",

keywords = "Active Recommendation, Distributed Collaborative Filtering, Emergence, Media Agents, Media Ecologies",

author = "Mattias Jacobsson and Mattias Rost and Holmquist, \{Lars Erik\}",

year = "2006",

month = jan,

day = "29",

doi = "10.1145/1111449.1111514",

language = "English",

volume = "2006",

pages = "291--293",

booktitle = "IUI '06 Proceedings of the 11th international conference on Intelligent user interfaces",

publisher = "ACM",

address = "United States",

note = "IUI 06 - 2006 International Conference on Intelligent User Interfaces ; Conference date: 29-01-2005 Through 01-02-2005",

}

Jacobsson, M, Rost, M & Holmquist, LE 2006, When media gets wise: Collaborative filtering with mobile media agents. in IUI '06 Proceedings of the 11th international conference on Intelligent user interfaces. vol. 2006, ACM, pp. 291-293, IUI 06 - 2006 International Conference on Intelligent User Interfaces, Sydney, Australia, 29/01/05. https://doi.org/10.1145/1111449.1111514

TY - GEN

T1 - When media gets wise

T2 - IUI 06 - 2006 International Conference on Intelligent User Interfaces

AU - Jacobsson, Mattias

AU - Rost, Mattias

AU - Holmquist, Lars Erik

PY - 2006/1/29

Y1 - 2006/1/29

N2 - We present a model where media (e.g. music files) are autonomous entities that carry their own individual information. Our goal is to turn such files into autonomous, rule-following agents capable of building their own identities from interactions with other agents and users, We are exploring how collaborative filtering-like behaviour could emerge out of large ensembles of interacting agents, which are distributed over mobile devices in social networks. We have implemented a first version of the model in the form of a music player application for mobile devices, called Push!Music. This system takes advantage of active recommendations as well as implicit user activity to build a profile for each media file.

AB - We present a model where media (e.g. music files) are autonomous entities that carry their own individual information. Our goal is to turn such files into autonomous, rule-following agents capable of building their own identities from interactions with other agents and users, We are exploring how collaborative filtering-like behaviour could emerge out of large ensembles of interacting agents, which are distributed over mobile devices in social networks. We have implemented a first version of the model in the form of a music player application for mobile devices, called Push!Music. This system takes advantage of active recommendations as well as implicit user activity to build a profile for each media file.

KW - Active Recommendation

KW - Distributed Collaborative Filtering

KW - Emergence

KW - Media Agents

KW - Media Ecologies

UR - https://www.scopus.com/pages/publications/33746068280

U2 - 10.1145/1111449.1111514

DO - 10.1145/1111449.1111514

M3 - Conference contribution

AN - SCOPUS:33746068280

VL - 2006

SP - 291

EP - 293

BT - IUI '06 Proceedings of the 11th international conference on Intelligent user interfaces

PB - ACM

Y2 - 29 January 2005 through 1 February 2005

ER -

When media gets wise: Collaborative filtering with mobile media agents

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this