Towards inferring ratings from user behavior in BitTorrent communities

Róbert Ormándi, István Hegedus, Kornél Csernai, M. Jelasity

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

6 Citations (Scopus)

Abstract

Peer-to-peer file-sharing has been increasingly popular in the last decade. In most cases file-sharing communities provide only minimal functionality, such as search and download. Extra features such as recommendation are difficult to implement because users are typically unwilling to provide sufficient rating information for the items they download. For this reason, it would be desirable to utilize user behavior to infer implicit ratings. For example, if a user deletes a file after downloading it, we could infer that the rating is low, or if the user is seeding the file for a long time, the rating is high. In this paper we demonstrate that it is indeed possible to infer implicit ratings from user behavior. We work with a large trace of Filelist.org, a BitTorrent-based private community, and demonstrate that we can identify a binary like/dislike distinction over the set of files users are downloading, using dynamic features of swarm membership. The resulting database containing the inferred ratings will be published online publicly and it can be used as a benchmark for P2P recommender systems.

Original languageEnglish
Title of host publicationProceedings of the Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE
Pages217-222
Number of pages6
DOIs
Publication statusPublished - 2010
Event19th IEEE International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE 2010 - Larissa, Greece
Duration: Jun 28 2010Jun 30 2010

Other

Other19th IEEE International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE 2010
CountryGreece
CityLarissa
Period6/28/106/30/10

Fingerprint

Recommender systems

Keywords

  • Database
  • Peer-to-peer
  • Recommendation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software

Cite this

Ormándi, R., Hegedus, I., Csernai, K., & Jelasity, M. (2010). Towards inferring ratings from user behavior in BitTorrent communities. In Proceedings of the Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE (pp. 217-222). [5541777] https://doi.org/10.1109/WETICE.2010.41

Towards inferring ratings from user behavior in BitTorrent communities. / Ormándi, Róbert; Hegedus, István; Csernai, Kornél; Jelasity, M.

Proceedings of the Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE. 2010. p. 217-222 5541777.

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

Ormándi, R, Hegedus, I, Csernai, K & Jelasity, M 2010, Towards inferring ratings from user behavior in BitTorrent communities. in Proceedings of the Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE., 5541777, pp. 217-222, 19th IEEE International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE 2010, Larissa, Greece, 6/28/10. https://doi.org/10.1109/WETICE.2010.41
Ormándi R, Hegedus I, Csernai K, Jelasity M. Towards inferring ratings from user behavior in BitTorrent communities. In Proceedings of the Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE. 2010. p. 217-222. 5541777 https://doi.org/10.1109/WETICE.2010.41
Ormándi, Róbert ; Hegedus, István ; Csernai, Kornél ; Jelasity, M. / Towards inferring ratings from user behavior in BitTorrent communities. Proceedings of the Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE. 2010. pp. 217-222
@inproceedings{2115bac352c2459cad0a24e5bd115a0b,
title = "Towards inferring ratings from user behavior in BitTorrent communities",
abstract = "Peer-to-peer file-sharing has been increasingly popular in the last decade. In most cases file-sharing communities provide only minimal functionality, such as search and download. Extra features such as recommendation are difficult to implement because users are typically unwilling to provide sufficient rating information for the items they download. For this reason, it would be desirable to utilize user behavior to infer implicit ratings. For example, if a user deletes a file after downloading it, we could infer that the rating is low, or if the user is seeding the file for a long time, the rating is high. In this paper we demonstrate that it is indeed possible to infer implicit ratings from user behavior. We work with a large trace of Filelist.org, a BitTorrent-based private community, and demonstrate that we can identify a binary like/dislike distinction over the set of files users are downloading, using dynamic features of swarm membership. The resulting database containing the inferred ratings will be published online publicly and it can be used as a benchmark for P2P recommender systems.",
keywords = "Database, Peer-to-peer, Recommendation",
author = "R{\'o}bert Orm{\'a}ndi and Istv{\'a}n Hegedus and Korn{\'e}l Csernai and M. Jelasity",
year = "2010",
doi = "10.1109/WETICE.2010.41",
language = "English",
isbn = "9780769540634",
pages = "217--222",
booktitle = "Proceedings of the Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE",

}

TY - GEN

T1 - Towards inferring ratings from user behavior in BitTorrent communities

AU - Ormándi, Róbert

AU - Hegedus, István

AU - Csernai, Kornél

AU - Jelasity, M.

PY - 2010

Y1 - 2010

N2 - Peer-to-peer file-sharing has been increasingly popular in the last decade. In most cases file-sharing communities provide only minimal functionality, such as search and download. Extra features such as recommendation are difficult to implement because users are typically unwilling to provide sufficient rating information for the items they download. For this reason, it would be desirable to utilize user behavior to infer implicit ratings. For example, if a user deletes a file after downloading it, we could infer that the rating is low, or if the user is seeding the file for a long time, the rating is high. In this paper we demonstrate that it is indeed possible to infer implicit ratings from user behavior. We work with a large trace of Filelist.org, a BitTorrent-based private community, and demonstrate that we can identify a binary like/dislike distinction over the set of files users are downloading, using dynamic features of swarm membership. The resulting database containing the inferred ratings will be published online publicly and it can be used as a benchmark for P2P recommender systems.

AB - Peer-to-peer file-sharing has been increasingly popular in the last decade. In most cases file-sharing communities provide only minimal functionality, such as search and download. Extra features such as recommendation are difficult to implement because users are typically unwilling to provide sufficient rating information for the items they download. For this reason, it would be desirable to utilize user behavior to infer implicit ratings. For example, if a user deletes a file after downloading it, we could infer that the rating is low, or if the user is seeding the file for a long time, the rating is high. In this paper we demonstrate that it is indeed possible to infer implicit ratings from user behavior. We work with a large trace of Filelist.org, a BitTorrent-based private community, and demonstrate that we can identify a binary like/dislike distinction over the set of files users are downloading, using dynamic features of swarm membership. The resulting database containing the inferred ratings will be published online publicly and it can be used as a benchmark for P2P recommender systems.

KW - Database

KW - Peer-to-peer

KW - Recommendation

UR - http://www.scopus.com/inward/record.url?scp=77955869479&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955869479&partnerID=8YFLogxK

U2 - 10.1109/WETICE.2010.41

DO - 10.1109/WETICE.2010.41

M3 - Conference contribution

SN - 9780769540634

SP - 217

EP - 222

BT - Proceedings of the Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE

ER -