Home > Research > Publications & Outputs > Recommendations Based on User-Generated Comment...

Research

Links

Text available via DOI:

Keywords

View graph of relations

Recommendations Based on User-Generated Comments in Social Media

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Recommendations Based on User-Generated Comments in Social Media. / Messenger, A.; Whittle, J.
Privacy, Security, Risk and Trust (PASSAT), 2011 IEEE Third International Conference on and 2011 IEEE Third International Confernece on Social Computing (SocialCom). IEEE, 2011. p. 505-508.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Messenger, A & Whittle, J 2011, Recommendations Based on User-Generated Comments in Social Media. in Privacy, Security, Risk and Trust (PASSAT), 2011 IEEE Third International Conference on and 2011 IEEE Third International Confernece on Social Computing (SocialCom). IEEE, pp. 505-508. https://doi.org/10.1109/PASSAT/SocialCom.2011.146

APA

Messenger, A., & Whittle, J. (2011). Recommendations Based on User-Generated Comments in Social Media. In Privacy, Security, Risk and Trust (PASSAT), 2011 IEEE Third International Conference on and 2011 IEEE Third International Confernece on Social Computing (SocialCom) (pp. 505-508). IEEE. https://doi.org/10.1109/PASSAT/SocialCom.2011.146

Vancouver

Messenger A, Whittle J. Recommendations Based on User-Generated Comments in Social Media. In Privacy, Security, Risk and Trust (PASSAT), 2011 IEEE Third International Conference on and 2011 IEEE Third International Confernece on Social Computing (SocialCom). IEEE. 2011. p. 505-508 doi: 10.1109/PASSAT/SocialCom.2011.146

Author

Messenger, A. ; Whittle, J. / Recommendations Based on User-Generated Comments in Social Media. Privacy, Security, Risk and Trust (PASSAT), 2011 IEEE Third International Conference on and 2011 IEEE Third International Confernece on Social Computing (SocialCom). IEEE, 2011. pp. 505-508

Bibtex

@inproceedings{a7e9380a18f84b9d93df0b26af1d53f5,
title = "Recommendations Based on User-Generated Comments in Social Media",
abstract = "Recommender systems gather user profile data either explicitly (users enter it) or implicitly (online behavior tracking).Surprisingly, given the prevalence of social media forums, which contain a rich set of user comments, there have been very few attempts to analyze the content of these comments to build up a user profile. In this paper, we compare and contrast a number of strategies for using text analysis to automatically gather profile data from user comments on news articles. We use this data to prototype a news recommender system based on the Guardian newspaper's 'Comment is Free' forum. The paper shows the feasibility of the approach: in a user study with fifty participants, our recommender outperforms a commercial 'best-in-class' system. Furthermore, we show that user comments allow recommender systems to track an evolving conversation related to a news article and can thus provide recommendations that better match the topics of conversation in comments, which maybe quite different from those in the original news article.",
keywords = "NLP , recommender systems, user-generated content",
author = "A. Messenger and J. Whittle",
year = "2011",
doi = "10.1109/PASSAT/SocialCom.2011.146",
language = "English",
isbn = "978-1-4577-1931-8",
pages = "505--508",
booktitle = "Privacy, Security, Risk and Trust (PASSAT), 2011 IEEE Third International Conference on and 2011 IEEE Third International Confernece on Social Computing (SocialCom)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Recommendations Based on User-Generated Comments in Social Media

AU - Messenger, A.

AU - Whittle, J.

PY - 2011

Y1 - 2011

N2 - Recommender systems gather user profile data either explicitly (users enter it) or implicitly (online behavior tracking).Surprisingly, given the prevalence of social media forums, which contain a rich set of user comments, there have been very few attempts to analyze the content of these comments to build up a user profile. In this paper, we compare and contrast a number of strategies for using text analysis to automatically gather profile data from user comments on news articles. We use this data to prototype a news recommender system based on the Guardian newspaper's 'Comment is Free' forum. The paper shows the feasibility of the approach: in a user study with fifty participants, our recommender outperforms a commercial 'best-in-class' system. Furthermore, we show that user comments allow recommender systems to track an evolving conversation related to a news article and can thus provide recommendations that better match the topics of conversation in comments, which maybe quite different from those in the original news article.

AB - Recommender systems gather user profile data either explicitly (users enter it) or implicitly (online behavior tracking).Surprisingly, given the prevalence of social media forums, which contain a rich set of user comments, there have been very few attempts to analyze the content of these comments to build up a user profile. In this paper, we compare and contrast a number of strategies for using text analysis to automatically gather profile data from user comments on news articles. We use this data to prototype a news recommender system based on the Guardian newspaper's 'Comment is Free' forum. The paper shows the feasibility of the approach: in a user study with fifty participants, our recommender outperforms a commercial 'best-in-class' system. Furthermore, we show that user comments allow recommender systems to track an evolving conversation related to a news article and can thus provide recommendations that better match the topics of conversation in comments, which maybe quite different from those in the original news article.

KW - NLP

KW - recommender systems

KW - user-generated content

U2 - 10.1109/PASSAT/SocialCom.2011.146

DO - 10.1109/PASSAT/SocialCom.2011.146

M3 - Conference contribution/Paper

SN - 978-1-4577-1931-8

SP - 505

EP - 508

BT - Privacy, Security, Risk and Trust (PASSAT), 2011 IEEE Third International Conference on and 2011 IEEE Third International Confernece on Social Computing (SocialCom)

PB - IEEE

ER -