From chatter to headlines

Harnessing the real-time web for personalized news recommendation

Gianmarco Morales, Aristides Gionis, Claudio Lucchese

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

74 Citations (Scopus)

Abstract

We propose a new methodology for recommending interesting news to users by exploiting the information in their twitter persona. We model relevance between users and news articles using a mix of signals drawn from the news stream and from twitter: the profile of the social neighborhood of the users, the content of their own tweet stream, and topic popularity in the news and in the whole twitter-land. We validate our approach on a real-world dataset of approximately 40k articles coming from Yahoo! News and one month of crawled twitter data. We train our model using a learning-to-rank approach and support-vector machines. The train and test set are drawn from Yahoo! toolbar log data. We heuristically identify 3 214 users of twitter in the log and use their clicks on news articles to train our system. Our methodology is able to predict with good accuracy the news articles clicked by the users and rank them higher than other news articles. The results show that the combination of various signals from real-time web and microblogging platforms can be a useful resource to understand user behavior.

Original languageEnglish
Title of host publicationWSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining
Pages153-162
Number of pages10
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event5th ACM International Conference on Web Search and Data Mining, WSDM 2012 - Seattle, WA, United States
Duration: 8 Feb 201212 Feb 2012

Other

Other5th ACM International Conference on Web Search and Data Mining, WSDM 2012
CountryUnited States
CitySeattle, WA
Period8/2/1212/2/12

Fingerprint

Support vector machines

Keywords

  • Micro-blogging applications
  • News recommendation
  • Personalization
  • Real-time web
  • Recommendation systems

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Morales, G., Gionis, A., & Lucchese, C. (2012). From chatter to headlines: Harnessing the real-time web for personalized news recommendation. In WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining (pp. 153-162) https://doi.org/10.1145/2124295.2124315

From chatter to headlines : Harnessing the real-time web for personalized news recommendation. / Morales, Gianmarco; Gionis, Aristides; Lucchese, Claudio.

WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012. p. 153-162.

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

Morales, G, Gionis, A & Lucchese, C 2012, From chatter to headlines: Harnessing the real-time web for personalized news recommendation. in WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. pp. 153-162, 5th ACM International Conference on Web Search and Data Mining, WSDM 2012, Seattle, WA, United States, 8/2/12. https://doi.org/10.1145/2124295.2124315
Morales G, Gionis A, Lucchese C. From chatter to headlines: Harnessing the real-time web for personalized news recommendation. In WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012. p. 153-162 https://doi.org/10.1145/2124295.2124315
Morales, Gianmarco ; Gionis, Aristides ; Lucchese, Claudio. / From chatter to headlines : Harnessing the real-time web for personalized news recommendation. WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012. pp. 153-162
@inproceedings{36e93383351447759d9a890466357020,
title = "From chatter to headlines: Harnessing the real-time web for personalized news recommendation",
abstract = "We propose a new methodology for recommending interesting news to users by exploiting the information in their twitter persona. We model relevance between users and news articles using a mix of signals drawn from the news stream and from twitter: the profile of the social neighborhood of the users, the content of their own tweet stream, and topic popularity in the news and in the whole twitter-land. We validate our approach on a real-world dataset of approximately 40k articles coming from Yahoo! News and one month of crawled twitter data. We train our model using a learning-to-rank approach and support-vector machines. The train and test set are drawn from Yahoo! toolbar log data. We heuristically identify 3 214 users of twitter in the log and use their clicks on news articles to train our system. Our methodology is able to predict with good accuracy the news articles clicked by the users and rank them higher than other news articles. The results show that the combination of various signals from real-time web and microblogging platforms can be a useful resource to understand user behavior.",
keywords = "Micro-blogging applications, News recommendation, Personalization, Real-time web, Recommendation systems",
author = "Gianmarco Morales and Aristides Gionis and Claudio Lucchese",
year = "2012",
doi = "10.1145/2124295.2124315",
language = "English",
isbn = "9781450307475",
pages = "153--162",
booktitle = "WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining",

}

TY - GEN

T1 - From chatter to headlines

T2 - Harnessing the real-time web for personalized news recommendation

AU - Morales, Gianmarco

AU - Gionis, Aristides

AU - Lucchese, Claudio

PY - 2012

Y1 - 2012

N2 - We propose a new methodology for recommending interesting news to users by exploiting the information in their twitter persona. We model relevance between users and news articles using a mix of signals drawn from the news stream and from twitter: the profile of the social neighborhood of the users, the content of their own tweet stream, and topic popularity in the news and in the whole twitter-land. We validate our approach on a real-world dataset of approximately 40k articles coming from Yahoo! News and one month of crawled twitter data. We train our model using a learning-to-rank approach and support-vector machines. The train and test set are drawn from Yahoo! toolbar log data. We heuristically identify 3 214 users of twitter in the log and use their clicks on news articles to train our system. Our methodology is able to predict with good accuracy the news articles clicked by the users and rank them higher than other news articles. The results show that the combination of various signals from real-time web and microblogging platforms can be a useful resource to understand user behavior.

AB - We propose a new methodology for recommending interesting news to users by exploiting the information in their twitter persona. We model relevance between users and news articles using a mix of signals drawn from the news stream and from twitter: the profile of the social neighborhood of the users, the content of their own tweet stream, and topic popularity in the news and in the whole twitter-land. We validate our approach on a real-world dataset of approximately 40k articles coming from Yahoo! News and one month of crawled twitter data. We train our model using a learning-to-rank approach and support-vector machines. The train and test set are drawn from Yahoo! toolbar log data. We heuristically identify 3 214 users of twitter in the log and use their clicks on news articles to train our system. Our methodology is able to predict with good accuracy the news articles clicked by the users and rank them higher than other news articles. The results show that the combination of various signals from real-time web and microblogging platforms can be a useful resource to understand user behavior.

KW - Micro-blogging applications

KW - News recommendation

KW - Personalization

KW - Real-time web

KW - Recommendation systems

UR - http://www.scopus.com/inward/record.url?scp=84858027034&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858027034&partnerID=8YFLogxK

U2 - 10.1145/2124295.2124315

DO - 10.1145/2124295.2124315

M3 - Conference contribution

SN - 9781450307475

SP - 153

EP - 162

BT - WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining

ER -