Personalized news recommendation based on click behavior

Liu, Jiahui; Dolan, Peter; Pedersen, Elin Rønby

doi:10.1145/1719970.1719976

Cited by 617 publications

(401 citation statements)

References 19 publications

Supporting

Mentioning

379

Contrasting

Unclassified

Order By: Relevance

“…Contrary to common wisdom [2], [1], we find that contentbased and hybrid techniques have surprisingly poor performance. We explain this by the fact that users do not like to read multiple stories about the same topic.…”

Section: Introductioncontrasting

confidence: 97%

“…For example, Liu et al [1] extend the study on Google News [2] by looking at the user click behaviour in order to create accurate user profiles. Li et al [12] introduce a contextual bandit algorithm which recommends news stories based on contextual information about the users and stories.…”

Section: Related Workmentioning

confidence: 99%

“…The cold-start problem in collaborative filtering can be addressed by applying it at the level of a topic model [1]. We implemented such a system where we cluster news stories based on topic distributions, then build a transition matrix between clusters.…”

Section: Hybrid Systemmentioning

confidence: 99%

“…Thus, techniques for recommendations based on user behaviour have been considered difficult to apply. Topic models may overcome this by modelling behaviour at the level of topics rather than individual articles [1].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Personalized News Recommendation Based on Collaborative Filtering

Garcin

Zhou

Faltings

et al. 2012

2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology

View full text Add to dashboard Cite

Abstract-Because of the abundance of news on the web, news recommendation is an important problem. We compare three approaches for personalized news recommendation: collaborative filtering at the level of news items, content-based system recommending items with similar topics, and a hybrid technique.We observe that recommending items according to the topic profile of the current browsing session seems to give poor results. Although news articles change frequently and thus data about their popularity is sparse, collaborative filtering applied to individual articles provides the best results.

show abstract

Section: Introductioncontrasting

confidence: 97%

Section: Related Workmentioning

confidence: 99%

Section: Hybrid Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Personalized News Recommendation Based on Collaborative Filtering

Garcin

Zhou

Faltings

et al. 2012

2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology

View full text Add to dashboard Cite

show abstract

“…Recommending Fresh Content Liu et al [25] analyzed content-based recommender for Google News. They showed that interests in news topics such as technologies, politics, etc.…”

Section: Application Scenariosmentioning

confidence: 99%

TUMS: Twitter-Based User Modeling Service

Tao

Abel

Gao

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Twitter is today's most popular micro-blogging service on the Social Web. As people discuss various fresh topics, Twitter messages (tweets) can tell much about the current interests and concerns of a user. In this paper, we introduce TUMS, a Twitter-based User Modeling Service, that infers semantic user profiles from the messages people post on Twitter. It features topic detection and entity extraction for tweets and allows for further enrichment by linking tweets to news articles that describe the context of the tweets. TUMS is made publicly available as a Web application. It allows end-users to overview Twitter-based profiles in a structured way and allows them to see in which topics or entities a user was interested in a specific point in time. Furthermore, it provides Twitter-based user profiles in RDF format and allows applications to incorporate these profiles in order to adapt their functionality to the current interests of a user. TUMS is available via: http://wis.ewi.tudelft.nl/tums/

show abstract

Personalizing news content: An experimental study

Sela

Lavie

Inbar

et al. 2014

Asso for Info Science & Tech

View full text Add to dashboard Cite

The delivery of personalized news content depends on the ability to predict user interests. We evaluated different methods for acquiring user profiles based on declared and actual interest in various news topics and items. In an experiment, 36 students rated their interest in six news topics and in specific news items and read on 6 days standard, nonpersonalized editions and personalized (basic or adaptive) news editions. We measured subjective satisfaction with the editions and expressed preferences, along with objective measures, to infer actual interest in items. Users' declared interest in news topics did not strongly predict their actual interest in specific news items. Satisfaction with all news editions was high, but participants preferred the personalized editions. User interest was weakly correlated with reading duration, article length, and reading order. Different measures predicted interest in different news topics. Explicit measures predicted interest in relatively clearly defined topics such as sports, but were less appropriate for broader topics such as science and technology. Our results indicate that explicit and implicit methods should be combined to generate user profiles. We suggest that a personalized newspaper should contain both general information and personalized items, selected based on specific combinations of measures for each of the different news topics. Based on the findings, we present a general model to decide on the personalization of news content to generate personalized editions for readers.

show abstract

Personalized news recommendation based on click behavior

Cited by 617 publications

References 19 publications

Personalized News Recommendation Based on Collaborative Filtering

Personalized News Recommendation Based on Collaborative Filtering

TUMS: Twitter-Based User Modeling Service

Personalizing news content: An experimental study

Contact Info

Product

Resources

About