User action interpretation for personalized content optimization in recommender systems

Dong, Anlei; Bian, Jiang; He, Xiaofeng; Reddy, Srihari; Chang, Yi

doi:10.1145/2063576.2063907

Cited by 5 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamics of groups of users • Modeling users behavior over time [21] • Detecting trends in user queries and interests [6,14] • Temporal dynamics in microblogs/social media (c) Multidimensional dynamics (e.g. spatio-temporal analysis) [24,25] [19,20] (c) Applications for time-sensitive web search: discovering fresh content [9]; time-sensitive relevance: freshness and relevance [8]; time-sensitive ranking [8,9]; time-sensitive query suggestion [22]; federated search [6,14]; supporting users in understanding time [1]; (d) Recommendation: how to recommend the most relevant and buzzy queries to users [7]? How to recommend relevant content?…”

Section: Format and Outlinementioning

confidence: 99%

Temporal web dynamics and its application to information retrieval

Radinsky

Dı́az

Dumais

et al. 2013

Proceedings of the Sixth ACM International Conference on Web Search and Data Mining

Self Cite

View full text Add to dashboard Cite

The World Wide Web is highly dynamic and is constantly evolving to cover the latest information about the physical and social updates in the world. At the same time, the changes in web contents are entangled with new information needs and time-sensitive user interactions with information sources. To address these temporal information needs effectively, it is essential for the search engines to model web dynamics and understand the changes in user behavior over time that are caused by them.In this full-day tutorial, we focus on modeling time-sensitive content on the web, and discuss the state-of-the-art approaches for integrating temporal signals in web search. We address many of the related research topics including those associated with searching dynamic collections, defining timesensitive relevance, understanding user query behavior over time, and investigating the main reasons behind content changes. We also cover algorithms, evaluation methodologies and metrics for time-aware search, and discuss the latest breakthroughs and open challenges.

show abstract

Section: Format and Outlinementioning

confidence: 99%

Temporal web dynamics and its application to information retrieval

Radinsky

Dı́az

Dumais

et al. 2013

Proceedings of the Sixth ACM International Conference on Web Search and Data Mining

Self Cite

View full text Add to dashboard Cite

show abstract

“…front page, in which users' interactions via clicks are relatively lower while the content pool size can be larger, simply trying to estimate CTR of each item by treating every logged views and clicks equally could cause more problems than solutions; that is, recommending content items based on inaccurate estimates of CTRs would not make the recommendation quality any better. In order to partly remedy such low-clicks and views problem, recently [Dong et al 2011] has proposed a method to effectively interpret users' actions, i.e., views and clicks, such that the estimates of CTRs of contents could become more reliable when using the data that have been appropriately interpreted.…”

Section: Introductionmentioning

confidence: 99%

Exploiting User Preference for Online Learning in Web Content Optimization Systems

Bian

Long

et al. 2014

ACM Trans. Intell. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

Web portal services have become an important medium to deliver digital content, e.g. news, advertisements, etc., to Web users in a timely fashion. To attract more users to various content modules on the Web portal, it is necessary to design a recommender system that can effectively achieve Web portal content optimization by automatically estimating content items' attractiveness and relevance to users' interests. The state-of-the-art online learning methodology adapts dedicated pointwise models to independently estimate the attractiveness score for each candidate content item. Although such pointwise models can be easily adapted for online recommendation, there still remain a few critical problems. First, this pointwise methodology fails to use invaluable user preferences between content items. Moreover, the performance of pointwise models decreases drastically when facing the problem of sparse learning samples. To address these problems, we propose to explore a new dynamic pairwise learning methodology for Web portal content optimization, in which we exploit dynamic user preferences extracted based on users' actions on portal services to compute the attractiveness scores of content items. In this paper, we introduce two specific pairwise learning algorithms, a straightforward graph-based algorithm and a formalized Bayesian modeling one. Experiments on large-scale data from a commercial Web portal demonstrate the significant improvement of pairwise methodologies over the baseline pointwise models. Further analysis illustrates that our new pairwise learning approaches can benefit personalized recommendation more than pointwise models, since the data sparsity is more critical for personalized content optimization.

show abstract

An interest propagation based movie recommendation method for social tagging system

Feng

2017

2017 International Conference on Machine Learning and Cybernetics (ICMLC)

View full text Add to dashboard Cite

User action interpretation for personalized content optimization in recommender systems

Cited by 5 publications

References 1 publication

Temporal web dynamics and its application to information retrieval

Temporal web dynamics and its application to information retrieval

Exploiting User Preference for Online Learning in Web Content Optimization Systems

An interest propagation based movie recommendation method for social tagging system

Contact Info

Product

Resources

About