1 / 16

Key Blog Distillation: Ranking Aggregates

Key Blog Distillation: Ranking Aggregates. Presenter : Yu-hui Huang Authors :Craig Macdonald, Iadh Ounis. 國立雲林科技大學 National Yunlin University of Science and Technology. CIKM 2009. Outline. Motivation Objective Methodology Experiments Conclusion Comments.

merwin
Download Presentation

Key Blog Distillation: Ranking Aggregates

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Key Blog Distillation: Ranking Aggregates Presenter : Yu-hui Huang Authors :Craig Macdonald, Iadh Ounis 國立雲林科技大學 National Yunlin University of Science and Technology CIKM 2009

  2. Outline • Motivation • Objective • Methodology • Experiments • Conclusion • Comments

  3. Motivation • Help user to look for blogs that interest them. • What is importance degree for each search result .

  4. Objective • To provide key blogs relevant to the query topic area. • Ranking the blog according to degree of importance. • Blog distillation :could be add search feet to directories or return suggest for his/her RSS.

  5. Methodology • Ranking:

  6. Methodology • Ranking:

  7. Methodology • Weight function • qtw:don’t ask me 

  8. Methodology • Three hypotheses: to model more fully the definition of a relevant blog given to the assessors. • Central Interest: If the posts of each blog are clustered, then relevant blogs will have blog posts about the topic in one of the larger clusters. • Recurring Interest: Relevant blogs will cover the topic many times across the timespan of the collection. • Focused Interest: Relevant blogs will mainly blog around a central topic area - i.e. they will have a coherent language model with which they blog.

  9. Methodology • Central interest: (quality score) • cluster(p;B) is the rank of the cluster in which post p occurred for blog B (largest cluster has rank 1).

  10. Methodology • Recurring interest:

  11. Methodology • Focused interest:

  12. Experiments

  13. Methodology • Mean Average Precision (MAP) • Mean Reciprocal Rank(MRR) • P @ rank 10: precision @ rank 10 direct translated into Chinese please

  14. Experiments

  15. Conclusion • Add normalization component to the voting techniques that could indeed improve the retrieval performance. • Authors consider that using the XML content will reduce the amount of noise. (god) 15

  16. Comments • Advantage • … • Drawback • This paper is non detail • Can description for example • Application • Search engine (maybe)

More Related