Quality-biased ranking for queries with commercial intent

  title={Quality-biased ranking for queries with commercial intent},
  author={Alexander Shishkin and Polina Zhinalieva and Kirill Nikolaev},
  journal={Proceedings of the 22nd International Conference on World Wide Web},
Modern search engines are good enough to answer popular commercial queries with mainly highly relevant documents. However, our experiments show that users behavior on such relevant commercial sites may differ from one to another web-site with the same relevance label. Thus search engines face the challenge of ranking results that are equally relevant from the perspective of the traditional relevance grading approach. To solve this problem we propose to consider additional facets of relevance… 

Figures and Tables from this paper

Extreme States Distribution Decomposition Method for Search Engine Online Evaluation

A novel method of quantifying the change in the distribution of the key metric is developed, which is interpretable, sensitive to more ways the two distributions may actually differ, and is based on the analysis of the two distribution as a whole.

Optimizing web search engines with interactions

This thesis studies how to use observed interactions between the user and the web search engine to optimize search engines using large datasets annotated by human judges.

Multimodal Marketing Intent Analysis for Effective Targeted Advertising

A novel supervised neural autoregressive model (SmiDocNADE) is proposed to enhance the discriminative capacity of the learned hidden features so that a single system is capable of solving three core questions of multimodalbased marketing intent analysis.

Circular Order Aggregation and Its Application to Cell-Cycle Genes Expressions

Two very different approaches to solve the problem of finding the order among the peak expression of a group of cell cycle genes that use pairwise and triplewise information are proposed.

Circular Order Aggregation and its Application to Cell-cycle Genes Expressions.

Two very different approaches to solve the problem of circular order aggregation that use pairwise and triplewise information are proposed and applied to the cell cycle data that motivated the problem.



Quality-biased ranking of web documents

This paper presents the quality-biased ranking method that promotes documents containing high-quality content, and penalizes low-quality documents, and consistently improves the retrieval performance of text-based and link-based retrieval methods that do not take into account the quality of the document content.

Cumulated gain-based evaluation of IR techniques

This article proposes several novel measures that compute the cumulative gain the user obtains by examining the retrieval result up to a given ranked position, and test results indicate that the proposed measures credit IR methods for their ability to retrieve highly relevant documents and allow testing of statistical significance of effectiveness differences.

Combining anchor text categorization and graph analysis for paid link detection

A novel method of identifying paid links is introduced by training a classifier of anchor text topics and analyzing web pages for diversity of their outgoing commercial links to find pages that sell links and sites that buy links and to identify the paid links.

Time is of the essence: improving recency ranking using Twitter data

A method to use the micro-blogging data stream to detect fresh URLs and to compute novel and effective features for ranking fresh URLs is proposed and demonstrated to improve effective of the portal web search engine for realtime web search.

Large-scale validation and analysis of interleaved search evaluation

This paper provides a comprehensive analysis of interleaving using data from two major commercial search engines and a retrieval system for scientific literature, and analyzes the agreement ofinterleaving with manual relevance judgments and observational implicit feedback measures.

Empirically validated web page design metrics

A quantitative analysis of a large collection of expert-rated web sites reveals that page-level metrics can accurately predict if a site will be highly rated and provides empirical evidence that important metrics differ among web site categories.

Quantifying the effect of user interface design features on cyberstore traffic and sales

Using a regression model, store traffic and dollar sales are predicted as a function of interface design features such as number of links into the store, image sizes, number of products, and store navigation features.

Controlled experiments on the web: survey and practical guide

This work provides a practical guide to conducting online experiments, and shares key lessons that will help practitioners in running trustworthy controlled experiments, including statistical power, sample size, and techniques for variance reduction.

E-Commerce Websites: a Qualitative Evaluation

This work identifies and ranks the main quality attributes to this application domain and the survey of the attributes was based on the specialized literature and on the analysis of significant websites.

Making sense of credibility on the Web: Models for evaluating online information and recommendations for future research

This article summarizes much of what is known from the communication and information literacy fields about the skills that Internet users need to assess the credibility of online information to assist users in locating reliable information online.