Implementation and Evaluation of a Quality Based Search Engine

Mandl, Thomas Implementation and Evaluation of a Quality Based Search Engine., 2006 . In 17th ACM Conference on Hypertext and Hypermedia (HT '06), Odense, Denmark, 2006 August 22nd –25th. (Unpublished) [Presentation]

[thumbnail of Mandl__Presentation-ACM_HT2006@Odense_AQUAINT.ppt.pdf]
Preview
PDF
Mandl__Presentation-ACM_HT2006@Odense_AQUAINT.ppt.pdf

Download (1MB) | Preview

English abstract

In this paper, an approach for the implementation of a quality-based Web search engine is proposed. Quality retrieval is introduced and an overview on previous efforts to implement such a service is given. Machine learning approaches are identified as the most promising methods to determine the quality of Web pages. Features for the most appropriate characterization of Web pages are determined. A quality model is developed based on human judgments. This model is integrated into a meta search engine which assesses the quality of all results at run time. The evaluation results show that quality based ranking does lead to better results concerning the perceived quality of Web pages presented in the result set. The quality models are exploited to identify potentially important features and characteristics for the quality of Web pages.

Item type: Presentation
Keywords: web information retrieval, automatic quality evaluation, user study
Subjects: L. Information technology and library technology > LM. Automatic text retrieval.
L. Information technology and library technology > LS. Search engines.
L. Information technology and library technology > LC. Internet, including WWW.
Depositing user: Thomas Mandl
Date deposited: 29 Aug 2006
Last modified: 02 Oct 2014 12:04
URI: http://hdl.handle.net/10760/8032

References

Jensen, Niels; Mandl, Thomas (2006): Different Indexing Strategies for Multilingual Web Retrieval: Experiments with the EuroGOV Corpus. In: Proceedings of the 17th ACM Conference on Hypertext and Hypermedia (HT '06) Odense, Denmark, August 22nd –25th. ACM Press. S. 169-170. http://doi.acm.org/10.1145/1149941.1149974


Downloads

Downloads per month over past year

Actions (login required)

View Item View Item