Bu öğeden alıntı yapmak, öğeye bağlanmak için bu tanımlayıcıyı kullanınız: http://hdl.handle.net/11452/21118
Başlık: Analysis of large data logs: an application of Poisson sampling on excite web queries
Yazarlar: Uludağ Üniversitesi/Mühendislik Fakültesi.
Özmutlu, H. Cenk
Spink, A.
Özmutlu, Seda
AAH-4480-2021
ABH-5209-2020
Anahtar kelimeler: Computer science
Information science & library science
Poisson sampling
Users
Large-scale in depth data analysis
Web user modeling
Search engine queries
Data mining
Yayın Tarihi: Tem-2002
Yayıncı: Pergamon-Elsevier Science
Atıf: Özmutlu, H. C. vd. (2002). "Analysis of large data logs: an application of Poisson sampling on excite web queries". Information Processing & Management, 38(4), 473-490.
Özet: Search engines are the gateway for users to retrieve information from the Web. There is a crucial need for tools that allow effective analysis of search engine queries to provide a greater understanding of Web users' information seeking behavior. The objective of the study is to develop an effective strategy for the selection of samples from large-scale data sets. Millions of queries are submitted to Web search engines daily and new sampling techniques are required to bring these databases to a manageable size, while preserving the statistically representative characteristics or the entire data set. This paper reports results from a study using data logs from the Excite Web search engine, We use Poisson sampling to develop a sampling strategy. and show how sample sets selected by Poisson sampling statistically effectively represent the characteristics of the entire dataset. In addition, this paper discusses the use of Poisson sampling in continuous monitoring of stochastic processes, such as Web site dynamics.
URI: https://doi.org/10.1016/S0306-4573(01)00043-7
https://www.sciencedirect.com/science/article/pii/S0306457301000437
http://hdl.handle.net/11452/21118
ISSN: 0306-4573
Koleksiyonlarda Görünür:Web of Science

Bu öğenin dosyaları:
Bu öğeyle ilişkili dosya bulunmamaktadır.


DSpace'deki bütün öğeler, aksi belirtilmedikçe, tüm hakları saklı tutulmak şartıyla telif hakkı ile korunmaktadır.