| Authors: |
Steven M. Beitzel
and Eric C. Jensen
and Abdur Chowdhury
and Ophir Frieder
and David Grossman
|
| URL: |
http://portal.acm.org/citation.cfm?id=1190282 |
| Description: |
Temporal analysis of a very large topically categorized Web query log |
| Tags: |
exploratory
log
query
trends
|
| Abstract: |
The authors review a log of billions of Web queries that constituted the total query traffic for a 6-month period of a general-purpose commercial Web search service. Previously, query logs were studied from a single, cumulative view. In contrast, this study builds on the authors' previous work, which showed changes in popularity and uniqueness of topically categorized queries across the hours in a day. To further their analysis, they examine query traffic on a daily, weekly, and monthly basis by matching it against lists of queries that have been topically precategorized by human editors. These lists represent 13% of the query traffic. They show that query traffic from particular topical categories differs both from the query stream as a whole and from other categories. Additionally, they show that certain categories of queries trend differently over varying periods. The authors key contribution is twofold: They outline a method for studying both the static and topical properties of a very large query log over varying periods, and they identify and examine topical trends that may provide valuable insight for improving both retrieval effectiveness and efficiency. © 2007 Wiley Periodicals, Inc. |
@article{Beitzel07temporal,
title = {Temporal analysis of a very large topically categorized Web query log},
address = {New York, NY, USA},
author = {Steven M. Beitzel and Eric C. Jensen and Abdur Chowdhury and Ophir Frieder and David Grossman},
journal = {J. Am. Soc. Inf. Sci. Technol.},
number = {2},
pages = {166--178},
publisher = {John Wiley \& Sons, Inc.},
url = {http://portal.acm.org/citation.cfm?id=1190282},
volume = {58},
year = {2007},
description = {Temporal analysis of a very large topically categorized Web query log},
abstract = {The authors review a log of billions of Web queries that constituted the total query traffic for a 6-month period of a general-purpose commercial Web search service. Previously, query logs were studied from a single, cumulative view. In contrast, this study builds on the authors' previous work, which showed changes in popularity and uniqueness of topically categorized queries across the hours in a day. To further their analysis, they examine query traffic on a daily, weekly, and monthly basis by matching it against lists of queries that have been topically precategorized by human editors. These lists represent 13% of the query traffic. They show that query traffic from particular topical categories differs both from the query stream as a whole and from other categories. Additionally, they show that certain categories of queries trend differently over varying periods. The authors key contribution is twofold: They outline a method for studying both the static and topical properties of a very large query log over varying periods, and they identify and examine topical trends that may provide valuable insight for improving both retrieval effectiveness and efficiency. © 2007 Wiley Periodicals, Inc.},
issn = {1532-2882}, doi = {http://dx.doi.org/10.1002/asi.v58:2},
keywords = {exploratory log query trends }
}
::