ACM Home Page
Please provide us with feedback. Feedback
Search advertising using web relevance feedback
Full text PdfPdf (287 KB)
Source
Conference on Information and Knowledge Management archive
Proceeding of the 17th ACM conference on Information and knowledge management table of contents
Napa Valley, California, USA
SESSION: IR: advertising & filtering table of contents
Pages 1013-1022  
Year of Publication: 2008
ISBN:978-1-59593-991-3
Authors
Andrei Z. Broder  Yahoo! Research, Santa Clara, CA, USA
Peter Ciccolo  Yahoo! Research, Santa Clara, CA, USA
Marcus Fontoura  PUC-Rio, Rio de Janeiro, Brazil
Evgeniy Gabrilovich  Yahoo! Research, Santa Clara, CA, USA
Vanja Josifovski  Yahoo! Research, Santa Clara, CA, USA
Lance Riedel  Yahoo! Research, Santa Clara, CA, USA
Sponsors
ACM: Association for Computing Machinery
SIGWEB: ACM Special Interest Group on Hypertext, Hypermedia, and Web
SIGIR: ACM Special Interest Group on Information Retrieval
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 34,   Downloads (12 Months): 286,   Citation Count: 8
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1458082.1458217
What is a DOI?

ABSTRACT

The business of Web search, a $10 billion industry, relies heavily on sponsored search, whereas a few carefully-selected paid advertisements are displayed alongside algorithmic search results. A key technical challenge in sponsored search is to select ads that are relevant for the user's query. Identifying relevant ads is challenging because queries are usually very short, and because users, consciously or not, choose terms intended to lead to optimal Web search results and not to optimal ads. Furthermore, the ads themselves are short and usually formulated to capture the reader's attention rather than to facilitate query matching.

Traditionally, matching of ads to queries employed standard information retrieval techniques using the bag of words approach. Here we propose to go beyond the bag of words, and augment both queries and ads with additional knowledge-rich features. We use Web search results initially returned for the query to create a pool of relevant documents. Classifying these documents with respect to an external taxonomy and identifying salient named entities give rise to two new feature types. Empirical evaluation based on over 9,000 query-ad pairwise judgments confirms that using augmented queries produces highly relevant ads. Our methodology also relaxes the requirement for each ad to explicitly specify the exhaustive list of queries ("bid phrases") that can trigger it.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

1
2
3
4
 
5
 
6
P. N. Bennett, S. T. Dumais, and E. Horvitz. Inductive transfer for text classification using generalized reliability indicators. In Proceedings of the ICML-2003 Workshop on The Continuum from Labeled to Unlabeled Data, 2003.
7
8
 
9
61 billion searches conducted worldwide in August. comscore, October 2007. Available from http://www.comscore.com/press/release.asp?press=1802.
10
11
 
12
C. Do and A. Ng. Transfer learning for text classification. In Proceedings of Neural Information Processing Systems (NIPS), 2005.
 
13
R. Duda and P. Hart. Pattern Classification and Scene Analysis. John Wiley and Sons, 1973.
 
14
B. Edelman, M. Ostrovsky, and M. Schwarz. Internet advertising and the generalized second price auction: Selling billions of dollars worth of keywords. American Economic Review, 97(1):242--259, 2007.
 
15
E. Efthimiadis and P. Biron. UCLA-okapi at TREC-2: Query expansion experiments. In Proceedings of TREC-2, 1994.
 
16
D. Fain and J. Pedersen. Sponsored search: A brief history. In Second Workshop on Sponsored Search Auctions, 2006.
 
17
E. Gabrilovich and S. Markovitch. Feature generation for text categorization using world knowledge. In Proceedings of the 19th International Joint Conference on Artificial Intelligence, pages 1048--1053, Edinburgh, Scotand, August 2005.
18
 
19
20
21
22
23
 
24
 
25
P. Kowalczyk, I. Zukerman, and M. Niemann. Analyzing the effect of query class on document retrieval performance. In Proceedings of the Australian Conference on Artificial Intelligence, pages 550--561, 2004.
26
 
27
28
29
 
30
D. Metzler, S. Dumais, and C. Meek. Similarity measures for short segments of text. In Proceedings of the 29th European Conference on Information Retrieval, pages 16--27, 2007.
31
 
32
M. Porter. An algorithm for suffix stripping. Program, 14(3):130--137, 1980.
33
34
 
35
S. Robertson, S. Walker, S. Jones, M. Hancock-Beaulieu, and M. Gatford. Okapi at TREC-3. In Proceedings of TREC-3, 1995.
 
36
S. E. Robertson, S. Walker, S. Jones, M. Hancock-Beaulieu, and M. Gatford. okapi at TREC-3. In Proceedings of the 3rd Text REtrieval Conference, 1994.
 
37
J. J. Rocchio. Relevance feedback in information retrieval. In The SMART Retrieval System: Experiments in Automatic Document Processing, pages 313--323. Prentice Hall, 1971.
38
 
39
 
40
G. Salton and C. Buckley. Improving retrieval performance by relevance feedback. Journal of the American Society for Information Science, 41(4):288--297, 1990.
 
41
42
43
44
 
45
 
46
C. Sutton and A. McCallum. Composition of conditional random fields for transfer learning. In Emprical Methods in Natural Language Processing (HLT/EMNLP), 1998.
47
 
48
 
49
C. Wang, P. Zhang, R. Choi, and M. D. Eredita. Understanding consumers attitude toward advertising. In 8th Americas Conference on Information Systems, 2002.
50
51
52
53

CITED BY  8

Collaborative Colleagues:
Andrei Z. Broder: colleagues
Peter Ciccolo: colleagues
Marcus Fontoura: colleagues
Evgeniy Gabrilovich: colleagues
Vanja Josifovski: colleagues
Lance Riedel: colleagues