Conference Paper

Using the geographic scopes of web documents for contextual advertising

DOI: 10.1145/1722080.1722103 Conference: Proceedings of the 6th Workshop on Geographic Information Retrieval, GIR 2010, Zurich, Switzerland, February 18-19, 2010
Source: DBLP


Geotargeting is a specialization of contextual advertising where the objective is to target ads to Website visitors concentrated in well-defined areas. Current approaches involve targeting ads based on the physical location of the visitors, estimated through their IP addresses. However, there are many situations where it would be more interesting to target ads based on the geographic scope of the target pages, i.e., on the general area implied by the locations mentioned in the textual contents of the pages. Our proposal applies techniques from the area of geographic information retrieval to the problem of geotargeting. We address the task through a pipeline of processing stages, which involves (i) determining the geographic scope of target pages, (ii) classifying target pages according to locational relevance, and (iii) retrieving ads relevant to the target page, using both textual contents and geographic scopes. Experimental results attest for the adequacy of the proposed methods in each of the individual processing stages.

Full-text preview

Available from:
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Location Based Services (LBS) belong to the most popular type of mobile applications today. Most of the content in LBS has to be created from scratch and needs to be explicitly location-tagged, which makes existing web content not directly usable for LBS. In this paper we aim at making websites location-aware and feed this information to LBS. For this purpose we first present SALT, an engine that receives websites as input and equips them with location-tags. Compared to other approaches, SALT is capable of extracting locations with a precision up to the street level. While the engine basically works unsupervised, it is also capable to handle user-feedback to improve the results. Second, we present as a use case of SALT. offers location-aware web surfing through a mobile website. It displays nearby websites depending on: 1) the user's current location and 2) the currently visited website. Finally we show that our application has a high acceptance from users through a formative user study.
    Procedia Computer Science 12/2012; 10:601–608. DOI:10.1016/j.procs.2012.06.077
  • [Show abstract] [Hide abstract]
    ABSTRACT: The growing availability of data in electronic form, the expansion of the World Wide Web (WWW) and the accessibility of computational methods for large-scale data processing have allowed researchers in Information Retrieval (IR) to design systems which can effectively and efficiently constrain search within the boundaries given by context, thus transforming classical search into contextual search. Because of the constraints imposed by context, contextual search better focuses on the user's relevance and improves retrieval performance, since the out-of-context aspects of the search carried out by users that are likely linked to irrelevant documents are left apart. This survey introduces contextual search within a computational framework based on contextual variables, contextual factors and statistical models. The framework adopted in this survey considers the data observable from the real world entities participating in contextual search and classifies them as whatwe call contextual variables. The contextual variables considered are content, geotemporal, interaction, and social variables. Moreover, we distinguish between contextual variables and contextual factor: the former is what can be observed, the latter is what cannot be observed, yet this is the factor affecting the user's relevance assessment. Therefore, in this survey, we describe how statistical models can process contextual variables to infer the contextual factors underlying the current search context. In this survey we provide a background to the subject by: placing it among other surveys on relevance, interaction, context, and behavior; providing the description of the contextual variables used for implementing the statistical models which represent and predict relevance and contextual factors; citing and surveying useful publications to the reader for further examination; providing an overview of the evaluation methodologies and findings relevant to this subject; and briefly describing some implementations of contextual search tools.
    01/2012; 6(4-5-4-5):257-405. DOI:10.1561/1500000023
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Traditional information retrieval (IR) systems show significant limitations on returning relevant documents that satisfy the user's information needs. In particular, to answer geographic and temporal user queries, the IR task becomes a nonstraightforward process where the available geographic and temporal information is often unstructured. In this article, we propose a geotemporal search approach that consists of modeling and exploiting geographic and temporal query context evidence that refers to implicit multivarying geographic and temporal intents behind the query. Modeling geographic and temporal query contexts is based on extracting and ranking geographic and temporal keywords found in pseudo-relevant feedback (PRF) documents for a given query. Our geotemporal search approach is based on exploiting the geographic and temporal query contexts separately into a probabilistic ranking model and jointly into a proximity ranking model. Our hypothesis is based on the concept that geographic and temporal expressions tend to co-occur within the document where the closer they are in the document, the more relevant the document is. Finally, geographic, temporal, and proximity scores are combined according to a linear combination formula. An extensive experimental evaluation conducted on a portion of the New York Times news collection and the TREC 2004 robust retrieval track collection shows that our geotemporal approach outperforms significantly a well-known baseline search and the best known geotemporal search approaches in the domain. Finally, an in-depth analysis shows a positive correlation between the geographic and temporal query sensitivity and the retrieval performance. Also, we find that geotemporal distance has a positive impact on retrieval performance generally. © 2013 Wiley Periodicals, Inc.
    Journal of the American Society for Information Science and Technology 01/2013; 64(1):190-212. DOI:10.1002/asi.22648 · 1.85 Impact Factor