A semantic approach to contextual advertising

Bröder, Arndt; Fontoura, Marcus; Josifovski, Vanja; Riedel, Lance

doi:10.1145/1277741.1277837

Cited by 264 publications

(187 citation statements)

References 10 publications

Supporting

Mentioning

184

Contrasting

Unclassified

Order By: Relevance

“…Prior work tends to focus on sponsored search advertising [4], contextual advertising [3], and display advertising optimized for some action in response to the ad-usually clicks and sometimes more sophisticated conversions. Provost et al [24] describe in detail a broad set of different sorts of data that can be useful for on-line ad targeting.…”

Section: Discussion and Limitationsmentioning

confidence: 99%

“…Provost et al [24] describe in detail a broad set of different sorts of data that can be useful for on-line ad targeting. Unlike this prior work and most actual on-line advertising [4,3] (especially when measured by current advertising spending), the focus of our research is on finding and evaluating audiences for brand advertising. It makes sense that better brand audiences also will be more likely to click or convert, which would be a natural and attractive by-product (but we have not shown this).…”

Section: Discussion and Limitationsmentioning

confidence: 99%

See 1 more Smart Citation

Audience Selection for On-Line Brand Advertising: Privacy-Friendly Social Network Targeting

Provost

D'Alessandro²,

Hook³

et al. 2011

SSRN Journal

View full text Add to dashboard Cite

This paper describes and evaluates privacy-friendly methods for extracting quasi-social networks from browser behavior on user-generated content sites, for the purpose of finding good audiences for brand advertising (as opposed to click maximizing, for example). Targeting social-network neighbors resonates well with advertisers, and on-line browsing behavior data counterintuitively can allow the identification of good audiences anonymously. Besides being one of the first papers to our knowledge on data mining for on-line brand advertising, this paper makes several important contributions. We introduce a framework for evaluating brand audiences, in analogy to predictive-modeling holdout evaluation. We introduce methods for extracting quasi-social networks from data on visitations to social networking pages, without collecting any information on the identities of the browsers or the content of the social-network pages. We introduce measures of brand proximity in the network, and show that audiences with high brand proximity indeed show substantially higher brand affinity. Finally, we provide evidence that the quasi-social network embeds a true social network, which along with results from social theory offers one explanation for the increases in audience brand affinity.

show abstract

Section: Discussion and Limitationsmentioning

confidence: 99%

Section: Discussion and Limitationsmentioning

confidence: 99%

Audience Selection for On-Line Brand Advertising: Privacy-Friendly Social Network Targeting

Provost

D'Alessandro²,

Hook³

et al. 2011

SSRN Journal

View full text Add to dashboard Cite

show abstract

“…al. [9], the authors introduce the class taxonomy to classify ads. This phase acts as a filter before conducting the phrase extraction process and this technique shows a clear improvement.…”

Section: Related Workmentioning

confidence: 99%

Mining Search-Phrase Definitions from Item Descriptions

Nguyen

Davulcu

2008

2008 IEEE 24th International Conference on Data Engineering

View full text Add to dashboard Cite

Abstract-In this paper, we develop a model for representing term dependence based on Markov Random Fields and present an approach based on Markov Chain Monte Carlo technique for generating phrase definitions. This approach can use a small corpus of keyword matching and a random sample of other product descriptions for an advertiser's search-phrase to effectively mine and rank alternative but highly relevant searchphrase definitions. These definitions, which are search-phrases themselves, can then be provided as alternative phrases to an advertiser.

show abstract

“…It is normalized to a value between 0 (no relatedness) and 1 (very high relatedness) and is significantly more powerful than simple keyword based matching. This metric has been steadily gaining attention among Natural Language Processing (NLP) researchers and has been used in several applications such as targeted advertising [5] and web search [12] with positive and beneficial results. We propose to utilize this metric as a measure of relevance of the information, provided by a service, to the user's situation or task.…”

Section: Introductionmentioning

confidence: 99%

Bootstrapped Discovery and Ranking of Relevant Services and Information in Context-aware Systems

Bhargava¹,

Lampton²,

Agrawala³

2015

Proceedings of the 12th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services

View full text Add to dashboard Cite

A context-aware system uses context to provide relevant information and services to the user, where relevancy depends on the user's situation. This relevant information could include a wide range of heterogeneous content. Many existing context-aware systems determine this information based on pre-defined ontologies or rules. In addition, they rely on users' context history to filter it. Moreover, they often provide domain-specific information. Such systems are not applicable to a large and varied set of user situations and information needs, and may suffer from cold start for new users. In this paper, we address these limitations and propose a novel, general and flexible approach for bootstrapped discovery and ranking of heterogeneous relevant services and information in context-aware systems. We design and implement four variations of a base algorithm that ranks candidate relevant services, and the information to be retrieved from them, based on the semantic relatedness between the information provided by the services and the user's situation description. We conduct a live deployment with 14 subjects to evaluate the efficacy of our algorithms. We demonstrate that they have strong positive correlation with human supplied relevance rankings and can be used as an effective means to discover and rank relevant services and information. We also show that our approach is applicable to a wide set of users' situations and to new users without requiring any user interaction history.

show abstract

A semantic approach to contextual advertising

Cited by 264 publications

References 10 publications

Audience Selection for On-Line Brand Advertising: Privacy-Friendly Social Network Targeting

Audience Selection for On-Line Brand Advertising: Privacy-Friendly Social Network Targeting

Mining Search-Phrase Definitions from Item Descriptions

Bootstrapped Discovery and Ranking of Relevant Services and Information in Context-aware Systems

Contact Info

Product

Resources

About