JOURNAL OF COMPUTING, VOLUME 2, ISSUE 10, OCTOBER 2010, ISSN 2151-9617HTTPS://SITES.GOOGLE.COM/SITE/JOURNALOFCOMPUTING/ WWW.JOURNALOFCOMPUTING.ORG
Lexeme: An Ontology-Based SemanticAdvertising Networks
Lilac A. Al-Safadi, Aseel Al-Dawood, Nadeen Al-Abdullatif
— Lexeme is a prototype for advertising network that connects Web sites that want to host advertisements withadvertisers who want to run advertisements. Lexeme aims to implement better approaches for reaching and attracting targetcustomers by integrating semantic Web technology and enables computers to know what particular ads mean, to know whatparticular Web sites are about, and to understand the relationships between them all. Advertising networks’ reliance on only thekeywords in the content results in displaying irrelevant and unappealing ads on the Web page. The Semantic-Based AdvertisingNetworks moves beyond simple keywords by understanding all the words on a page, and how they relate to one another. InLexeme, the description of ads and Web site content relies on the ontology that represents the conceptualization of theknowledge domain. Advertiser defines the concept that corresponds to the product or services to sell in their ad along withproperties specifying the characteristics of the product and relationships with other concepts. The paper proposes a novelapproach for matching ads with Web site content using semantic Web technology, illustrated by Lexeme prototype.
— Intelligent Web Services and Semantic Web, Ontology, Electronic commerce, Context Analysis and Indexing.
HE escalation of the Internet as a consumer mediumin the 1990s is unprecedented in the history of media.The Internet made its way into our homes and officesfaster than any other medium (or appliance), reachingfifty-million users in only five years (it took radio thirty-six years to get to that point) . The power of the Inter-net is especially evident in the business industry as mar-keters and advertisers realize the significant financial re-wards the Web can offer. One of the goals of marketing iscontacting potential customers directly, without investingin a big ad or research budget. This is possible with theInternet. Rapid growth in the number of online venueshas led advertisers to market directly, as marketing andadvertising campaigns are using the Web as an efficientpathway into our homes and lives. While banner ads onWeb sites sometimes get no more than one percent re-sponse (compared to five to seven percent for direct mail),the cost is dramatically less. A Web site may cost $5 foreach 1,000 people who view a marketing message, whiledirect mail could average $50 to reach the same 1,000 setsof views . Nevertheless, the basics of marketing con-tinue to hold true.
1.1 Advertising Networks
Advertising networks or ad networks are companies thatconnect Web sites that want to host advertisements withadvertisers who want to run advertisements. Neverthe-less, it is a mistake for these Ad networks to think thatusers are willing to sift through Web pages before theystumble on appealing ads. Advertising networks can onlybe effective when they are able to bring resources andproducts that are of interest to the Web user. AdSense(www.google.com/adsense) is one of the most famous adnetworks. It presents ads based on tracing the contentaround the page and matching keywords with adver-tisements. However, advertising networks' reliance ononly the keywords in the content without an accurateinterpretation of the context of the page, results in dis-playing irrelevant and unappealing ads on the Web page.
1.2 Semantic Web
Semantics is a field that studies the meaning of words,phrases, sentences, and larger units of discourse . Se-mantic technologies enable semantic interoperability forIT systems with different data structures, formats, andvocabularies, without changing the core systems them-selves . The introduction of semantics into the adver-tising networks will solve some of the failed attempts atreaching target audiences and increase the potential toleverage existing information on the Web for far greaterbenefits to advertisers.Unlike humans, computers do not possess a range ofvocabulary understanding. In order to understand whatwords mean and what the relationships between wordsare, a computer has to have documents that describe allthe words and logic to make the necessary connections. In the semantic Web, these documents come fromontologies and schemata. In terms of the Internet, an on-tology is a file that defines the relationships among agroup of terms . A schema is a method for organizinginformation.
L. A. Al-Safadi, A. Al-Dawood, N. Al-Abdullatif are with the Departmentof Information Technology, College of Computer & Information Sciences,King Saud University.