-
Multimedia content and the Semantic Web : methods, standards, and tools (2005)
0.05
0.04779466 = product of:
0.09558932 = sum of:
0.09558932 = sum of:
0.06502452 = weight(_text_:web in 150) [ClassicSimilarity], result of:
0.06502452 = score(doc=150,freq=36.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.38244262 = fieldWeight in 150, product of:
6.0 = tf(freq=36.0), with freq of:
36.0 = termFreq=36.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.01953125 = fieldNorm(doc=150)
0.030564802 = weight(_text_:22 in 150) [ClassicSimilarity], result of:
0.030564802 = score(doc=150,freq=6.0), product of:
0.18244034 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.052098576 = queryNorm
0.16753313 = fieldWeight in 150, product of:
2.4494898 = tf(freq=6.0), with freq of:
6.0 = termFreq=6.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.01953125 = fieldNorm(doc=150)
0.5 = coord(1/2)
- Classification
- 006.7 22
- Date
- 7. 3.2007 19:30:22
- DDC
- 006.7 22
- Footnote
- Rez. in: JASIST 58(2007) no.3, S.457-458 (A.M.A. Ahmad): "The concept of the semantic web has emerged because search engines and text-based searching are no longer adequate, as these approaches involve an extensive information retrieval process. The deployed searching and retrieving descriptors arc naturally subjective and their deployment is often restricted to the specific application domain for which the descriptors were configured. The new era of information technology imposes different kinds of requirements and challenges. Automatic extracted audiovisual features are required, as these features are more objective, domain-independent, and more native to audiovisual content. This book is a useful guide for researchers, experts, students, and practitioners; it is a very valuable reference and can lead them through their exploration and research in multimedia content and the semantic web. The book is well organized, and introduces the concept of the semantic web and multimedia content analysis to the reader through a logical sequence from standards and hypotheses through system examples, presenting relevant tools and methods. But in some chapters readers will need a good technical background to understand some of the details. Readers may attain sufficient knowledge here to start projects or research related to the book's theme; recent results and articles related to the active research area of integrating multimedia with semantic web technologies are included. This book includes full descriptions of approaches to specific problem domains such as content search, indexing, and retrieval. This book will be very useful to researchers in the multimedia content analysis field who wish to explore the benefits of emerging semantic web technologies in applying multimedia content approaches. The first part of the book covers the definition of the two basic terms multimedia content and semantic web. The Moving Picture Experts Group standards MPEG7 and MPEG21 are quoted extensively. In addition, the means of multimedia content description are elaborated upon and schematically drawn. This extensive description is introduced by authors who are actively involved in those standards and have been participating in the work of the International Organization for Standardization (ISO)/MPEG for many years. On the other hand, this results in bias against the ad hoc or nonstandard tools for multimedia description in favor of the standard approaches. This is a general book for multimedia content; more emphasis on the general multimedia description and extraction could be provided.
Semantic web technologies are explained, and ontology representation is emphasized. There is an excellent summary of the fundamental theory behind applying a knowledge-engineering approach to vision problems. This summary represents the concept of the semantic web and multimedia content analysis. A definition of the fuzzy knowledge representation that can be used for realization in multimedia content applications has been provided, with a comprehensive analysis. The second part of the book introduces the multimedia content analysis approaches and applications. In addition, some examples of methods applicable to multimedia content analysis are presented. Multimedia content analysis is a very diverse field and concerns many other research fields at the same time; this creates strong diversity issues, as everything from low-level features (e.g., colors, DCT coefficients, motion vectors, etc.) up to the very high and semantic level (e.g., Object, Events, Tracks, etc.) are involved. The second part includes topics on structure identification (e.g., shot detection for video sequences), and object-based video indexing. These conventional analysis methods are supplemented by results on semantic multimedia analysis, including three detailed chapters on the development and use of knowledge models for automatic multimedia analysis. Starting from object-based indexing and continuing with machine learning, these three chapters are very logically organized. Because of the diversity of this research field, including several chapters of recent research results is not sufficient to cover the state of the art of multimedia. The editors of the book should write an introductory chapter about multimedia content analysis approaches, basic problems, and technical issues and challenges, and try to survey the state of the art of the field and thus introduce the field to the reader.
The final part of the book discusses research in multimedia content management systems and the semantic web, and presents examples and applications for semantic multimedia analysis in search and retrieval systems. These chapters describe example systems in which current projects have been implemented, and include extensive results and real demonstrations. For example, real case scenarios such as ECommerce medical applications and Web services have been introduced. Topics in natural language, speech and image processing techniques and their application for multimedia indexing, and content-based retrieval have been elaborated upon with extensive examples and deployment methods. The editors of the book themselves provide the readers with a chapter about their latest research results on knowledge-based multimedia content indexing and retrieval. Some interesting applications for multimedia content and the semantic web are introduced. Applications that have taken advantage of the metadata provided by MPEG7 in order to realize advance-access services for multimedia content have been provided. The applications discussed in the third part of the book provide useful guidance to researchers and practitioners properly planning to implement semantic multimedia analysis techniques in new research and development projects in both academia and industry. A fourth part should be added to this book: performance measurements for integrated approaches of multimedia analysis and the semantic web. Performance of the semantic approach is a very sophisticated issue and requires extensive elaboration and effort. Measuring the semantic search is an ongoing research area; several chapters concerning performance measurement and analysis would be required to adequately cover this area and introduce it to readers."
- LCSH
- Semantic Web
- RSWK
- Semantic Web / Multimedia / Automatische Indexierung / Information Retrieval
- Subject
- Semantic Web / Multimedia / Automatische Indexierung / Information Retrieval
Semantic Web
- Theme
- Semantic Web
-
Tjondronegoro, D.; Spink, A.: Web search engine multimedia functionality (2008)
0.03
0.030499205 = product of:
0.06099841 = sum of:
0.06099841 = product of:
0.12199682 = sum of:
0.12199682 = weight(_text_:web in 2038) [ClassicSimilarity], result of:
0.12199682 = score(doc=2038,freq=22.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.717526 = fieldWeight in 2038, product of:
4.690416 = tf(freq=22.0), with freq of:
22.0 = termFreq=22.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.046875 = fieldNorm(doc=2038)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- Web search engines are beginning to offer access to multimedia searching, including audio, video and image searching. In this paper we report findings from a study examining the state of multimedia search functionality on major general and specialized Web search engines. We investigated 102 Web search engines to examine: (1) how many Web search engines offer multimedia searching, (2) the type of multimedia search functionality and methods offered, such as "query by example", and (3) the supports for personalization or customization which are accessible as advanced search. Findings include: (1) few major Web search engines offer multimedia searching and (2) multimedia Web search functionality is generally limited. Our findings show that despite the increasing level of interest in multimedia Web search, those few Web search engines offering multimedia Web search, provide limited multimedia search functionality. Keywords are still the only means of multimedia retrieval, while other methods such as "query by example" are offered by less than 1% of Web search engines examined.
-
E-Text : Strategien und Kompetenzen. Elektronische Kommunikation in Wissenschaft, Bildung und Beruf (2001)
0.03
0.026378417 = product of:
0.052756835 = sum of:
0.052756835 = sum of:
0.024522282 = weight(_text_:web in 622) [ClassicSimilarity], result of:
0.024522282 = score(doc=622,freq=2.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.14422815 = fieldWeight in 622, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.03125 = fieldNorm(doc=622)
0.028234553 = weight(_text_:22 in 622) [ClassicSimilarity], result of:
0.028234553 = score(doc=622,freq=2.0), product of:
0.18244034 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.052098576 = queryNorm
0.15476047 = fieldWeight in 622, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.03125 = fieldNorm(doc=622)
0.5 = coord(1/2)
- Abstract
- Elektronische Produktion, Verbreitung und Rezeption von Texten - deren integrative Wechselbeziehungen eingeschlossen - verändern unausweichlich unsere Forschungs-, Lernund Arbeitsbedingungen. In diesem Wandel braucht es Orientierung, Strategien und Kompetenzen. Dieser Band bietet sie in interdisziplinärer Vielfalt. Teil 1 befaßt sich mit Wissen und Wissenschaft. Er spannt den Bogen der Medientheorie von der Antike bis ins 21. Jahrhundert und bietet einen konstruktivistischen Ansatz für das Wissensmanagement. Textsortenkonventionen und Hypertext sind ebenso Schwerpunkte wie empiriegestützte Guidelines und innovative Werkzeuge für das wissenschaftliche Arbeiten. Teil 2 ist Lernumgebungen gewidmet. Reflexionen zur Theorie von hypermedialem Lernen und Kognition werden ergänzt durch ein Produktionssystem für interaktive Software. Eine Felduntersuchungvergleicht Varianten kooperativen Schreibens, ein Schreibdidaktik-Projekt vermittelt zwischen Studium und Beruf. Teil 3 vereint unter dem Titel «Domänen der Praxis» empirische Erhebungen zur Text(re)produktion und elektronischen Kommunikation im Berufsalltag, die Konzeption eines Werkzeugs für die Übersetzungsarbeit und den Ausblick auf kulturspezifische Web-Sites in der Wirtschaft.
- Date
- 12. 8.2012 18:05:22
-
Ozmutlu, S.; Spink, A.; Ozmutlu, H.C.: Multimedia Web searching trends : 1997-2001 (2003)
0.03
0.026279347 = product of:
0.052558694 = sum of:
0.052558694 = product of:
0.10511739 = sum of:
0.10511739 = weight(_text_:web in 1072) [ClassicSimilarity], result of:
0.10511739 = score(doc=1072,freq=12.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.6182494 = fieldWeight in 1072, product of:
3.4641016 = tf(freq=12.0), with freq of:
12.0 = termFreq=12.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.0546875 = fieldNorm(doc=1072)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- Multimedia is proliferating on Web sites, as the Web continues to enhance the integration of multimedia and textual information. In this paper we examine trends in multimedia Web searching by Excite users from 1997 to 2001. Results from an analysis of 1,025,910 Excite queries from 2001 are compared to similar Excite datasets from 1997 to 1999. Findings include: (1) queries per multimedia session have decreased since 1997 as a proportion of general queries due to the introduction of multimedia buttons near the query box, (2) multimedia queries identified are longer than non-multimedia queries, and (3) audio queries are more prevalent than image or video queries in identified multimedia queries. Overall, we see multimedia Web searching undergoing major changes as Web content and searching evolves.
-
Cunliffe, D.; Herring, S.C.: Introduction to minority languages, multimedia and the Web (2005)
0.03
0.026009807 = product of:
0.052019615 = sum of:
0.052019615 = product of:
0.10403923 = sum of:
0.10403923 = weight(_text_:web in 4771) [ClassicSimilarity], result of:
0.10403923 = score(doc=4771,freq=4.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.6119082 = fieldWeight in 4771, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.09375 = fieldNorm(doc=4771)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Content
- Einleitung in ein Themenheft "Minority languages, multimedia and the Web"
-
Tjondronegoro, D.; Spink, A.; Jansen, B.J.: ¬A study and comparison of multimedia Web searching : 1997-2006 (2009)
0.02
0.024233207 = product of:
0.048466414 = sum of:
0.048466414 = product of:
0.09693283 = sum of:
0.09693283 = weight(_text_:web in 3090) [ClassicSimilarity], result of:
0.09693283 = score(doc=3090,freq=20.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.5701118 = fieldWeight in 3090, product of:
4.472136 = tf(freq=20.0), with freq of:
20.0 = termFreq=20.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.0390625 = fieldNorm(doc=3090)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- Searching for multimedia is an important activity for users of Web search engines. Studying user's interactions with Web search engine multimedia buttons, including image, audio, and video, is important for the development of multimedia Web search systems. This article provides results from a Weblog analysis study of multimedia Web searching by Dogpile users in 2006. The study analyzes the (a) duration, size, and structure of Web search queries and sessions; (b) user demographics; (c) most popular multimedia Web searching terms; and (d) use of advanced Web search techniques including Boolean and natural language. The current study findings are compared with results from previous multimedia Web searching studies. The key findings are: (a) Since 1997, image search consistently is the dominant media type searched followed by audio and video; (b) multimedia search duration is still short (>50% of searching episodes are <1 min), using few search terms; (c) many multimedia searches are for information about people, especially in audio search; and (d) multimedia search has begun to shift from entertainment to other categories such as medical, sports, and technology (based on the most repeated terms). Implications for design of Web multimedia search engines are discussed.
-
Jörgensen, C.: ¬The MPEG-7 standard : multimedia description in theory and application (2007)
0.02
0.020274958 = product of:
0.040549915 = sum of:
0.040549915 = product of:
0.08109983 = sum of:
0.08109983 = weight(_text_:web in 472) [ClassicSimilarity], result of:
0.08109983 = score(doc=472,freq=14.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.47698978 = fieldWeight in 472, product of:
3.7416575 = tf(freq=14.0), with freq of:
14.0 = termFreq=14.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.0390625 = fieldNorm(doc=472)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- Allowing the description of the structure of documents has been one of the key factors for the success of the hypertext markup language (HTML) family of markup languages. This capability has motivated the phenomenon that has become known as the World Wide Web (the "Web"). The next generation of the Web, known as the Semantic Web (Berners-Lee, Hendler. & Lassila, 2001), aims at describing the meaning rather than the structure of data, adding more intelligent search, retrieval, and other agent functionalities to the Web, and tools that make the implementation of this Semantic Web possible are greatly needed. The increasing availability of multimedia on the World Wide Web makes metadata description efforts for multimedia a pressing need, yet with the volume of content being created, often only a rudimentary description of the multimedia content is available. In addition, the digital mode entails a host of other descriptive needs, such as the format, factors such as compression and transmission, and issues such as copyright restrictions and terns for usage. Thus, new and efficient ways of describing multimedia content and meaning are needed as well as a structure that is capable of carrying such descriptions. Several attempts have been made to grapple with this issue using descriptive metadata, one of the earliest of which was the revision of the Dublin Core to ascertain essential features necessary to resource discovery of visual items in a networked environment (Weibel & Miller, 1997). Other metadata schemes, such as the Visual Resources Association Core Categories (http://www.vraweb.org/vracore3.htm), also include format information necessary to the use and display of digital images.
-
Greenberg, B.; Schipprack, A.: Blick zurück & nach vorn : Von der Film- und Video-Produktion zum Web-Design (2000)
0.02
0.01839171 = product of:
0.03678342 = sum of:
0.03678342 = product of:
0.07356684 = sum of:
0.07356684 = weight(_text_:web in 5044) [ClassicSimilarity], result of:
0.07356684 = score(doc=5044,freq=2.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.43268442 = fieldWeight in 5044, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.09375 = fieldNorm(doc=5044)
0.5 = coord(1/2)
0.5 = coord(1/2)
-
Visual based retrieval systems and Web mining (2001)
0.02
0.01839171 = product of:
0.03678342 = sum of:
0.03678342 = product of:
0.07356684 = sum of:
0.07356684 = weight(_text_:web in 179) [ClassicSimilarity], result of:
0.07356684 = score(doc=179,freq=2.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.43268442 = fieldWeight in 179, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.09375 = fieldNorm(doc=179)
0.5 = coord(1/2)
0.5 = coord(1/2)
-
Loviscach, J.: ¬Die elektronische Uni : Neue Medien in der Lehre (2001)
0.01
0.014117276 = product of:
0.028234553 = sum of:
0.028234553 = product of:
0.056469105 = sum of:
0.056469105 = weight(_text_:22 in 5627) [ClassicSimilarity], result of:
0.056469105 = score(doc=5627,freq=2.0), product of:
0.18244034 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.052098576 = queryNorm
0.30952093 = fieldWeight in 5627, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0625 = fieldNorm(doc=5627)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Date
- 14. 2.2001 19:09:22
-
Schweibenz, W.: Evaluation des Intranet-Angebots Multimediales Lernen bei DaimlerCrysler, Standort Stuttgart (2001)
0.01
0.013004904 = product of:
0.026009807 = sum of:
0.026009807 = product of:
0.052019615 = sum of:
0.052019615 = weight(_text_:web in 5852) [ClassicSimilarity], result of:
0.052019615 = score(doc=5852,freq=4.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.3059541 = fieldWeight in 5852, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.046875 = fieldNorm(doc=5852)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- Der Beitrag beschreibt eine Usability-Studie zur Evaluation eines betrieblichen IntranetAngebots zum Thema Multimediales Lernen. Es wurde eine mehrstufige, kombinierte Evaluation durchgeführt eine heuristische Evaluation mit den neu entwickelten Heuristicsfor Web Communication als expertenorientierte Methode und ein Produkttest (Benutzertest) im Usability-Labor mit der Methode des lauten Denkens als benutzerorientierte Methode. Die Durchführung der Studie wird beschrieben und die Methoden diskutiert. Die Heuristics for Web Communication benötigen geschulte Gutachter, sind schnell und einfach anzuwenden und unterstützen ein systematisches Vorgehen beim Entdecken von Usability-Problemen. Die Evaluation mit den Heuristiken ist gut kombinierbar mit einem Benutzertest und ergänzt ihn, indem sie Usability-Probleme aufdeckt, die in Produkttests vermutlich nicht gefunden werden. Der Aufwand für den Produkttest ist sehr hoch, er liefert anschauliche und aussagekräftige Aussagen von echten Nutzern und rechtfertigt unter Umständen den Aufwand
-
Mandl, T.: Web- und Multimedia-Dokumente : Neuere Entwicklungen bei der Evaluierung von Information Retrieval Systemen (2003)
0.01
0.012261141 = product of:
0.024522282 = sum of:
0.024522282 = product of:
0.049044564 = sum of:
0.049044564 = weight(_text_:web in 1734) [ClassicSimilarity], result of:
0.049044564 = score(doc=1734,freq=2.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.2884563 = fieldWeight in 1734, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.0625 = fieldNorm(doc=1734)
0.5 = coord(1/2)
0.5 = coord(1/2)
-
Agnew, G.; Kniesner, D.; Weber, M.B.: Integrating MPEG-7 into the moving image collections portal (2007)
0.01
0.01083742 = product of:
0.02167484 = sum of:
0.02167484 = product of:
0.04334968 = sum of:
0.04334968 = weight(_text_:web in 478) [ClassicSimilarity], result of:
0.04334968 = score(doc=478,freq=4.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.25496176 = fieldWeight in 478, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.0390625 = fieldNorm(doc=478)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- This article discusses the implementation of MPEG-7 within the Moving Image Collections (MIC) portal. MIC is a union catalog of the world's moving images, as well as a portal to information on the care, management, and use of moving images. The MIC Union Catalog utilizes a core registry schema that is designed to map readily to any metadata schema used to describe moving images. The MIC development team was particularly interested in supporting MPEG-7 for future nontextual digital video indexing applications. An MPEG-7 application profile and Microsoft Access cataloging utility were developed in order to test MPEG-7 within the MIC Union Catalog; 400 science digital videos in the ResearchChannel collection were cataloged in MPEG-7. The MPEG-7 records were mapped to MIC and ingested. Draft MPEG-7 to MIC and MIC to MPEG-7 maps were developed and are available at the MIC Web site. MPEG-7 records are available for viewing for any record in the MIC database via a collections explore search within the Archivists' portal. The MPEG-7 cataloging utility may be downloaded from the MIC project Web site (Moving Image Collections. MIC Cataloging Utility. http://gondolin.rutgers.edu/MIC/text/ how/cataloging_utility.htm). This article also discusses issues with MPEG-7 as a descriptive metadata schema, as well as mapping and implementation issues identified in the project.
-
Iyengar, S.S.: Visual based retrieval systems and Web mining (2001)
0.01
0.008669936 = product of:
0.017339872 = sum of:
0.017339872 = product of:
0.034679744 = sum of:
0.034679744 = weight(_text_:web in 6520) [ClassicSimilarity], result of:
0.034679744 = score(doc=6520,freq=4.0), product of:
0.17002425 = queryWeight, product of:
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.052098576 = queryNorm
0.2039694 = fieldWeight in 6520, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.2635105 = idf(docFreq=4597, maxDocs=44218)
0.03125 = fieldNorm(doc=6520)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- Relevance has been a difficult concept to define, let alone measure. In this paper, a simple operational definition of relevance is proposed for a Web-based library catalog: whether or not during a search session the user saves, prints, mails, or downloads a citation. If one of those actions is performed, the session is considered relevant to the user. An analysis is presented illustrating the advantages and disadvantages of this definition. With this definition and good transaction logging, it is possible to ascertain the relevance of a session. This was done for 905,970 sessions conducted with the University of California's Melvyl online catalog. Next, a methodology was developed to try to predict the relevance of a session. A number of variables were defined that characterize a session, none of which used any demographic information about the user. The values of the variables were computed for the sessions. Principal components analysis was used to extract a new set of variables out of the original set. A stratified random sampling technique was used to form ten strata such that each new strata of 90,570 sessions contained the same proportion of relevant to nonrelevant sessions. Logistic regression was used to ascertain the regression coefficients for nine of the ten strata. Then, the coefficients were used to predict the relevance of the sessions in the missing strata. Overall, 17.85% of the sessions were determined to be relevant. The predicted number of relevant sessions for all ten strata was 11 %, a 6.85% difference. The authors believe that the methodology can be further refined and the prediction improved. This methodology could also have significant application in improving user searching and also in predicting electronic commerce buying decisions without the use of personal demographic data
