120 research outputs found
Using Web Search Logs to Identify Query Classification Terms
No full textPurpose – The work presented in this paper aims to provide an approach to classifying web logs by personal properties of users.\ud
\ud
Design/methodology/approach – The authors describe an iterative system that begins with a small set of manually labeled terms, which are used to label queries from the log. A set of background knowledge related to these labeled queries is acquired by combining web search results on these queries. This background set is used to obtain many terms that are related to the classification task. The system then ranks each of the related terms, choosing those that most fit the personal properties of the users. These terms are then used to begin the next iteration.\ud
\ud
Findings – The authors identify the difficulties of classifying web logs, by approaching this problem from a machine learning perspective. By applying the approach developed, the authors are able to show that many queries in a large query log can be classified.\ud
\ud
Research limitations/implications – Testing results in this type of classification work is difficult, as the true personal properties of web users are unknown. Evaluation of the classification results in terms of the comparison of classified queries to well known age-related sites is a direction that is currently being exploring.\ud
\ud
Practical implications – This research is background work that can be incorporated in search engines or other web-based applications, to help marketing companies and advertisers.\ud
\ud
Originality/value – This research enhances the current state of knowledge in short-text classification and query log learning.\ud
Classification schemes, Computer networks, Information retrieval, Man-machine systems, User interface
Using the Web to Construct Taxonomy for a Heterogeneous Community of Practice
No full textA heterogeneous community of practice spans many disciplines, industries and professions. Members of these communities are united by common research, products and experiences but are frequently separated by specialized vocabulary and industry terms. This lack of language commonality presents a challenge to efficiently locating relevant Web based information which usually depends on the user’s knowledge of the field and ability to select suitable terms to formulate a search query. Research and practice have shown that the quality of information retrieval is significantly improved when taxonomy is employed to organize terms that describe the search domain. This paper presents an innovative, collaborative approach to building taxonomy for a particular domain, populating it with Web content and sharing it among members of the community of practice. A model is built and results and implications are discussed
Evaluating Usability of a Long Query Meta Search Engine
No full textUsability is an important factor for search engine acceptance. This paper examines usability of a long query meta search engine. The engine was designed to accept and process an unlimited size query expressed in natural language. We briefly review current search engine usability research and then apply some of the common metrics to various tasks of the search and retrieval process beginning with query formulation and concluding with knowledge discovery in relevant search results. We report on users' utilization of many features offered by the engine which enhance the search experience, increase the quality of the search results and improve the usability measurements. Additionally, the implications of this study on the advancement of search engine development are discusse
Metasearch Engines and Information Retrieval: Computational complexity of ranking multiple search results
No full textWho Brings Which Peace?
No full textThis study examines the effect of biased versus neutral mediation on the content of peace agreements. The author argues that neutral mediators, who are engaged primarily because of their interest to end the war, will have incentives to hasten the reaching of an agreement to the expense of its quality. By contrast, biased mediators, seeking to protect their protégés, will take care to ensure that there are stipulations in an agreement guaranteeing the interest of their side or use their particular access and leverage to make their side agree to costly concessions. Biased mediation processes are therefore more likely than neutral mediation processes to lead to elaborated institutional arrangements that are generally considered conducive to democracy and durable peace, such as power sharing, third-party security guarantees, and justice provisions. Empirical analysis, covering the 1989-2004 period and building on data from 124 peace agreements, supports these claims.</p
Information extraction from blogs
No full textThis chapter introduces information extraction from blog texts. It argues that the classical techniques for information extraction that are commonly used for mining well-formed texts lose some of their validity in the context of blogs. This finding is demonstrated by considering each step in the information extraction process and by illustrating this problem in different applications. In order to tackle the problem of mining content from blogs, algorithms are developed that combine different sources of evidence in the most flexible way. The chapter concludes with ideas for future research.status: Publishe
Messages of the prophets
No full text"Jedan čovek iz naroda napisao je brošuru u stihovima, u kojoj je izneo svoju ljubav prema Svetom Pismu i prorocima, kao i svoje veliko oduševljenje za cionizam i budućnost jevrejskog naroda u Palestini. Kako ova brošura može da doprinese jačanju svesti za verske i nacionalne ideale našeg življa, to se njena lektira najlepše preporučuje našim građanima". Ovo su reči o knjizi i njenom autoru, izrečene od strane Vrhovnog rabina Kraljevine Jugoslavije dr Isaka Alkalaja."A man from the people wrote a brochure in verse, in which he expressed his love for the Holy Scripture and the prophets, as well as his great enthusiasm for Zionism and the future of the Jewish people in Palestine. Considering how this brochure can contribute to strengthening awareness of the religious and national ideals of our community, its reading is most warmly recommended to our citizens." These are words about the book and its author, spoken by the Chief Rabbi of the Kingdom of Yugoslavia, Dr Isak Alkalaj
Portraits, sketches, and the décor: poems
No full textZbirka pesama "Portreti, skice i dekori" predstavlja kolaž od jedanaest pesama. Isak Nahmijas kroz ove pesme spaja lirski izraz i vizuelnu imaginaciju u intiman, meditativan prostor. Kroz kratke zapise i skice karaktera autor u malim trenucima pronalazi duboka značenja, otkrivajući slojeve identiteta i sećanja. Knjižica je sažet, ali sugestivan doprinos savremenoj jevrejskoj i regionalnoj književnoj tradiciji.The poetry collection "Portraits, Sketches, and the Décor: poems" consists of eleven poems. Isak Nahmijas' works combine lyrical expression and visual imagination, creating an intimate, reflective space. In brief notes and character sketches, the author reveals deep meanings within small moments, revealing layers of identity and memory. The booklet makes a brief but evocative contribution to the contemporary Jewish and regional literature traditions.Na poleđini naslovne strane. "Ova je knjiga štampana u 540 primeraka od kojih 500 na običnoj hartiji a 40 numerisanih i od autora potpisanih na „Federleicht" hartiji, i to od 1 do 25 u prodaji a od 25 do 40 izvan prodaje"
- …
