O modelo de recuperação de informação mais amplamente utilizado no contexto de acervos digitais é o Vector Space Model. Algoritmos implementados para este modelo que aproveitam informações sobre relevância obtidas dos usuários (chamados feedbacks) na tentativa de melhorar os resultados da busca. Porém, estes algoritmos de feedback de relevância não possuem uma estratégia global e permanente, as informações obtidas desses feedbacks são descartadas para cada nova sessão de usuário (são perenes) ou não modificam os documentos como um todo (são alterações locais). Este trabalho apresenta um método de feedbacks de relevância denominado orientado a termos, permitindo que as modificações realizadas por influência dos feedbacks dos usuários sejam globais e permanentes. Foram realizados experimentos utilizando o dataset ClueWeb09 que dão evidências de que este método melhora a qualidade dos resultados da busca em relação ao modelo tradicional Vector Space Model. / The Vector Space Model is the most widely used information retrieval model within digital libraries\' systems. Algorithms developed to be used with this model use relevance information obtained from users (called feedbacks) to improve the search results. However, the relevance feedback algorithms developed are not global nor permanent, the feedbacks are discarded in users new sessions and do not affect every document. This paper presents a method that uses of relevance feedback named terms oriented. In this method, users\' feedbacks lead to modifications in the terms\' vectors representations. These modifications are global and permanent, influencing further searches. An experiment was conducted using the ClueWeb09 dataset, giving evidence that this method improves the quality of search results when compared with Vector Space Model.

A localização de páginas relevantes na Internet em atividades como clipping de notícias, detecção de uso indevido de marcas ou em serviços anti-phishing torna-se cada vez mais complexa devido a vários fatores como a quantidade cada vez maior de páginas na Web e a grande quantidade de páginas irrelevantes retornadas por mecanismos de busca. Em muitos casos as técnicas tradicionais utilizadas em mecanismos de busca na Internet, isto é, localização de termos em páginas e ordenação por relevância, não são suficientes para resolver o problema de localização de páginas específicas em atividades como as citadas anteriormente. A contextualização das páginas, ou seja, a classificação de páginas segundo um contexto definido pelo usuário baseando-se nas necessidades de uma atividade específica deve permitir uma busca mais eficiente por páginas na Internet. Neste trabalho é estudada a utilização de métodos de mineração na Web para a composição de métodos de contextualização de páginas, que permitam definir contextos mais sofisticados como seu assunto ou alguma forma de relacionamento. A contextualização de páginas deve permitir a solução de vários problemas na busca de páginas na Internet pela composição de métodos, que permitam a localização de páginas através de um conjunto de suas características, diferentemente de mecanismos de busca tradicionais que apenas localizam páginas que possuam um ou mais termos especificados. / Internet services as news clipping service, anti-phising, anti-plagiarism service and other that require intensive searching in Internet have a difficult work, because of huge number of existing pages. Search Engines try driver this problem, but search engines methods retrieve a lot of irrelevant pages, some times thousands of pages and more powerful methods are necessary to drive this problem. Page content, subject, hyperlinks or location can be used to define page context and create a more powerful method that can retrieve more relevant pages, improving precision. Classification of page context is defined as classification of a page by a set of its feature. This report presents a study about Web Mining, Search Engines and application of web mining technologies to classify page context. Page context classification applied to search engines must solve the problem of irrelevant pages flood by allowing search engines retrieve pages of a context.

Cognitive limitations such as those described in Miller's (1956) work on channel capacity and Cowen's (2001) on short-term memory are factors in determining user cognitive load and in turn task performance. Inappropriate user cognitive load can reduce user efficiency in goal realization. For instance, if the user's attentional capacity is not appropriately applied to the task, distractor processing can tend to appropriate capacity from it. Conversely, if a task drives users beyond their short-term memory envelope, information loss may be realized in its translation to long-term memory and subsequent retrieval for task base processing. To manage user cognitive capacity in the task of text search the interface should allow users to draw on their powerful and innate pattern recognition abilities. This harmonizes with Johnson-Laird's (1983) proposal that propositional representation is tied to mental models. Combined with the theory that knowledge is highly organized when stored in memory an appropriate approach for cognitive load optimization would be to graphically present single documents, or clusters thereof, with an appropriate number and type of descriptors. These descriptors are commonly words and/or phrases. Information theory research suggests that words have different levels of importance in document topic differentiation. Although key word identification is well researched, there is a lack of basic research into human preference regarding query formation and the heuristics users employ in search. This lack extends to features as elementary as the number of words preferred to describe and/or search for a document. Contrastive understanding these preferences will help balance processing overheads of tasks like clustering against user cognitive load to realize a more efficient document retrieval process. Common approaches such as search engine log analysis cannot provide this degree of understanding and do not allow clear identification of the intended set of target documents. This research endeavours to improve the manner in which text search returns are presented so that user performance under real world situations is enhanced. To this end we explore both how to appropriately present search information and results graphically to facilitate optimal cognitive and perceptual load/utilization, as well as how people use textual information in describing documents or constructing queries.

The main purpose of this research is to find an effective way to personalise information searching on the Internet using middleware search agents, namely, Personalised Search Agents (PSA). The PSA acts between users and search engines, and applies new and existing techniques to mine and exploit relevant and personalised information for users. Much research has already been done in developing personalising filters, as a middleware technique which can act between user and search engines to deliver more personalised results. These personalising filters, apply one or more of the popular techniques for search result personalisation, such as the category concept, learning from user actions and using metasearch engines. By developing the PSA, these techniques have been investigated and incorporated to create an effective middleware agent for web search personalisation. In this thesis, a conceptual model for the Personalised Search Agent is developed, implemented by developing a prototype and benchmarked the prototype against existing web search practices. System development methodology which has flexible and iterative procedures that switch between conceptual design and prototype development was adopted as the research methodology. In the conceptual model of the PSA, a multi-layer client server architecture is used by applying generalisation-specialisation features. The client and the server are structurally the same, but differ in the level of generalisation and interface. The client handles personalising information regarding one user whereas the server effectively combines the personalising information of all the clients (i.e. its users) to generate a global profile. Both client and server apply the category concept where user selected URLs are mapped against categories. The PSA learns the user relevant URLs both by requesting explicit feedback and by implicitly capturing user actions (for instance the active time spent by the user on a URL). The PSA also employs a keyword-generating algorithm, and tries different combinations of words in a user search string by effectively combining them with the relevant category values. The core functionalities of the conceptual model for the PSA, were implemented in a prototype, used to test the ideas in the real word. The result was benchmarked with the results from existing search engines to determine the efficiency of the PSA over conventional searching. A comparison of the test results revealed that the PSA is more effective and efficient in finding relevant and personalised results for individual users and possesses a unique user sense rather than the general user sense of traditional search engines. The PSA, is a novel architecture and contributes to the domain of knowledge web information searching, by delivering new ideas such as active time based user relevancy calculations, automatic generation of sensible search keyword combinations and the implementation of a multi-layer agent architecture. Moreover, the PSA has high potential for future extensions as well. Because it captures highly personalised data, data mining techniques which employ case-based reasoning make the PSA a more responsive, more accurate and more effective tool for personalised information searching.

Thesis (MTech (Information Technology))--Cape Peninsula University of Technology, 2006. / Includes bibliographical references (leaves: 77-86). Also available online.

Thesis (MTech (Information Technology))--Cape Peninsula University of Technology, Cape Town, 2005. / Includes bibliographical references (p. 132-142). Also available online.

<p>The use for a readability classification model is mainly as an integrated part of an information retrieval system. By matching the user's demands of readability to the documents with the corresponding readability, the classification model can further improve the results of, for example, a search engine. This thesis presents a new solution for classification into readability levels for Swedish. The results from the thesis are a number of classification models. The models were induced by training a Support Vector Machines classifier on features that are established by previous research as good measurements of readability. The features were extracted from a corpus annotated with three readability levels. Natural Language Processing tools for tagging and parsing were used to analyze the corpus and enable the extraction of the features from the corpus. Empirical testings of different feature combinations were performed to optimize the classification model. The classification models render a good and stable classification. The best model obtained a precision score of 90.21\% and a recall score of 89.56\% on the test-set, which is equal to a F-score of 89.88.</p> / <p>Uppsatsen beskriver utvecklandet av en klassificeringsmodell för Svenska texter beroende på dess läsbarhet. Användningsområdet för en läsbaretsklassificeringsmodell är främst inom informationssökningssystem. Modellen kan öka träffsäkerheten på de dokument som anses relevanta av en sökmotor genom att matcha användarens krav på läsbarhet med de indexerade dokumentens läsbarhet. Resultatet av uppsatsen är ett antal modeller för klassificering av text beroende på läsbarhet. Modellerna har tagits fram genom att träna upp en Support Vector Machines klassificerare, på ett antal särdrag som av tidigare forskning har fastslagits vara goda mått på läsbarhet. Särdragen extraherades från en korpus som är annoterad med tre läsbarhetsnivåer. Språkteknologiska verktyg för taggning och parsning användes för att möjliggöra extraktionen av särdragen. Särdragen utvärderades empiriskt i olika särdragskombinationer för att optimera modellerna. Modellerna testades och utvärderades med goda resultat. Den bästa modellen hade en precision på 90,21 och en recall på 89,56, detta ger en F-score som är 89,88. Uppsatsen presenterar förslag på vidareutveckling samt potentiella användningsområden.</p>

This thesis discusses the possibilities to visualise the presentation layer of a search engine on a mobile device in an alternative way. Previous work in the area has shown that the use of text-based-lists can be problematic when accessed on a device with a limited display. In the scope of the thesis and in order to tackle the current problems when displaying the results a literature review was carried out. The findings of the review formed the basis for a requirement definition on which a mock-up was developed. The mock-up was then evaluated and tested during a usability test where a number of users got to experience the alternative presentation layer that uses a visualisation technique called tree- map. The results from the test show that the mock-up could be seen as a alternative to the current presentation of results. The mock-up also shows that a future implementation could also include the use of categories and sorting of information in order to provide content with a meaning.

This paper examines the effects of serial position, price promotion, user experience and brand familiarity on search advertising in China. Past research on traditional media has hypothesized that TV ads in prime time and print ads in cover pages received more audience's attention than other ads placed in nonprime time spots on TV or other ads placed in inside pages in print media. Recent study finds the "banner blindness" phenomenon in interactive advertising due to user expertness. Past research also indicates that price promotion and brand familiarity have positive effects on consumer behavior. Will these theories also apply to the new media search engine? This study investigates whether higher ranked ads will result in higher click-through rates, whether "banner blindness" phenomenon also exists in search advertising and whether price promotion and brand familiarity lead to higher level of user attention and thus higher click-through rate. First, this paper analyzes advertisements in varied positions within the same context to better understand the effect of advertisement position ranking on consumer behavior, its role in advertising effectiveness, and the implications for interactive advertising and marketing communication. Second, it compares advertisement with price promotion message in ad copy with advertisement without price promotion message at the same ranking position within the same context. Finally, this study explores the relationship between user experience, brand familiarity and click-through rate. Major findings of this study include the following: first, primacy effect, price promotion and brand familiarity can lead to higher level of user attention to search advertisements and thus result in higher click-through rates. Second, user experience has a negative effect on search advertising effectiveness. The more experienced the users are, the less likely they click on search advertisements. Lastly, recency effect is not obtained in search advertising in this study. This study helps us better understand the effects of ad serial position, price promotion, user experience & brand familiarity on search advertising. It adds to our knowledge in search advertising and provides theoretical & practical implications for future research. / text

Šiame darbe buvo išanalizuota keletas paieškos sistemų, bei įvardinti jų privalumai bei trūkumai. Palygintos sistemos kūrimo technologijos. Tai įvertinus buvo sukurta informacijos paieškos sistema elektroninėje bibliotekoje (eLABa). Jos pagrindinis privalumas yra tai, kad paieška vykdoma ne tik tarp dokumento metaduomenų (aprašo), bet ir dokumento tekste. Eksperimentiškai buvo nustatytas galimas paieškos vykdymo optimizavimas. / This system is invented to help people search for the e. documents in FEDORA repository. The system has following features: indexing of Fedora FOXML records, including the text contents of data streams and search in the index. There is possibility to registered users to save results in the history page, and to do repeated search if you want. Also you can go directly to e. document after you have made search.