One of the problems associated with automatic thesaurus construction is with determining the semantic relationship between word pairs. Quasi-synonyms provide a type of equivalence relationship: words are similar only for purposes of information retrieval. Determining such relationships in a thesaurus is hard to achieve automatically. The term vector space model and an inverse term frequency similarity function can provide a way to automatically determine the similarity between words in thesaurus. A thesaurus constructed using this method can also improve precision and recall in information retrieval, when the thesaurus is constructed in conjunction with fuzzy rough set algorithms and used with tight upper approximation query expansion. This dissertation presents a method that combines fuzzy rough sets and a word weighting and inverse term frequency similarity function as a technique for automatic thesaurus construction.

Orientador: Mariângela Spotti Lopes Fujita / Banca: Maria de Fátima Gonçalves Moreira Tálamo / Banca: João Batista Ernesto de Moraes / Banca: Marta Lígia Pomim Valentim / Banca: Vera Regina Casari Boccato / Resumo: Investiga a integração da Terminografia para a construção de tesauros na busca de procedimentos terminográficos que podem ser aplicados em conjunto com procedimentos metodológicos existentes de análise de assunto, para o aprimoramento da representação de conceitos na construção de tesauros. Realiza um estudo teórico-metodológico da construção de tesauro, com enfoque na identificação de conceitos em áreas de especialidade para a organização e recuperação temática da informação. Apresenta como objetivo geral enunciar um modelo metodológico para a construção de tesauro com a integração de procedimentos terminográficos. Como objetivos específicos: analisar e sintetizar referenciais teórico-metodológicos sobre construção de tesauros; identificar os principais aspectos teórico-metodológicos da Terminologia/Terminografia contribuintes para a construção de tesauros; e apresentar proposta de um modelo metodológico terminográfico para a construção de tesauros. A metodologia da pesquisa qualifica-se por sua natureza bibliográfica, descritiva e exploratória, concentrando-se na abordagem temática do vocabulário de áreas de especialidade. Enfatiza como um resultado do trabalho aplicado o "Tesauro Terminográfico Preliminar em Gestão da Informação", disponível na web. Conclui que o aprimoramento de etapas da construção de tesauro, aliado a contribuições de procedimentos terminográficos, produz uma representação de conceitos, por meio de termos, tendo em vista a obtenção de um vocabulário consistente, que compõe a base para a organização e recuperação temática da informação, e compatível com a demanda de áreas de especialidade. / Abstract: It investigates the terminographic integration for the thesauri construction in the search of terminographic procedures that may be used together with existing methodological procedures of subject analysis, for the improvement of the concepts representation in the thesauri construction. It is a theoretical-methodological study of the thesauri construction, focusing in the concepts identification in specialized area for the representation and thematic information retrieval. The general purpose of this research is to conceive a methodological model for the thesauri construction with the terminographic procedures integration. The specific purposes are to analyze and synthesize theoretical-methodological framework on thesauri construction, identify the main theoretical-methodological aspects of Terminology/Terminography which contribute to the thesauri construction, and present a proposal of a terminographic methodological model for the thesaurus construction. The research methodology is bibliographical, descriptive and exploratory, focusing on the thematic approach of vocabulary of speciality areas. It emphasizes as a result of this work, the "Preliminary Terminographic Thesauri in Information Management", available in the web. It concludes that the improvement of thesauri construction stages, with the contributions of terminographic procedures, produce a concepts representation, by means of terms, having in mind the acquisition of a consistent vocabulary, which forms the basis for the organization and thematic information retrieval, and compatible with the demand of specialized areas. / Doutor

Made available in DSpace on 2014-06-11T19:32:42Z (GMT). No. of bitstreams: 0 Previous issue date: 2009-09-25Bitstream added on 2014-06-13T20:43:41Z : No. of bitstreams: 1 cervantes_bmn_dr_mar.pdf: 771731 bytes, checksum: e1199688bf675a26db2c9fbd1fc8ad17 (MD5) / Uel / Investiga a integração da Terminografia para a construção de tesauros na busca de procedimentos terminográficos que podem ser aplicados em conjunto com procedimentos metodológicos existentes de análise de assunto, para o aprimoramento da representação de conceitos na construção de tesauros. Realiza um estudo teórico-metodológico da construção de tesauro, com enfoque na identificação de conceitos em áreas de especialidade para a organização e recuperação temática da informação. Apresenta como objetivo geral enunciar um modelo metodológico para a construção de tesauro com a integração de procedimentos terminográficos. Como objetivos específicos: analisar e sintetizar referenciais teórico-metodológicos sobre construção de tesauros; identificar os principais aspectos teórico-metodológicos da Terminologia/Terminografia contribuintes para a construção de tesauros; e apresentar proposta de um modelo metodológico terminográfico para a construção de tesauros. A metodologia da pesquisa qualifica-se por sua natureza bibliográfica, descritiva e exploratória, concentrando-se na abordagem temática do vocabulário de áreas de especialidade. Enfatiza como um resultado do trabalho aplicado o “Tesauro Terminográfico Preliminar em Gestão da Informação”, disponível na web. Conclui que o aprimoramento de etapas da construção de tesauro, aliado a contribuições de procedimentos terminográficos, produz uma representação de conceitos, por meio de termos, tendo em vista a obtenção de um vocabulário consistente, que compõe a base para a organização e recuperação temática da informação, e compatível com a demanda de áreas de especialidade. / It investigates the terminographic integration for the thesauri construction in the search of terminographic procedures that may be used together with existing methodological procedures of subject analysis, for the improvement of the concepts representation in the thesauri construction. It is a theoretical-methodological study of the thesauri construction, focusing in the concepts identification in specialized area for the representation and thematic information retrieval. The general purpose of this research is to conceive a methodological model for the thesauri construction with the terminographic procedures integration. The specific purposes are to analyze and synthesize theoretical-methodological framework on thesauri construction, identify the main theoretical-methodological aspects of Terminology/Terminography which contribute to the thesauri construction, and present a proposal of a terminographic methodological model for the thesaurus construction. The research methodology is bibliographical, descriptive and exploratory, focusing on the thematic approach of vocabulary of speciality areas. It emphasizes as a result of this work, the “Preliminary Terminographic Thesauri in Information Management”, available in the web. It concludes that the improvement of thesauri construction stages, with the contributions of terminographic procedures, produce a concepts representation, by means of terms, having in mind the acquisition of a consistent vocabulary, which forms the basis for the organization and thematic information retrieval, and compatible with the demand of specialized areas.

This study investigates, within the current health care situation, the interrelationship of the user, resources and tool in the design of a prototype WELLNESS database-driven web site. A shift has taken place in health care, in which the base of conventional medicine has broadened to integrate other systems, practices and worldviews. These include complementary and alternative medicine, health promotion, disease prevention and wellness. Emphasis is placed on the need to take personal responsibility for one's own health and wellness. The global burden of chronic disease, reaching epidemic proportions, is increasingly linked to risk factors resulting from personal lifestyle choices. The growing evidence of the user's need to make personal, informed, lifestyle choices and their reliance on the Web for health information, required investigation. WELLNESS, a specific orientation to health and wellness, formed the framework within which the user and resources were defined and the tool designed. The user was profiled as the WELLNESS health information seeker, hereby contributing significantly to an understanding of the user in this new context. The user profile informed the establishment of resource selection criteria and tool design. The identification of WELLNESS content selection criteria, within a five-dimensional model, was required to ensure quality, relevant and credible resources. The tool is comprised of the WELLNESS thesaurus and WELLNESS database-driven web site. The WELLNESS thesaurus was constructed based on a combination of relevant thesauri. It will be used as an indexing tool. An investigation of existing health information web sites highlighted the importance of designing a specific WELLNESS database-driven web site. A database host was identified against which the original study's conceptual schema was assessed. A low-fidelity prototype web site was designed as the interface between the WELLNESS health information seeker and the database of WELLNESS health information resources. This study has epidemiological, philosophical, epistemological, sociological and psychological relevance. The provision of access to WELLNESS health information resources, made available in the WELLNESS database-driven web site, for personal, informed lifestyle choice by the WELLNESS health information seeker could potentially contribute to the reduction of the global burden of chronic disease. / Information Science / D.Litt. et Phil. (Information Science)

Die Arbeit analysiert die dynamische Entwicklung und den Gebrauch von Thesaurusbegriffen. Zusätzlich konzentriert sie sich auf die Faktoren, die die Zahl von Indexbegriffen pro Dokument oder Zeitschrift beeinflussen. Als Untersuchungsobjekt dienten der MeSH und die entsprechende Datenbank „MEDLINE“. Die wichtigsten Konsequenzen sind: 1. Der MeSH-Thesaurus hat sich durch drei unterschiedliche Phasen jeweils logarithmisch entwickelt. Solch einen Thesaurus sollte folgenden Gleichung folgen: „T = 3.076,6 Ln (d) – 22.695 + 0,0039d“ (T = Begriffe, Ln = natürlicher Logarithmus und d = Dokumente). Um solch einen Thesaurus zu konstruieren, muss man demnach etwa 1.600 Dokumente von unterschiedlichen Themen des Bereiches des Thesaurus haben. Die dynamische Entwicklung von Thesauri wie MeSH erfordert die Einführung eines neuen Begriffs pro Indexierung von 256 neuen Dokumenten. 2. Die Verteilung der Thesaurusbegriffe erbrachte drei Kategorien: starke, normale und selten verwendete Headings. Die letzte Gruppe ist in einer Testphase, während in der ersten und zweiten Kategorie die neu hinzukommenden Deskriptoren zu einem Thesauruswachstum führen. 3. Es gibt ein logarithmisches Verhältnis zwischen der Zahl von Index-Begriffen pro Aufsatz und dessen Seitenzahl für die Artikeln zwischen einer und einundzwanzig Seiten. 4. Zeitschriftenaufsätze, die in MEDLINE mit Abstracts erscheinen erhalten fast zwei Deskriptoren mehr. 5. Die Findablity der nicht-englisch sprachigen Dokumente in MEDLINE ist geringer als die englische Dokumente. 6. Aufsätze der Zeitschriften mit einem Impact Factor 0 bis fünfzehn erhalten nicht mehr Indexbegriffe als die der anderen von MEDINE erfassten Zeitschriften. 7. In einem Indexierungssystem haben unterschiedliche Zeitschriften mehr oder weniger Gewicht in ihrem Findability. Die Verteilung der Indexbegriffe pro Seite hat gezeigt, dass es bei MEDLINE drei Kategorien der Publikationen gibt. Außerdem gibt es wenige stark bevorzugten Zeitschriften. / This dissertation analyzes dynamic developments and use of thesauri. It focuses also on six effecting factors on the number of index terms per document or journal. MeSH and its corresponding well known database “MEDLINE” were established to conduct this research. The main consequences of statistical analyses are: 1. MeSH has developed logarithmically through three different phases. Such a thesaurus should follow the equation “T = 3,076.6 Ln(d) –22,695 + 0.0039d” (T = thesaurus terms, Ln = natural logarithm, and d = documents). To construct such a thesaurus, one needs to have at least 1,600 documents covering different topics of the thesaurus. The dynamic of thesauri such as MeSH is due to the persistent inclusion of one new term per indexing of 256 new documents. 2. The distribution of thesaurus terms yielded three classes: highly, normally, and rarely used terms. The last group is in a test phase, and only growth rates of most frequented terms in the first class and newer terms in the second class were becoming persistent over time. 3. There is a logarithmic relationship between the number of index terms per article and its pages, if the articles are between one and twenty-one pages. 4. Journal articles with abstracts received almost two more terms than those included into MEDLINE without abstracts. 5. The findability of non-English documents, such as articles written in German and indexed in an US-based database like MEDLINE, is less than that of English documents. The greatest difference is for articles with ten pages and the least is for those with twenty and more pages. 6. Journals with Impact Factors in the range from 0 to fifteen receive roughly the same number of index terms per page. 7. In an indexing system, different journals have more or less weight in their findability. Distribution of index terms per page has shown that there are three regions of journals in MEDLINE. In addition, few journals are the most favored ones and get more index term per page.

This study investigates, within the current health care situation, the interrelationship of the user, resources and tool in the design of a prototype WELLNESS database-driven web site. A shift has taken place in health care, in which the base of conventional medicine has broadened to integrate other systems, practices and worldviews. These include complementary and alternative medicine, health promotion, disease prevention and wellness. Emphasis is placed on the need to take personal responsibility for one's own health and wellness. The global burden of chronic disease, reaching epidemic proportions, is increasingly linked to risk factors resulting from personal lifestyle choices. The growing evidence of the user's need to make personal, informed, lifestyle choices and their reliance on the Web for health information, required investigation. WELLNESS, a specific orientation to health and wellness, formed the framework within which the user and resources were defined and the tool designed. The user was profiled as the WELLNESS health information seeker, hereby contributing significantly to an understanding of the user in this new context. The user profile informed the establishment of resource selection criteria and tool design. The identification of WELLNESS content selection criteria, within a five-dimensional model, was required to ensure quality, relevant and credible resources. The tool is comprised of the WELLNESS thesaurus and WELLNESS database-driven web site. The WELLNESS thesaurus was constructed based on a combination of relevant thesauri. It will be used as an indexing tool. An investigation of existing health information web sites highlighted the importance of designing a specific WELLNESS database-driven web site. A database host was identified against which the original study's conceptual schema was assessed. A low-fidelity prototype web site was designed as the interface between the WELLNESS health information seeker and the database of WELLNESS health information resources. This study has epidemiological, philosophical, epistemological, sociological and psychological relevance. The provision of access to WELLNESS health information resources, made available in the WELLNESS database-driven web site, for personal, informed lifestyle choice by the WELLNESS health information seeker could potentially contribute to the reduction of the global burden of chronic disease. / Information Science / D.Litt. et Phil. (Information Science)