Normalização automática de descrições de hotéis

As descrições de produtos turísticos na área da hotelaria, aviação, rent-a-car e pacotes de férias baseiam-se sobretudo em descrições textuais em língua natural muito heterogénea com estilos, apresentações e conteúdos muito diferentes entre si. Uma vez que o sector do turismo é bastante dinâmico e que os seus produtos e ofertas estão constantemente em alteração, o tratamento manual de normalização de toda essa informação não é possível. Neste trabalho construiu-se um protótipo que permite a classificação e extracção automática de informação a partir de descrições de produtos de turismo. Inicialmente a informação é classificada quanto ao tipo. Seguidamente são extraídos os elementos relevantes de cada tipo e gerados objectos facilmente computáveis. Sobre os objectos extraídos, o protótipo com recurso a modelos de textos e imagens gera automaticamente descrições normalizadas e orientadas a um determinado mercado. Esta versatilidade permite um novo conjunto de serviços na promoção e venda dos produtos que seria impossível implementar com a informação original. Este protótipo, embora possa ser aplicado a outros domínios, foi avaliado na normalização da descrição de hotéis. As frases descritivas do hotel são classificadas consoante o seu tipo (Local, Serviços e/ou Equipamento) através de um algoritmo de aprendizagem automática que obtém valores médios de cobertura de 96% e precisão de 72%. A cobertura foi considerada a medida mais importante uma vez que a sua maximização permite que não se percam frases para processamentos posteriores. Este trabalho permitiu também a construção e população de uma base de dados de hotéis que possibilita a pesquisa de hotéis pelas suas características. Esta funcionalidade não seria possível utilizando os conteúdos originais. ABSTRACT: The description of tourism products, like hotel, aviation, rent-a-car and holiday packages, is strongly supported on natural language expressions. Due to the extent of tourism offers and considering the high dynamics in the tourism sector, manual data management is not a reliable or scalable solution. Offer descriptions - in the order of thousands - are structured in different ways, possibly comprising different languages, complementing and/or overlap one another. This work aims at creating a prototype for the automatic classification and extraction of relevant knowledge from tourism-related text expressions. Captured knowledge is represented in a normalized/standard format to enable new services based on this information in order to promote and sale tourism products that would be impossible to implement with the raw information. Although it could be applied to other areas, this prototype was evaluated in the normalization of hotel descriptions. Hotels descriptive sentences are classified according their type (Location, Services and/or Equipment) using a machine learning algorithm. The built setting obtained an average recall of 96% and precision of 72%. Recall considered the most important measure of performance since its maximization allows that sentences were not lost in further processes. As a side product a database of hotels was built and populated with search facilities on its characteristics. This ability would not be possible using the original contents.

Consumers sensory evaluation of melon sweetness and quality

CONSUMERS SENSORY EVALUATION OF MELON SWEETNESS AND QUALITY Agulheiro Santos, A.C, Rato, A.E., Laranjo, M. and Gonçalves, C. Departamento de Fitotecnia, Escola de Ciências e Tecnologia, Instituto de Ciências Agrárias e Ambientais Mediterrânicas (ICAAM), Instituto de Investigação e Formação Avançada (IIFA), Universidade de Évora, Polo da Mitra, Ap.94, 7002-554 Évora, Portugal. ABSTRACT The sensory quality of fruits is made of a range of attributes like sweetness, acidity, aroma, firmness, color. Taste perception and perception threshold of these attributes are variable according to the psychological and cultural development of individuals. To better understand the quality evaluation of melon by consumers, consumers were invited to taste melon samples, in supermarkets in Évora (South region), Lisbon (Central region) and Vila Nova de Gaia (North region). The present work explored the importance given by consumers to sweetness in order to classify the overall quality of melon. Furthermore, the relationship of the chemical evaluation of Total Soluble Solids (TSS) with sweetness of melon was studied. Fruits from the variety Melão branco picked randomly from those that were exposed for sale in supermarkets were used for analysis. Fruits were chinned along the equatorial zone and only the central part of the fruit, opposite to the part that leaned on the soil, was used to obtain homogeneous samples. Consumers were invited to taste four small pieces of each fruit, previously referenced with a code number, and answer a questionnaire with two questions related to sweetness and overall quality. Each question had five possible levels, identified from “Nothing sweet”, to “Extremely sweet”, in one case, and from “Poor” to “Excellent” in the other. Simultaneously, the values of TSS (measured in ºBrix) for each melon used in the study were evaluated by refractometry. This sensory analysis allowed us to point out the following findings: first of all, there is good agreement between the results obtained to classify “Sweetness” and “Overall Quality” (Cohen’s Kappa=53.1%, p<0.001), which means, for example, that fruits with excellent quality are in general extremely sweet. Moreover, fruits with less than 9.6 °Brix are considered of poor quality and nothing sweet, whereas fruits with values between 10 °Brix and 12 °Brix are considered good in terms of overall quality. It seems that the thresholds for the stimulus/intensity of sweetness lied between 10 °Brix to 14 °Brix for this melon variety. Acknowledgments This work was support by national funds through Fundação para a Ciência e a Tecnologia (FCT) under the Strategic Project Pest-OE/AGR/UI0115/2014 and co-funded by FEDER funds through the COMPETE Program.