Text mining e twitter : o poder das redes sociais num mercado competitivo

Actualmente, com a massificação da utilização das redes sociais, as empresas passam a sua mensagem nos seus canais de comunicação, mas os consumidores dão a sua opinião sobre ela. Argumentam, opinam, criticam (Nardi, Schiano, Gumbrecht, & Swartz, 2004). Positiva ou negativamente. Neste contexto o Text Mining surge como uma abordagem interessante para a resposta à necessidade de obter conhecimento a partir dos dados existentes. Neste trabalho utilizámos um algoritmo de Clustering hierárquico com o objectivo de descobrir temas distintos num conjunto de tweets obtidos ao longo de um determinado período de tempo para as empresas Burger King e McDonald’s. Com o intuito de compreender o sentimento associado a estes temas foi feita uma análise de sentimentos a cada tema encontrado, utilizando um algoritmo Bag-of-Words. Concluiu-se que o algoritmo de Clustering foi capaz de encontrar temas através do tweets obtidos, essencialmente ligados a produtos e serviços comercializados pelas empresas. O algoritmo de Sentiment Analysis atribuiu um sentimento a esses temas, permitindo compreender de entre os produtos/serviços identificados quais os que obtiveram uma polaridade positiva ou negativa, e deste modo sinalizar potencias situações problemáticas na estratégia das empresas, e situações positivas passíveis de identificação de decisões operacionais bem-sucedidas.

Business intelligence in banking: A literature analysis from 2002 to 2013 using Text Mining and latent Dirichlet allocation

telligence applications for the banking industry. Searches were performed in relevant journals resulting in 219 articles published between 2002 and 2013. To analyze such a large number of manuscripts, text mining techniques were used in pursuit for relevant terms on both business intelligence and banking domains. Moreover, the latent Dirichlet allocation modeling was used in or- der to group articles in several relevant topics. The analysis was conducted using a dictionary of terms belonging to both banking and business intelli- gence domains. Such procedure allowed for the identification of relationships between terms and topics grouping articles, enabling to emerge hypotheses regarding research directions. To confirm such hypotheses, relevant articles were collected and scrutinized, allowing to validate the text mining proce- dure. The results show that credit in banking is clearly the main application trend, particularly predicting risk and thus supporting credit approval or de- nial. There is also a relevant interest in bankruptcy and fraud prediction. Customer retention seems to be associated, although weakly, with targeting, justifying bank offers to reduce churn. In addition, a large number of ar- ticles focused more on business intelligence techniques and its applications, using the banking industry just for evaluation, thus, not clearly acclaiming for benefits in the banking business. By identifying these current research topics, this study also highlights opportunities for future research.

Reconstructing transcriptional regulatory networks using data integration and text mining

Transcriptional Regulatory Networks (TRNs) are powerful tool for representing several interactions that occur within a cell. Recent studies have provided information to help researchers in the tasks of building and understanding these networks. One of the major sources of information to build TRNs is biomedical literature. However, due to the rapidly increasing number of scientific papers, it is quite difficult to analyse the large amount of papers that have been published about this subject. This fact has heightened the importance of Biomedical Text Mining approaches in this task. Also, owing to the lack of adequate standards, as the number of databases increases, several inconsistencies concerning gene and protein names and identifiers are common. In this work, we developed an integrated approach for the reconstruction of TRNs that retrieve the relevant information from important biological databases and insert it into a unique repository, named KREN. Also, we applied text mining techniques over this integrated repository to build TRNs. However, was necessary to create a dictionary of names and synonyms associated with these entities and also develop an approach that retrieves all the abstracts from the related scientific papers stored on PubMed, in order to create a corpora of data about genes. Furthermore, these tasks were integrated into @Note, a software system that allows to use some methods from the Biomedical Text Mining field, including an algorithms for Named Entity Recognition (NER), extraction of all relevant terms from publication abstracts, extraction relationships between biological entities (genes, proteins and transcription factors). And finally, extended this tool to allow the reconstruction Transcriptional Regulatory Networks through using scientific literature.

Problemáticas de la interacción discursiva en la enseñanza y el aprendizaje de las Ciencias Naturales. Aportes didácticos. Interaction discoursive issues in teaching and learning Natural Sciences. Didactic contributions

Las didácticas específicas de las ciencias naturales revelan diferentes problemáticas en su enseñanza y aprendizaje en los diferentes niveles del sistema educativo. En particular, en las clases de ciencias la interacción discursiva docente alumnos adquiere relevancia, ya que el proceso de comunicación del conocimiento es uno de los pilares didácticos, junto a la trasposición del mismo. Especificamente, en este proyecto nos abocamos a aquellas intervenciones de docentes y alumnos que se relacionan con la construcción del conocimiento biológico y químico. El proyecto se enmarca en una actual linea de trabajo que indaga sobre las dificultades en los abordajes del conocimiento científico en las aulas, las características del discurso entre docentes y alumnos, las habilidades y dificultades en la comprensión de los enunciados de problemas y las características de los textos que se utilizan en las clases. Se focaliza este estudio en casos que intentan dar respuesta a tres temáticas, agrupadas en un conjunto de situaciones de investigación relacionadas con la interacción discursiva docente-alumno, retomando el rol del docente al hablar, guiar o diseñar las situaciones de referencia para el aprendizaje de los alumnos. Los casos son: 1- En cuanto a las concepciones sobre diversidad biológica en estudiantes de escuela secundaria y en textos académicos, atendemos a cómo la escuela presenta los contenidos ecológicos como un conjunto de dogmas y conceptos estáticos. Además suelen simplificarse conceptualmente y presentarse poco actualizados. Es por ello que se planea estudiar las concepciones y actitudes de los alumnos de secundaria sobre la biodiversidad, cómo estas dificultan su comprensión y los textos usados en relación a la promoción de la transposición didáctica. 2- En relación a cómo se elabora el patrón temático del tema célula en clases de Biología, se analizarán las diferentes estrategias de significados y de desarrollo temático, que se emplean en la comunicación aulica. Se intentará establecer si hay cambios en el desarrollo temático a medida que se avanza en la escolaridad. Esto es porque se puede apreciar que muchos de los problemas de aprendizaje del alumnado se deben a un desconocimiento tanto del patrón temático como del patrón estructural de la ciencia, siendo preciso evocar los patrones temáticos que se quieren utilizar, para construir un conocimiento compartido. 3-Finalmente, en los enunciados de problemas de Química, se analizarán las dificultades de comprensión lectora de alumnos de Ingeniería. Los docentes frecuentemente atribuyen los problemas a deficiencias en la instrucción recibida, sin considerarse los conocimientos previos del alumno, los obstáculos conceptuales originados en el tema, las deficiencias en la habilidad lectora, el tipo textual predominante en la consigna, el formato en el que se escribió la consigna y los factores personales, etc., siendo que la comprensión del enunciado de una consigna de trabajo condiciona fuertemente la posibilidad de su resolución. Los tres casos utilizarán metodologías cualitaritas que incluyan análisis de contenido en discursos orales y escritos. Los datos se registrarán desde observación no participante, registro etnográfico y con grabaciones de audio. Se espera contribuir al conocimiento, realizando aportes a la formación docente en tanto las estrategias discursivas que se emplean en el aula, en forma oral y en la escrita, conocer concepciones que dificultan o favoren la construcción del conocimiento científico, entre otras. Los productos de estos estudios estarán integrados por nuevos desarrollos para la formación docente, publicaciones científicas de impacto nacional e internacional, presentaciones a congresos, materiales didácticos y divulgativos, dictado de seminarios y/o cursos, redacción de informes a las escuelas intervinientes.. The specific Natural Sciences didactics show different problems in teaching and learning along the school system. In particular, the discourse used to communicate knowledge in Science lessons becomes important. With this project we will focus on the teachers and students actions regarding the construction of biological and chemical knowledge. This project attempts to answer these issues and brings together a range of research situations related to teacher-student interaction, through discourse, taking up the role of the teacher to speak, to plan and to guide student learning. We will study the ideas and attitudes of high school students about biodiversity that make difficult its understanding and the textbooks used in relation to promotion of the didactic transposition. In addition, regarding how the thematic pattern in biology classes is costructed, it will be analyzed the different meaning and thematic development strategies that are used in communication. We will attempt to establish whether there are any changes in the thematic development throughout high school education. Finally, we will analyze the reading comprehension problems in engineering students. Teachers frequently attribute these issues to deficiencies in prior education, without considering the students background, the conceptual obstacles arising in the field, the format in which the prompt is written, personal factors, etc., keeping in mind that the outcome of an activity is strictly dependant con the prompt understanding. We expect to make contributions to the teacher education in both the discourse strategies used in the classroom, orally and in writing, to learn about the conceptions that hinder or favor the knowledge construction, among others. The products of this study will be national and international impact scientific publications, conference presentations, popular science publications, seminars courses and reports to the schools involeved.

In search of a language textile and text in contemporary women's art

This research uses the textile/text axis concept as a conceptual tool to investigate the role of textile and text in contemporary women’s art practice and theorizing, investigating textile as a largely hitherto unacknowledged element in women’s art practice of the late 20th and early 21st centuries. Textile and text share a common etymological root, from the Latin textere to weave, textus a fabric. The thesis illuminates the pathways whereby textile and text played an important role in women reclaiming a speaking voice as creators of culture and signification during a revolutionary period of renewal in women’s cultural contribution and positioning. The methodological approach used in the research consisted of a comprehensive literature review, the compilation of an inventory of relevant women artists, developing a classificatory system differentiating types of approaches, concerns and concepts underpinning women’s art practice vis a vis the textile/text axis and a series of three in-depth case studies of artists Tracey Emin, Louise Bourgeois and Faith Ringgold. The thesis points to the fact that contemporary women artists and theorists have rounded their art practice and aesthetic discourse in textile as prime visual metaphor and signifier, turning towards the ancient language of textile not merely to reclaim a speaking voice but to occupy a ground breaking locus of signification and representation in contemporary culture. The textile/text axis facilitated women artists in powerfully countering a culturally inscribed status of Lacanian ‘no-woman’ (a position of abjection, absence and lack in the phallocentric symbolic). Turning towards a language of aeons, textile as fertile wellspring, the thesis identifies the methodologies and strategies whereby women artists have inserted their webs of subjectivities and deepest concerns into the records and discourses of contemporary culture. Presenting an anatomy of the textile/text axis, the thesis identifies nine component elements manifesting in contemporary women’s aesthetic practice and discourse. In this cultural renaissance, the textile/text axis, the thesis suggests, served as a complex lexicon, a system of labyrinthine references and signification, a site of layered meanings and ambiguities, a body proxy and a corporeal cartography, facilitating a revolution in women’s aesthetic praxis.

Robust learning in safety-related domains : machine learning methods for solving safety-related application problems

Magdeburg, Univ., Fak. für Informatik, Diss., 2009

Machine learning with Lipschitz classifiers

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2010

An illustrated flora of the northern United States, Canada and the British possessions, from Newfoundland to the parallel of the southern boundary of Virginia, and from the Atlantic Ocean westward to the 102d meridian, by Nathaniel Lord Britton and Addison Brown. The descriptive text chiefly prepared by Britton, with the assistance of specialists in several groups; the figures also drawn under his supervision.

2

An illustrated flora of the northern United States, Canada and the British possessions, from Newfoundland to the parallel of the southern boundary of Virginia, and from the Atlantic Ocean westward to the 102d meridian, by Nathaniel Lord Britton and Addison Brown. The descriptive text chiefly prepared by Britton, with the assistance of specialists in several groups; the figures also drawn under his supervision.

3

Advanced mapping of environmental data: Geostatistics, Machine Learning and Bayesian Maximum Entropy

This book combines geostatistics and global mapping systems to present an up-to-the-minute study of environmental data. Featuring numerous case studies, the reference covers model dependent (geostatistics) and data driven (machine learning algorithms) analysis techniques such as risk mapping, conditional stochastic simulations, descriptions of spatial uncertainty and variability, artificial neural networks (ANN) for spatial data, Bayesian maximum entropy (BME), and more.

Extreme Precipitation Modelling Using Geostatistics and Machine Learning Algorithms

The paper presents an approach for mapping of precipitation data. The main goal is to perform spatial predictions and simulations of precipitation fields using geostatistical methods (ordinary kriging, kriging with external drift) as well as machine learning algorithms (neural networks). More practically, the objective is to reproduce simultaneously both the spatial patterns and the extreme values. This objective is best reached by models integrating geostatistics and machine learning algorithms. To demonstrate how such models work, two case studies have been considered: first, a 2-day accumulation of heavy precipitation and second, a 6-day accumulation of extreme orographic precipitation. The first example is used to compare the performance of two optimization algorithms (conjugate gradients and Levenberg-Marquardt) of a neural network for the reproduction of extreme values. Hybrid models, which combine geostatistical and machine learning algorithms, are also treated in this context. The second dataset is used to analyze the contribution of radar Doppler imagery when used as external drift or as input in the models (kriging with external drift and neural networks). Model assessment is carried out by comparing independent validation errors as well as analyzing data patterns.