Sentiment-Topic Modelling in Text Mining

Peer reviewed

Sentiment-Topic Modelling in Text Mining

Peer reviewed

A Curated Corpus for Sentiment-Topic Analysis

Postprint

Sentiment-Topic Modelling in Text Mining

Peer reviewed

Segmentation hiérarchique du domaine sémantique pour l'accélération d'un modèle de langage

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Segmentation hiérarchique du domaine sémantique pour l'accélération d'un modèle de langage

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Estructura formal, textual y oral del discurso público

Estructura formal, textual y oral del discurso públicoExisten tres competencias comunicativas muy valoradas en la sociedad de la información. Primero, la búsqueda, selección y gestión de grandes cantidades de información. Segundo, la redacción de textos claros, concisos y rigurosos. Y en tercer lugar, la exposición y defensa oral de esta información en un discurso público. Tradicionalmente, los estudios de periodismo han abordado estas competencias de forma independiente. Pero actualmente, instituciones y empresas de ámbitos diferentes demandan un perfil profesional capaz de aplicarlas ante cualquier tipo de información y con objetivos diversos. Se propone un modelo integral en tres niveles estructurales basado en teorías, conceptos y estudios específicos de periodismo, oratoria, retórica… o comunicación, en los últimos años. Este modelo puede contribuir a encauzar las investigaciones de académicos y representa una herramienta de entrenamiento para profesionales.

Multi-scale colorectal tumour segmentation using a novel coarse to fine strategy

This paper addresses the problem of colorectal tumour segmentation in complex real world imagery. For efficient segmentation, a multi-scale strategy is developed for extracting the potentially cancerous region of interest (ROI) based on colour histograms while searching for the best texture resolution. To achieve better segmentation accuracy, we apply a novel bag-of-visual-words method based on rotation invariant raw statistical features and random projection based l2-norm sparse representation to classify tumour areas in histopathology images. Experimental results on 20 real world digital slides demonstrate that the proposed algorithm results in better recognition accuracy than several state of the art segmentation techniques.

The economic impact of sports mega-events : The case study of the FIS Nordic World Ski Championship Falun 2015

Since the second half of 1990s, the economic impact of sports mega-events concerned the researchers, the public and the professionals. The investment of public funds and the effects on several sectors of the economy motivate the economic impact studies. The economic impact of the FIS Nordic World Ski Championship Falun 2015 to the region of Dalarna is the topic of this thesis. This requires the calculation of direct, indirect and induced economic impact. Within the analysis, data from a questionnaire survey conducted on seven different days during the event are used. The final sample of the analysis contains 893 observations. The segmentation approach was applied for the calculations and the visitors were classified regarding their choice of accommodation. The regional economic impact is calculated at 321 M SEK and the employment effect on the tourism sector is estimated. However, the lack of information limits the study. The analysis could be extended with an accurate investigation of certain issues. Further, the impact of the event should be estimated from all the perspectives. The organization of sports mega-events creates tangible and intangible effects to the host-city. The thesis reviews literature on the economic impact studies of sports mega-events. The results of the study can be used for a comprehensive analysis of the case study. Further, the professionals of the tourism and the event could be benefited.

LDA-TM : A two-step approach to twitter topic data clustering

The Twitter System is the biggest social network in the world, and everyday millions of tweets are posted and talked about, expressing various views and opinions. A large variety of research activities have been conducted to study how the opinions can be clustered and analyzed, so that some tendencies can be uncovered. Due to the inherent weaknesses of the tweets - very short texts and very informal styles of writing - it is rather hard to make an investigation of tweet data analysis giving results with good performance and accuracy. In this paper, we intend to attack the problem from another aspect - using a two-layer structure to analyze the twitter data: LDA with topic map modelling. The experimental results demonstrate that this approach shows a progress in twitter data analysis. However, more experiments with this method are expected in order to ensure that the accurate analytic results can be maintained.

Exploring social representations of adapting to climate change using topic modeling and Bayesian networks

When something unfamiliar emerges or when something familiar does something unexpected people need to make sense of what is emerging or going on in order to act. Social representations theory suggests how individuals and society make sense of the unfamiliar and hence how the resultant social representations (SRs) cognitively, emotionally, and actively orient people and enable communication. SRs are social constructions that emerge through individual and collective engagement with media and with everyday conversations among people. Recent developments in text analysis techniques, and in particular topic modeling, provide a potentially powerful analytical method to examine the structure and content of SRs using large samples of narrative or text. In this paper I describe the methods and results of applying topic modeling to 660 micronarratives collected from Australian academics / researchers, government employees, and members of the public in 2010-2011. The narrative fragments focused on adaptation to climate change (CC) and hence provide an example of Australian society making sense of an emerging and conflict ridden phenomena. The results of the topic modeling reflect elements of SRs of adaptation to CC that are consistent with findings in the literature as well as being reasonably robust predictors of classes of action in response to CC. Bayesian Network (BN) modeling was used to identify relationships among the topics (SR elements) and in particular to identify relationships among topics, sentiment, and action. Finally the resulting model and topic modeling results are used to highlight differences in the salience of SR elements among social groups. The approach of linking topic modeling and BN modeling offers a new and encouraging approach to analysis for ongoing research on SRs.

ICTM: an interval tessellation-based model for reliable topographic segmentation

This work introduces a tessellation-based model for the declivity analysis of geographic regions. The analysis of the relief declivity, which is embedded in the rules of the model, categorizes each tessellation cell, with respect to the whole considered region, according to the (positive, negative, null) sign of the declivity of the cell. Such information is represented in the states assumed by the cells of the model. The overall configuration of such cells allows the division of the region into subregions of cells belonging to a same category, that is, presenting the same declivity sign. In order to control the errors coming from the discretization of the region into tessellation cells, or resulting from numerical computations, interval techniques are used. The implementation of the model is naturally parallel since the analysis is performed on the basis of local rules. An immediate application is in geophysics, where an adequate subdivision of geographic areas into segments presenting similar topographic characteristics is often convenient.

Typologie de la flottille chalutière du port de Sète par une méthode de segmentation

This work aims to define a typology of trawler f1eet in Sète, the main fishing harbour along the French Mediterranean coast, using several multivariate analysis methods. The fishing ships taken to account are represented by annual profiles of landing specific compositions. Five fishing strategies have been identified. A segmentation method using symbolic objects allows a formaI characterisation of the different strategies. These strategies are studied according to several general characteristics usually used for management rules elaboration (power, length, ship age). The typological analysis allows to characterise two main exploitation ways, one directed to the catch of a few species (Engraulis encrasicolus, Sardina pilchardus), the other characterised by the exploitation of a great diversity of species. By this way, it is possible to estimate how the catch of low represented species can significantly contribute to the exploitation of a resource.