Notre recherche s’insère dans la mouvance des humanités numériques; nous y faisons dialoguer les arts et les sciences de l’information. Depuis quelques décennies, la danse est un sujet d’études et de recherche à part entière. Il devient donc nécessaire de mieux décrire la danse dans les archives, sachant que la description en amont influe grandement sur l’accès en aval. Les méthodes d’extraction automatique de connaissances nous semblent offrir de nouvelles possibilités. L’objectif de notre recherche est de contribuer au développement d’outils de gestion de l’information dans les archives de la danse en comparant un vocabulaire de description de la danse dans les archives et un vocabulaire de représentation de la danse dans la littérature, recueilli grâce à des méthodes d’extraction automatique de connaissances, pour en distinguer une possible complémentarité, particulièrement en ce qui a trait au vocabulaire de l’expérience esthétique. D’abord, nous analysons un vocabulaire de description de la danse dans les archives. Nous décrivons certains outils de description des archives de la danse et nous analysons le thésaurus de descripteurs Collier. Nous constatons que le vocabulaire de description de la danse dans les archives ne semble pas prendre en compte l’expérience esthétique. Ensuite, nous analysons un vocabulaire de représentation de la danse dans la littérature. Un vocabulaire structuré de l’expérience esthétique de la danse moderne est ainsi extrait d’un corpus de textes de l’écrivain français Stéphane Mallarmé et analysé. Puis nous comparons les deux vocabulaires afin d'en distinguer la complémentarité quant à la description de l’expérience esthétique. Nous formulons une première suggestion d’amélioration de certains thésaurus employés dans les archives de la danse : un thésaurus au vocabulaire essentiellement factuel, comme le thésaurus de descripteurs Collier, peut être enrichi de termes à propos de l’expérience esthétique. Le vocabulaire de représentation de la danse dans la littérature est jusqu’à un certain point complémentaire au vocabulaire de description de l’expérience esthétique de la danse dans les archives. Nous menons ainsi une première expérimentation qui justifie en partie la pertinence de certaines méthodes d’extraction de connaissances dans le développement et la maintenance de ressources documentaires pour le domaine des arts d’interprétation tels que la danse. / This research falls within the field of digital humanities; arts and information science engage in dialogue. In the last few decades, dance has become a distinct research subject. Dance description in archives needs to be improved, because the quality of the description impacts access to the documentation. Knowledge extraction seems to offer new opportunities in this regard. The goal of this research is to contribute to the development of information management tools by comparing a vocabulary for describing dance in archives with a vocabulary for representing dance in literature obtained through knowledge extraction. We look for possible complementarity, particularly in regard to the aesthetic experience. First, some tools for describing dance in archives are described, and the Collier Descriptor Thesaurus is analyzed. We observe that this vocabulary for describing dance in archives does not take into account aesthetic experience. Second, a vocabulary for representing dance in literature is analyzed. More specifically, a structured vocabulary of aesthetic experience of modern dance is drawn from a corpus of texts from the French writer Stéphane Mallarmé, and the vocabulary obtained is analyzed. Finally, the two vocabularies are compared to consider their complementarity. We conclude that some vocabularies for describing dance in archives, consisting mainly of factual terms, such as the Collier Descriptor Thesaurus, can be enriched with terms related to aesthetic experience. The vocabulary for representing dance in literature complements to a certain extent the vocabulary for describing dance in archives. Thus this initial experiment supports the relevance of knowledge extraction in information resources maintenance and development for performing arts such as dance. / Diese Arbeit beschäftigt sich mit dem Fachgebiet der Digital Humanities und verbindet dabei Kunst mit informationswissenschaftlichen Methoden. In den letzten Jahrzehnten ist Tanz ein eigenständiges Forschungsgebiet geworden. Da sich die Qualität der Beschreibung direkt auf den Zugang zu Dokumenten im Archiv auswirkt, bedarf die Beschreibung von Tanz in Archiven Verbesserung. Ziel der Forschung ist es zur Entwicklung von Informationsverwaltungs-Tools beizutragen, indem das Vokabular der Beschreibung von Tanz im Archiv mit Vokabular aus der Literatur, extrahiert aus textuellen Datenbanken, verglichen wird. Dabei liegt der Fokus auf der Komplementarität beider Quellen, besonders in Bezug auf die Beschreibung von ästhetischen Erfahrungen. Zunächst werden Tools für die Beschreibung von Tanz in Archiven beschrieben und der Collier Descriptor Thesaurus analysiert. Dabei zeigt sich, dass das Vokabular der Tanz-Beschreibung im Archiv ästhetische Erfahrung generell nicht berücksichtigt. Daraufhin wird das Vokabular der Tanz-Darstellung in der Literatur am Beispiel der Text-Sammlung des franzözischen Dichters Stéphane Mallarmé analysiert. Im Anschluss werden die zwei Wortschätze verglichen, um die Komplementarität beider Quellen zu beschreiben. Die Arbeit kommt zu dem Schluss, dass das Vokabular der Tanz-Beschreibung im Archiv hauptsächlich aus sachbezogenen Begriffen besteht (z.B. der Collier Descriptor Thesaurus), welche um Begriffe zur ästhetischen Erfahrung ergänzt werden können. Die Begriffe für die Tanz-Beschreibung in der Literatur komplementieren bis zu einem gewissen Grad das Vokabular der Tanz-Beschreibung im Archiv. Demzufolge bildet diese Arbeit eine Grundlage für weitere Forschung im Bereich der Wissensextraktion in textuellen Datenbanken im Fachgebiet darstellender Künste wie Tanz.

Undoubtedly, the rapid development of information systems and the widespread use of electronic means and social networks have played a significant role in accelerating the pace of events worldwide, such as, in the 2012 Gaza conflict (the 8-day war), in the pro-secessionist rebellion in the 2013-2014 conflict in Eastern Ukraine, in the 2016 US Presidential elections, and in conjunction with the COVID-19 outbreak pandemic since the beginning of 2020. As the number of daily shared data grows quickly on various social networking platforms in different languages, techniques to carry out automatic classification of this huge amount of data timely and correctly are needed. Of the many social networking platforms, Twitter is of the most used ones by netizens. It allows its users to communicate, share their opinions, and express their emotions (sentiments) in the form of short blogs easily at no cost. Moreover, unlike other social networking platforms, Twitter allows research institutions to access its public and historical data, upon request and under control. Therefore, many organizations, at different levels (e.g., governmental, commercial), are seeking to benefit from the analysis and classification of the shared tweets to serve in many application domains, for examples, sentiment analysis to evaluate and determine user’s polarity from the content of their shared text, and misleading information detection to ensure the legitimacy and the credibility of the shared information. To attain this objective, one can apply numerous data representation, preprocessing, natural language processing techniques, and machine/deep learning algorithms. There are several challenges and limitations with existing approaches, including issues with the management of tweets in multiple languages, the determination of what features the feature vector should include, and the assignment of representative and descriptive weights to these features for different mining tasks. Besides, there are limitations in existing performance evaluation metrics to fully assess the developed classification systems. In this dissertation, two novel frameworks are introduced; the first is to efficiently analyze and classify bilingual (Arabic and English) textual content of social networks, while the second is for evaluating the performance of binary classification algorithms. The first framework is designed with: (1) An approach to handle Arabic and English written tweets, and can be extended to cover data written in more languages and from other social networking platforms, (2) An effective data preparation and preprocessing techniques, (3) A novel feature selection technique that allows utilizing different types of features (content-dependent, context-dependent, and domain-dependent), in addition to (4) A novel feature extraction technique to assign weights to the linguistic features based on how representative they are in in the classes they belong to. The proposed framework is employed in performing sentiment analysis and misleading information detection. The performance of this framework is compared to state-of-the-art classification approaches utilizing 11 benchmark datasets comprising both Arabic and English textual content, demonstrating considerable improvement over all other performance evaluation metrics. Then, this framework is utilized in a real-life case study to detect misleading information surrounding the spread of COVID-19. In the second framework, a new multidimensional classification assessment score (MCAS) is introduced. MCAS can determine how good the classification algorithm is when dealing with binary classification problems. It takes into consideration the effect of misclassification errors on the probability of correct detection of instances from both classes. Moreover, it should be valid regardless of the size of the dataset and whether the dataset has a balanced or unbalanced distribution of its instances over the classes. An empirical and practical analysis is conducted on both synthetic and real-life datasets to compare the comportment of the proposed metric against those commonly used. The analysis reveals that the new measure can distinguish the performance of different classification techniques. Furthermore, it allows performing a class-based assessment of classification algorithms, to assess the ability of the classification algorithm when dealing with data from each class separately. This is useful if one of the classifying instances from one class is more important than instances from the other class, such as in COVID-19 testing where the detection of positive patients is much more important than negative ones. / Graduate

Very often, people buy goods on the Internet that they can not see and try. They therefore rely on reviews of other customers. However, there may be too many reviews for a human to handle them quickly and comfortably. The aim of this work is to offer an application that can recognize in Czech reviews what features of a product are most commented and whether the commentary is positive or negative. The results can save a lot of time for e-shop customers and provide interesting feedback to the manufacturers of the products.

The master's thesis deals with automatic classifi cation of text document. It explains basic terms and problems of text mining. The thesis explains term clustering and shows some basic clustering algoritms. The thesis also shows some methods of classi fication and deals with matrix regression closely. Application using matrix regression for classifi cation was designed and developed. Experiments were focused on normalization and thresholding.

With advances in information and communication technologies over the past few years, the amount of information stored in the form of electronic text documents has been rapidly growing. Since the human abilities to effectively process and analyze large amounts of information are limited, there is an increasing demand for tools enabling to automatically analyze these documents and benefit from their emotional content. These kinds of systems have extensive applications. The purpose of this work is to design and implement a system for identifying expression of emotions in Czech texts. The proposed system is based mainly on machine learning methods and therefore design and creation of a training set is described as well. The training set is eventually utilized to create a model of classifier using the SVM. For the purpose of improving classification results, additional components were integrated into the system, such as lexical database, lemmatizer or derived keyword dictionary. The thesis also presents results of text documents classification into defined emotion classes and evaluates various approaches to categorization.

The thesis deals with machine processing of textual data. In the theoretical part, issues related to natural language processing are described and different ways of pre-processing and representation of text are also introduced. The thesis also focuses on the usage of N-grams as features for document representation and describes some algorithms used for their extraction. The next part includes an outline of classification methods used. In the practical part, an application for pre-processing and creation of different textual data representations is suggested and implemented. Within the experiments made, the influence of these representations on accuracy of classification algorithms is analysed.

La détection d'insatisfaction basée sur les notes de progression rédigées par des soignants de la santé domestique attire de plus en plus d'attention en tant que méthode de sondage, ce qui aidera à réduire le taux de rotation du personnel soignant. Nous proposons d'étudier la détection d'insatisfaction du soignant comme un problème de classification binaire (le soignant est susceptible de quitter ou pas). Dans ce mémoire, les données réelles de six mois recueillies à partir de deux agences de soins à domicile sont utilisées. Après avoir montré la nature des données et le prétraitement des données, trois tâches de classification avec des granularités d'échantillonnage différentes (par note, par période et par soignant) sont conçues et abordées. Différentes combinaisons d'hyper-paramètres d'étiquetage sont soigneusement testées. Différentes méthodes de découpage sont couvertes pour montrer les limites des performances théoriques des modèles. L'aire sous la courbe ROC est utilisée pour évaluer les limites des approches mises en place que nous aurons mis en place. Les 6 ensembles d'attributs textuels et statistiques sont comparées. Enfin, les caractéristiques importantes des résultats sont analysées manuellement et automatiquement. Nous montrons que les modèles fonctionnent mieux "par note" et "par période" que "par soignant" en termes de classification des notes. L'analyse manuelle montre que les modèles capturent les facteurs d'insatisfaction bien qu'il y en ait assez peu. L'analyse automatique n'exprime cependant aucune information utile. / Dissatisfaction detection based on the home health caregiver's progress note draws more and more attention as a probing method, which will help lower down the turnover rate. We propose to study the detection of dissatisfaction of health caregiver as a binary classification problem (the caregiver is likely to "leave" or "stay"). In this master thesis, the real six-month data collected from two home care agencies are used. After showing the nature of the data and the prepossessing of data, three classification tasks with different sample granularity (note wise, period wise and employee wise) are designed and tackled. Different combinations of labeling hyper-parameters are tested thoroughly. Different split methods are covered to show the theoretical performance boundaries of the models. The under the ROC curve area (AUC) scores are reported to show the description ability of each model. The 6 sets of textual and statistical features' performance are compared. Lastly, the important features from the results are analyzed manually and automatically. We show that models work better on note wise and period wise than employee wise in terms of classifying the notes. The result of manual analysis shows the models capture the dissatisfaction factors, although there are quite few. The result of automatic analysis doesn't show any useful information.

Dans le contexte actuel, il y a un besoin évident de techniques de fouille de textes pour analyser l'énorme quantité de documents textuelles non structurées disponibles sur Internet. Ces données textuelles sont souvent représentées par des matrices creuses (sparses) de grande dimension où les lignes et les colonnes représentent respectivement des documents et des termes. Ainsi, il serait intéressant de regrouper de façon simultanée ces termes et documents en classes homogènes, rendant ainsi cette quantité importante de données plus faciles à manipuler et à interpréter. Les techniques de classification croisée servent justement cet objectif. Bien que plusieurs techniques existantes de co-clustering ont révélé avec succès des blocs homogènes dans plusieurs domaines, ces techniques sont toujours contraintes par la grande dimensionalité et la sparsité caractérisant les matrices documents-termes. En raison de cette sparsité, plusieurs co-clusters sont principalement composés de zéros. Bien que ces derniers soient homogènes, ils ne sont pas pertinents et doivent donc être filtrés en aval pour ne garder que les plus importants. L'objectif de cette thèse est de proposer de nouveaux algorithmes de co-clustering conçus pour tenir compte des problèmes liés à la sparsité mentionnés ci-dessus. Ces algorithmes cherchent une structure diagonale par blocs et permettent directement d'identifier les co-clusters les plus pertinents, ce qui les rend particulièrement efficaces pour le co-clustering de données textuelles. Dans ce contexte, nos contributions peuvent être résumées comme suit: Tout d'abord, nous introduisons et démontrons l'efficacité d'un nouvel algorithme de co-clustering basé sur la maximisation directe de la modularité de graphes. Alors que les algorithmes de co-clustering existants qui se basent sur des critères de graphes utilisent des approximations spectrales, l'algorithme proposé utilise une procédure d'optimisation itérative pour révéler les co-clusters les plus pertinents dans une matrice documents-termes. Par ailleurs, l'optimisation proposée présente l'avantage d'éviter le calcul de vecteurs propres, qui est une tâche rédhibitoire lorsque l'on considère des données de grande dimension. Ceci est une amélioration par rapport aux approches spectrales, où le calcul des vecteurs propres est nécessaire pour effectuer le co-clustering. Dans un second temps, nous utilisons une approche probabiliste pour découvrir des structures en blocs homogènes diagonaux dans des matrices documents-termes. Nous nous appuyons sur des approches de type modèles de mélanges, qui offrent de solides bases théoriques et une grande flexibilité qui permet de découvrir diverses structures de co-clusters. Plus précisément, nous proposons un modèle de blocs latents parcimonieux avec des distributions de Poisson sous contraintes. De façon intéressante, ce modèle comprend la sparsité dans sa formulation, ce qui le rend particulièrement adapté aux données textuelles. En plaçant l'estimation des paramètres de ce modèle dans le cadre du maximum de vraisemblance et du maximum de vraisemblance classifiante, quatre algorithmes de co-clustering ont été proposées, incluant une variante dure, floue, stochastique et une quatrième variante qui tire profit des avantages des variantes floue et stochastique simultanément. Pour finir, nous proposons un nouveau cadre de fouille de textes biomédicaux qui comprend certains algorithmes de co-clustering mentionnés ci-dessus. Ce travail montre la contribution du co-clustering dans une problématique réelle de fouille de textes biomédicaux. Le cadre proposé permet de générer de nouveaux indices sur les résultats retournés par les études d'association pan-génomique (GWAS) en exploitant les abstracts de la base de données PUBMED. (...) / In the current context, there is a clear need for Text Mining techniques to analyse the huge quantity of unstructured text documents available on the Internet. These textual data are often represented by sparse high dimensional matrices where rows and columns represent documents and terms respectively. Thus, it would be worthwhile to simultaneously group these terms and documents into meaningful clusters, making this substantial amount of data easier to handle and interpret. Co-clustering techniques just serve this purpose. Although many existing co-clustering approaches have been successful in revealing homogeneous blocks in several domains, these techniques are still challenged by the high dimensionality and sparsity characteristics exhibited by document-term matrices. Due to this sparsity, several co-clusters are primarily composed of zeros. While homogeneous, these co-clusters are irrelevant and must be filtered out in a post-processing step to keep only the most significant ones. The objective of this thesis is to propose new co-clustering algorithms tailored to take into account these sparsity-related issues. The proposed algorithms seek a block diagonal structure and allow to straightaway identify the most useful co-clusters, which makes them specially effective for the text co-clustering task. Our contributions can be summarized as follows: First, we introduce and demonstrate the effectiveness of a novel co-clustering algorithm based on a direct maximization of graph modularity. While existing graph-based co-clustering algorithms rely on spectral relaxation, the proposed algorithm uses an iterative alternating optimization procedure to reveal the most meaningful co-clusters in a document-term matrix. Moreover, the proposed optimization has the advantage of avoiding the computation of eigenvectors, a task which is prohibitive when considering high dimensional data. This is an improvement over spectral approaches, where the eigenvectors computation is necessary to perform the co-clustering. Second, we use an even more powerful approach to discover block diagonal structures in document-term matrices. We rely on mixture models, which offer strong theoretical foundations and considerable flexibility that makes it possible to uncover various specific cluster structure. More precisely, we propose a rigorous probabilistic model based on the Poisson distribution and the well known Latent Block Model. Interestingly, this model includes the sparsity in its formulation, which makes it particularly effective for text data. Setting the estimate of this model’s parameters under the Maximum Likelihood (ML) and the Classification Maximum Likelihood (CML) approaches, four co-clustering algorithms have been proposed, including a hard, a soft, a stochastic and a fourth algorithm which leverages the benefits of both the soft and stochastic variants, simultaneously. As a last contribution of this thesis, we propose a new biomedical text mining framework that includes some of the above mentioned co-clustering algorithms. This work shows the contribution of co-clustering in a real biomedical text mining problematic. The proposed framework is able to propose new clues about the results of genome wide association studies (GWAS) by mining PUBMED abstracts. This framework has been tested on asthma disease and allowed to assess the strength of associations between asthma genes reported in previous GWAS as well as discover new candidate genes likely associated to asthma. In a nutshell, while several text co-clustering algorithms already exist, their performance can be substantially increased if more appropriate models and algorithms are available. According to the extensive experiments done on several challenging real-world text data sets, we believe that this thesis has served well this objective.

As a part of the growing movement called the “peer-to-peer” economy, Airbnb has changed the short-stay rental market and has become one of the world’s largest booking websites for finding an accommodation to stay. The platform has also affected the economy of tourism around the world, so, given the importance of the subject, in this thesis study, the impacts that the Airbnb rental accommodation model has on clients of Stockholm, Barcelona and Rio de Janeiro is studied. In this way, it has been analyzed how factors such as price, location and seasonality affect Airbnb customers in these cities. To do this, the three cities were first analyzed individually and then compared, using data from the Inside Airbnb website from 2010 to now. This research has been carried out through an exploratory analysis using the R programming language. The study has been divided into three parts: First, the Spatial Data Analysis has shown that Airbnb´s presence in all three cities has increased significantly in the past decade, growing from the most touristy parts of the city to surrounding areas. In addition, it has been observed that the largest number of Airbnb properties are apartments located near the city center and touristic places, which also are the most valued areas by Airbnb customers and the most expensive to rent a property. Secondly, a Demand and Price Analysis has been carried out. In this part, the demand for Airbnb listings has been estimated over the years since 2010 and across months. A significant increase in demand has been appreciated in the last decade, which also shows a seasonal pattern. In the three cases, the demand graph follows the city´s climate, showing the highest demand during the summer months, which corresponds to the most expensive period. Finally, through User Review Mining, customer opinion has been studied by applying text mining to reviews. In this part of the research, word clouds have been used to have a visual representation of the text data, showing the most frequent words and analyzing what makes customers feel comfortable and uncomfortable. / I detta examensarbete har effekterna som Airbnbs hyresmodell har på kunder i Stockholm, Barcelona och Rio de Janeiro studerats. På detta sätt har det varit möjligt att analysera hur faktorer som pris, plats och säsongsvaror påverkar Airbnbs kunder i dessa städer. För att göra detta analyserades först de tre städerna individuellt och jämfördes sedan med data från webbplatsen Inside Airbnb från 2010 till nu. Denna forskning har genomförts genom en undersökande analys med programmeringsspråket R. Studien har delats in i tre delar: För det första har den rumsliga dataanalysen visat att Airbnbs närvaro i alla tre städerna har ökat markant under det senaste decenniet och växte från att omfatta de delar av staden som är mest intressanta för turister till omgivande områden. Dessutom har det observerats att det största antalet objekt på Airbnb är lägenheter belägna nära centrum och platser intressanta för turister, som också är de mest värderade områdena av Airbnbs kunder och de som är dyrast att hyra i en fastighet. För det andra har en efterfrågan och prisanalys genomförts. I denna del har efterfrågan på Airbnbs registreringar uppskattats under åren sedan 2010 och över flera månader. En betydande ökning av efterfrågan under det senaste decenniet har uppskattats, vilket också visar ett säsongsmönster. I samtliga tre fall följer efterfrågan förändringarna i stadens klimat och visar den högsta efterfrågan under sommarmånaderna, vilket också motsvarar den dyraste perioden. Slutligen, i avsnittet Användarrecensioner, har återkoppling från kunderna studerats genom att använda textutvinning på recensioner. I denna del av forskningen har ordmoln använts för att få en visuell representation av textdata, som visar de vanligaste orden och analyserar vad som gör att kunderna känner sig bekväma och obekväma.

Low Impact Development (LID) is a sustainable stormwater management approach that aims to control runoff close to its source, mimicking the natural hydrological processes such as infiltration and storage. It is being adopted by many cities, where its implementation is rapidly evolving. The LID practices are small-scale measures; therefore, they need to be widely implemented to impact significantly. The selection of LIDs depends on the land use and characteristics of the area of interest. This study focuses on residential LIDs. First, a systematic and bibliometric literature review is conducted on the residential LIDs articles published up to the year 2020; a total of 94 papers were found in the Web of Science. This review resulted that LID implementation in residential areas still needs to be investigated. To assist the City, engineers, and policy-makers in implementing the suitable LIDs for detached houses, a multi-criteria decision analysis framework incorporating a hydrological model is developed in this study. The commonly used LIDs were identified, which are rain gardens, permeable pavement, rain barrels, soakaways. Seven criteria were selected – runoff depth reduction rate, peak runoff reduction rate, installation cost, maintenance cost, retrofit cost, life cycle, and aesthetical view. For the properties of the single-detached house and LIDs, the standards of Credit Valley Conservation (CVC) and Toronto and Region Conservation Authority (TRCA) were followed. The proposed decision-making framework also was applied to a case study. This framework is still in the preliminary stage, thus holds the potential to convert into a tool that will be handy enough for the homeowners and consume less time. / Thesis / Master of Applied Science (MASc)