Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
2,011
result(s) for
"Bernard, Patrick"
Sort by:
Analyzing influence of COVID-19 on crypto & financial markets and sentiment analysis using deep ensemble model
COVID-19 affected the world’s economy severely and increased the inflation rate in both developed and developing countries. COVID-19 also affected the financial markets and crypto markets significantly, however, some crypto markets flourished and touched their peak during the pandemic era. This study performs an analysis of the impact of COVID-19 on public opinion and sentiments regarding the financial markets and crypto markets. It conducts sentiment analysis on tweets related to financial markets and crypto markets posted during COVID-19 peak days. Using sentiment analysis, it investigates the people’s sentiments regarding investment in these markets during COVID-19. In addition, damage analysis in terms of market value is also carried out along with the worse time for financial and crypto markets. For analysis, the data is extracted from Twitter using the SNSscraper library. This study proposes a hybrid model called CNN-LSTM (convolutional neural network-long short-term memory model) for sentiment classification. CNN-LSTM outperforms with 0.89, and 0.92 F1 Scores for crypto and financial markets, respectively. Moreover, topic extraction from the tweets is also performed along with the sentiments related to each topic.
Journal Article
Sentiment Analysis and Topic Modeling on Tweets about Online Education during COVID-19
Amid the worldwide COVID-19 pandemic lockdowns, the closure of educational institutes leads to an unprecedented rise in online learning. For limiting the impact of COVID-19 and obstructing its widespread, educational institutions closed their campuses immediately and academic activities are moved to e-learning platforms. The effectiveness of e-learning is a critical concern for both students and parents, specifically in terms of its suitability to students and teachers and its technical feasibility with respect to different social scenarios. Such concerns must be reviewed from several aspects before e-learning can be adopted at such a larger scale. This study endeavors to investigate the effectiveness of e-learning by analyzing the sentiments of people about e-learning. Due to the rise of social media as an important mode of communication recently, people’s views can be found on platforms such as Twitter, Instagram, Facebook, etc. This study uses a Twitter dataset containing 17,155 tweets about e-learning. Machine learning and deep learning approaches have shown their suitability, capability, and potential for image processing, object detection, and natural language processing tasks and text analysis is no exception. Machine learning approaches have been largely used both for annotation and text and sentiment analysis. Keeping in view the adequacy and efficacy of machine learning models, this study adopts TextBlob, VADER (Valence Aware Dictionary for Sentiment Reasoning), and SentiWordNet to analyze the polarity and subjectivity score of tweets’ text. Furthermore, bearing in mind the fact that machine learning models display high classification accuracy, various machine learning models have been used for sentiment classification. Two feature extraction techniques, TF-IDF (Term Frequency-Inverse Document Frequency) and BoW (Bag of Words) have been used to effectively build and evaluate the models. All the models have been evaluated in terms of various important performance metrics such as accuracy, precision, recall, and F1 score. The results reveal that the random forest and support vector machine classifier achieve the highest accuracy of 0.95 when used with Bow features. Performance comparison is carried out for results of TextBlob, VADER, and SentiWordNet, as well as classification results of machine learning models and deep learning models such as CNN (Convolutional Neural Network), LSTM (Long Short Term Memory), CNN-LSTM, and Bi-LSTM (Bidirectional-LSTM). Additionally, topic modeling is performed to find the problems associated with e-learning which indicates that uncertainty of campus opening date, children’s disabilities to grasp online education, and lagging efficient networks for online education are the top three problems.
Journal Article
Development and validation of the Italian version of the Mobile Application Rating Scale and its generalisability to apps targeting primary prevention
Background
A growing body of literature affirms the usefulness of mobile technologies, including mobile applications (apps), in the primary prevention field. The quality of health apps, which today number in the thousands, is a crucial parameter, as it may affect health-related decision-making and outcomes among app end-users. The mobile application rating scale (MARS) has recently been developed to evaluate the quality of such apps, and has shown good psychometric properties. Since there is no standardised tool for assessing the apps available in Italian app stores, the present study developed and validated an Italian version of MARS in apps targeting primary prevention.
Methods
The original 23-item version of the MARS assesses mobile app quality in four objective quality dimensions (engagement, functionality, aesthetics, information) and one subjective dimension. Validation of this tool involved several steps; the universalist approach to achieving equivalence was adopted. Following two backward translations, a reconciled Italian version of MARS was produced and compared with the original scale. On the basis of sample size estimation, 48 apps from three major app stores were downloaded; the first 5 were used for piloting, while the remaining 43 were used in the main study in order to assess the psychometric properties of the scale. The apps were assessed by two raters, each working independently. The psychometric properties of the final version of the scale was assessed including the inter-rater reliability, internal consistency, convergent, divergent and concurrent validities.
Results
The intralingual equivalence of the Italian version of the MARS was confirmed by the authors of the original scale. A total of 43 apps targeting primary prevention were tested. The MARS displayed acceptable psychometric properties. The MARS total score showed an excellent level of both inter-rater agreement (intra-class correlation coefficient of .96) and internal consistency (Cronbach’s
α
of .90 and .91 for the two raters, respectively). Other types of validity, including convergent, divergent, discriminative, known-groups and scalability, were also established.
Conclusions
The Italian version of MARS is a valid and reliable tool for assessing the health-related primary prevention apps available in Italian app stores.
Journal Article
FinTech adoption in SMEs and bank credit supplies: A study on manufacturing SMEs
Bank lending to SMEs plays a vital role in economic growth, contributing significantly to employment and GDP. Access to bank lending is crucial for small- and medium-sized enterprises (SMEs), as they contribute significantly to global employment and GDP. New financial technologies promise better bank operations, fewer costs, and enhanced credit supply to SMEs. However, there is still a lack of empirical findings on how these technologies can solve demand-side bank lending problems for small- and medium-sized firms. This study gathered data from a sample of 381 respondents, comprising CEOs, managers, officers, loan managers, IT consultants, and other relevant stakeholders. The findings indicate that the adoption of blockchain technologies, as well as the adoption of Big Data technologies encompassing cloud computing, data analytics, algorithms, and programming, along with the adoption of mobile banking technologies, have had a substantial positive impact on bank credit supplies for small- and medium-sized enterprises (SMEs) in Pakistan. This novel study contributes to existing knowledge in two ways. First, it provides knowledge to SMEs looking to adopt new technologies; second, it provides knowledge to a manager looking to finance the SMEs with information asymmetries. This research also provides key findings for researchers and policymakers.
Journal Article
Deepfake tweets classification using stacked Bi-LSTM and words embedding
The spread of altered media in the form of fake videos, audios, and images, has been largely increased over the past few years. Advanced digital manipulation tools and techniques make it easier to generate fake content and post it on social media. In addition, tweets with deep fake content make their way to social platforms. The polarity of such tweets is significant to determine the sentiment of people about deep fakes. This paper presents a deep learning model to predict the polarity of deep fake tweets. For this purpose, a stacked bi-directional long short-term memory (SBi-LSTM) network is proposed to classify the sentiment of deep fake tweets. Several well-known machine learning classifiers are investigated as well such as support vector machine, logistic regression, Gaussian Naive Bayes, extra tree classifier, and AdaBoost classifier. These classifiers are utilized with term frequency-inverse document frequency and a bag of words feature extraction approaches. Besides, the performance of deep learning models is analyzed including long short-term memory network, gated recurrent unit, bi-direction LSTM, and convolutional neural network+LSTM. Experimental results indicate that the proposed SBi-LSTM outperforms both machine and deep learning models and achieves an accuracy of 0.92.
Journal Article
A \Cipher Language\
The first known study of the black musical form of call-and-response and its immense significance in African American oral and literary practices is \"A Study in Negro Folk Rhymes\" by Thomas W. Talley (1870-1952) in his book Negro Folk Rhymes Wise and Otherwise: With A Study (1922), a collection of black secular folksongs, unquestionably the first such compilation by a black scholar. Belonging to collections on black music and poetry published during the Harlem Renaissance or New Negro Movement,1 Talley and his text do not appear in studies about the period. They are absent from The Encyclopedia of the Harlem Renaissance (2004) and Harlem Renaissance Lives (2009), two compendiums about the era. Moreover, studies of antiphony in African American oral and literary discourses fail to credit Talley's pioneering work. Two anthologies on the subject, Call & Response (1998) and Call and Response (2011), and a study of the form in African American fiction, Call-and-Response in Twentieth-Century Black Fiction (1988, 2001), fail to acknowledge Talley's \"Study.\" It is unmentioned in works on black poetics and prosody.2 Indeed, Talley's book has been so thoroughly ignored that it is currently listed on the Forgotten Books website.3 Although this listing does not necessarily imply scholarly neglect, it is useful to note how major scholarly bibliographies, for example the MLA Bibliography, also demonstrate the range of scholarship that fails to acknowledge or discuss Talley.4 The neglect of this central text in the black oral and literary traditions deserves examination.
Journal Article
The dynamics of pseudographs in convex Hamiltonian systems
We study the evolution, under convex Hamiltonian flows on cotangent bundles of compact manifolds, of certain distinguished subsets of the phase space. These subsets are generalizations of Lagrangian graphs, which we call pseudographs. They emerge in a natural way from Fathi’s weak KAM theory. By this method, we find various orbits which connect prescribed regions of the phase space. Our study was inspired by works of John Mather. As an application, we obtain the existence of diffusion in a large class of a priori unstable systems and provide a solution to the large gap problem. We hope that our method will have applications to more examples. Résumé. Nous étudions l’évolution, par le flot d’un Hamiltonien convexe sur une variété compacte, de certains ensembles de l’espace des phases. Nous appelons pseudographes ces ensembles, qui sont des généralisations de graphes Lagrangiens apparaissant de manière naturelle dans la théorie KAM faible de Fathi. Par cette méthode, nous trouvons diverses orbites qui joignent des domaines donnés de l’espace des phases. Notre étude s’inspire de travaux de John Mather. Nous obtenons l’existence de diffusion dans une large classe de systèmes à priori instables comme application de cette méthode, qui permet de résoudre le probleme de l’écart entre les tores invariants. Nous espérons que la méthode s’appliquera à d’autres exemples.
Journal Article
The Lax–Oleinik semi-group: a Hamiltonian point of view
The weak KAM theory was developed by Fathi in order to study the dynamics of convex Hamiltonian systems. It somehow makes a bridge between viscosity solutions of the Hamilton–Jacobi equation and Mather invariant sets of Hamiltonian systems, although this was fully understood only a posteriori. These theories converge under the hypothesis of convexity, and the richness of applications mostly comes from this remarkable convergence. In this paper, we provide an elementary exposition of some of the basic concepts of weak KAM theory. In a companion paper, Albert Fathi exposed the aspects of his theory which are more directly related to viscosity solutions. Here, on the contrary, we focus on dynamical applications, even if we also discuss some viscosity aspects to underline the connections with Fathi's lecture. The fundamental reference on weak KAM theory is the still unpublished book Weak KAM theorem in Lagrangian dynamics by Albert Fathi. Although we do not offer new results, our exposition is original in several aspects. We only work with the Hamiltonian and do not rely on the Lagrangian, even if some proofs are directly inspired by the classical Lagrangian proofs. This approach is made easier by the choice of a somewhat specific setting. We work on ℝd and make uniform hypotheses on the Hamiltonian. This allows us to replace some compactness arguments by explicit estimates. For the most interesting dynamical applications, however, the compactness of the configuration space remains a useful hypothesis and we retrieve it by considering periodic (in space) Hamiltonians. Our exposition is centred on the Cauchy problem for the Hamilton–Jacobi equation and the Lax–Oleinik evolution operators associated to it. Dynamical applications are reached by considering fixed points of these evolution operators, the weak KAM solutions. The evolution operators can also be used for their regularizing properties; this opens an alternative route to dynamical applications.
Journal Article