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.

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.

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.

Acupuncture complication--a case report.

A migrating, broken acupuncture needle inserted 28 years prior, impinged the L5 nerve root causing severe chronic pain which was relieved by surgical removal. Worldwide literature revealed an unexpected and surprising number of serious complications from acupuncture treatment.