Patient perceptions of disease burden and treatment of myasthenia gravis based on sentiment analysis of digital conversations.

Myasthenia gravis (MG) is a rare, autoimmune, antibody-mediated, neuromuscular disease. This study analyzed digital conversations about MG to explore unprovoked perspectives. Advanced search, data extraction, and artificial intelligence-powered algorithms were used to harvest, mine, and structure public domain digital conversations about MG from US Internet Protocol addresses (August 2021 to August 2022). Thematic analyses examined topics, mindsets, and sentiments/key drivers via natural language processing and text analytics. Findings were described by sex/gender and treatment experience with steroids or intravenous immunoglobulin (IVIg). The 13,234 conversations were extracted from message boards (51%), social media networks (22%), topical sites (21%), and blogs (6%). Sex/gender was confirmed as female in 5703 and male in 2781 conversations, and treatment experience was with steroids in 3255 and IVIg in 2106 conversations. Topics focused on diagnosis (29%), living with MG (28%), symptoms (24%), and treatment (19%). Within 3176 conversations about symptoms, eye problems (21%), facial muscle problems (18%), and fatigue (18%) were most commonly described. Negative sentiments about MG were expressed in 59% of conversations, with only 2% considered positive. Negative conversations were dominated by themes of impact on life (29%), misdiagnosis problems (27%), treatment issues (24%), and symptom severity (20%). Impact on life was a key driver of negativity in conversations by both men (27%) and women (34%), and treatment issues was a dominant theme in conversations by steroid-treated (29%) and IVIg-treated (31%) patients. Of 1382 conversations discussing treatment barriers, 36% focused on side effects, 33% on lack of efficacy, 21% on misdiagnosis, and 10% on cost/insurance. Side effects formed the main barrier in conversations by both steroid-treated and IVIg-treated patients. Capturing the patient voice via digital conversations reveals a high degree of concern related to burden of disease, misdiagnosis, and common MG treatments among those with MG, pointing to a need for treatment options that can improve quality of life.

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.

Explainable hybrid word representations for sentiment analysis of financial news.

Due to the increasing interest of people in the stock and financial market, the sentiment analysis of news and texts related to the sector is of utmost importance. This helps the potential investors in deciding what company to invest in and what are their long-term benefits. However, it is challenging to analyze the sentiments of texts related to the financial domain, given the enormous amount of information available. The existing approaches are unable to capture complex attributes of language such as word usage, including semantics and syntax throughout the context, and polysemy in the context. Further, these approaches failed to interpret the models' predictability, which is obscure to humans. Models' interpretability to justify the predictions has remained largely unexplored and has become important to engender users' trust in the predictions by providing insight into the model prediction. Accordingly, in this paper, we present an explainable hybrid word representation that first augments the data to address the class imbalance issue and then integrates three embeddings to involve polysemy in context, semantics, and syntax in a context. We then fed our proposed word representation to a convolutional neural network (CNN) with attention to capture the sentiment. The experimental results show that our model outperforms several baselines of both classic classifiers and combinations of various word embedding models in the sentiment analysis of financial news. The experimental results also show that the proposed model outperforms several baselines of word embeddings and contextual embeddings when they are separately fed to a neural network model. Further, we show the explainability of the proposed method by presenting the visualization results to explain the reason for a prediction in the sentiment analysis of financial news.

LSTM based stock prediction using weighted and categorized financial news.

A significant correlation between financial news with stock market trends has been explored extensively. However, very little research has been conducted for stock prediction models that utilize news categories, weighted according to their relevance with the target stock. In this paper, we show that prediction accuracy can be enhanced by incorporating weighted news categories simultaneously into the prediction model. We suggest utilizing news categories associated with the structural hierarchy of the stock market: that is, news categories for the market, sector, and stock-related news. In this context, Long Short-Term Memory (LSTM) based Weighted and Categorized News Stock prediction model (WCN-LSTM) is proposed. The model incorporates news categories with their learned weights simultaneously. To enhance the effectiveness, sophisticated features are integrated into WCN-LSTM. These include, hybrid input, lexicon-based sentiment analysis, and deep learning to impose sequential learning. Experiments have been performed for the case of the Pakistan Stock Exchange (PSX) using different sentiment dictionaries and time steps. Accuracy and F1-score are used to evaluate the prediction model. We have analyzed the WCN-LSTM results thoroughly and identified that WCN-LSTM performs better than the baseline model. Moreover, the sentiment lexicon HIV4 along with time steps 3 and 7, optimized the prediction accuracy. We have conducted statistical analysis to quantitatively assess our findings. A qualitative comparison of WCN-LSTM with existing prediction models is also presented to highlight its superiority and novelty over its counterparts.

Sentiment Analysis of Tweets on Soda Taxes.

CONTEXT: As a primary source of added sugars, sugar-sweetened beverage (SSB) consumption may contribute to the obesity epidemic. A soda tax is an excise tax charged on selling SSBs to reduce consumption. Currently, 8 cities/counties in the United States have imposed soda taxes. OBJECTIVE: This study assessed people's sentiments toward soda taxes in the United States based on social media posts on Twitter. DESIGN: We designed a search algorithm to systematically identify and collect soda tax-related tweets posted on Twitter. We built deep neural network models to classify tweets by sentiments. SETTING: Computer modeling. PARTICIPANTS: Approximately 370 000 soda tax-related tweets posted on Twitter from January 1, 2015, to April 16, 2022. MAIN OUTCOME MEASURE: Sentiment associated with a tweet. RESULTS: Public attention paid to soda taxes, indicated by the number of tweets posted annually, peaked in 2016, but has declined considerably ever since. The decreasing prevalence of tweets quoting soda tax-related news without revealing sentiments coincided with the rapid increase in tweets expressing a neutral sentiment toward soda taxes. The prevalence of tweets expressing a negative sentiment rose steadily from 2015 to 2019 and then slightly leveled off, whereas that of tweets expressing a positive sentiment remained unchanged. Excluding news-quoting tweets, tweets with neutral, negative, and positive sentiments occupied roughly 56%, 29%, and 15%, respectively, during 2015-2022. The authors' total number of tweets posted, followers, and retweets predicted tweet sentiment. The finalized neural network model achieved an accuracy of 88% and an F1 score of 0.87 in predicting tweet sentiments in the test set. CONCLUSIONS: Despite its potential to shape public opinion and catalyze social changes, social media remains an underutilized source of information to inform government decision making. Social media sentiment analysis may inform the design, implementation, and modification of soda tax policies to gain social support while minimizing confusion and misinterpretation.

Orientação a pais por chamadas de áudio durante a pandemia de covid-19 / Support for parents via audio calls during the covid-19 pandemic / Orientación de los padres mediante llamadas de audio durante la pandemia de covid-19

O distanciamento social ocasionado pela pandemia de Covid-19 levou a profundas mudanças na rotina das famílias com crianças pequenas, aumentando o estresse no ambiente doméstico. Este estudo analisou a experiência de planejamento e implementação de um projeto de extensão universitária que ofereceu orientação a pais com filhos de 0 a 11 anos por meio de chamadas de áudio durante a pandemia. O protocolo de atendimento foi desenvolvido para atender às necessidades de famílias de baixa renda e listava problemas específicos relacionados ao confinamento em casa e ao fechamento das escolas seguidos por uma variedade de estratégias de enfrentamento. A análise de 223 queixas relatadas pelos usuários em 130 ligações revelou que 94% dos problemas referidos pelos pais foram contemplados pelo protocolo de atendimento e estavam relacionados aos problemas externalizantes (39%) ou internalizantes (26%) das crianças ou ao declínio do bem-estar subjetivo dos pais (29%). Serviços de apoio devem orientar os pais quanto ao uso de práticas responsivas e assertivas que promovam o bem-estar emocional da criança e estabeleçam expectativas comportamentais em contextos estressantes. A diminuição dos conflitos entre pais e filhos resultante do uso dessas estratégias tende a reduzir o sofrimento dos pais, aumentando sua sensação de bem-estar subjetivo. Recomenda-se ampla divulgação dessas iniciativas e seguimento dos casos.(AU)

The social distancing the COVID-19 pandemic entailed has led to profound changes in the routine of families with young children, increasing stress in the home environment. This study analyzed the experience of planning and implementing a university extension program that offered support to parents with children from 0 to 11 years old via audio calls during the COVID-19 pandemic. The service protocol was developed to meet the needs of low-income families and listed specific problems related to home confinement and school closure followed by a variety of coping strategies. The analysis of 223 complaints reported by users in 130 calls revealed that 94% of the problems reported by parents were addressed by the protocol and were related to children's externalizing (39%) or internalizing (26%) problems or to the decline in parents' subjective well-being (29%). Support services should guide parents on the use of responsive and assertive practices that promote the child's emotional well-being and set behavioral expectations in stressful contexts. The reduction in conflicts between parents and children resulting from the use of these strategies tends to reduce parents' suffering, increasing their sense of subjective well-being. Wide dissemination of these initiatives and case follow-up are recommended.(AU)

La distancia social causada por la pandemia de COVID-19 condujo a cambios profundos en la rutina de las familias con niños pequeños, aumentando el estrés en el entorno del hogar. Este estudio analizó la experiencia de planificar e implementar un proyecto de extensión universitaria que ofreció orientación a los padres con niños de cero a 11 años a través de llamadas de audio durante la pandemia COVID-19. El protocolo de atención se desarrolló para satisfacer las necesidades de las familias de bajos ingresos y enumeró problemas específicos relacionados con el confinamiento en el hogar y el cierre de la escuela, seguido de una variedad de estrategias de afrontamiento. El análisis de 223 quejas informadas por los usuarios en 130 llamadas reveló que el 94% de los problemas informados por los padres fueron abordados por el protocolo de atención y estaban relacionados con los problemas de externalización (39%) o internalización (26%) de los niños o la disminución del bienestar subjetivo de los padres (29%). Los servicios de apoyo deberían aconsejar a los padres sobre el uso de prácticas receptivas y asertivas que promuevan el bienestar emocional del niño y establezcan expectativas de comportamiento en contextos estresantes. La reducción de los conflictos entre padres e hijos como resultado del uso de estas estrategias tiende a reducir el sufrimiento de los padres, aumentando su sensación de bienestar subjetivo. Se recomienda una amplia difusión de estas iniciativas y seguimiento de casos.(AU)

Exploring the Chinese Public's Perception of Omicron Variants on Social Media: LDA-Based Topic Modeling and Sentiment Analysis.

The COVID-19 pandemic caused by SARS-CoV-2 is still raging. Similar to other RNA viruses, SARS-COV-2 is constantly mutating, which leads to the production of many infectious and lethal strains. For instance, the omicron variant detected in November 2021 became the leading strain of infection in many countries around the world and sparked an intense public debate on social media. The aim of this study is to explore the Chinese public's perception of the omicron variants on social media. A total of 121,632 points of data relating to omicron on Sina Weibo from 0:00 27 November 2021 to 23:59:59 30 March 2022 (Beijing time) were collected and analyzed with LDA-based topic modeling and DLUT-Emotion ontology-based sentiment analysis. The results indicate that (1) the public discussion of omicron is based on five topics, including omicron's impact on the economy, the omicron infection situation in other countries/regions, the omicron infection situation in China, omicron and vaccines and pandemic prevention and control for omicron. (2) From the 3 sentiment orientations of 121,632 valid Weibo posts, 49,402 posts were judged as positive emotions, accounting for approximately 40.6%; 47,667 were negative emotions, accounting for nearly 39.2%; and 24,563 were neutral emotions, accounting for about 20.2%. (3) The result of the analysis of the temporal trend of the seven categories of emotion attribution showed that fear kept decreasing, whereas good kept increasing. This study provides more insights into public perceptions of and attitudes toward emerging SARS-CoV-2 variants. The results of this study may provide further recommendations for the Chinese government, public health authorities, and the media to promote knowledge about SARS-CoV-2 variant pandemic-resistant messages.

Deep-Learning-Based Financial Message Sentiment Classification in Business Management.

A deep-learning-based financial text sentiment classification method is proposed in this paper, which can provide a reference for business management. In the proposed method, domain adaptation is adopted to solve the common problem of insufficient labeled samples in the financial textual domain. Specifically, in the classification process, the seq2seq model is firstly adopted to extract the abstract from the financial message, which can reduce the influence of invalid information and speed up processing. In the process of sentiment classification, a bidirectional LSTM model is adopted for classification, which can more comprehensively make use of context information. Experiments are carried out to testify the proposed method through the open-source data set. It can be seen that the proposed method can effectively transfer from the reduced Amazon data set to the StockTwits financial text data set. Compared with the parameter-frozen-based method and the SDA-based method, the recognition rates have improved by 0.5% and 6.8%, respectively. If the target domain data set can be directly adopted for training, the recognition rate of the proposed method is higher than that of the SVM method and the LSTM method by 8.3% and 4.5%, respectively.

Deep Neural Networks Applied to Stock Market Sentiment Analysis.

The volume of data is growing exponentially and becoming more valuable to organizations that collect it, from e-commerce data, shipping, audio and video logs, text messages, internet search queries, stock market activity, financial transactions, the Internet of Things, and various other sources. The major challenges are related with the way to extract insights from such a rich data environment and whether Deep Learning can be successful with Big Data. To get some insight on these topics, social network data are employed as a case study on how sentiments can affect decisions in stock market environments. In this paper, we propose a generalized Deep Learning-based classification framework for Stock Market Sentiment Analysis. This work comprises the study, the development, and implementation of an automatic classification system based on Deep Learning and the validation of its adequacy and efficiency in any scenario, particularly Stock Market Sentiment Analysis. Distinct datasets and several Deep Learning approaches with different layers and embedded techniques are used, and their performances are evaluated. These developments show how Deep Learning reacts to distinct contexts. The results also give context on how different techniques with different parameter combinations react to certain types of data. Convolution obtained the best results when dealing with complex data inputs, and long short-term layers kept a memory of data, allowing inputs which are not as common to still be considered for decisions. The models that resulted from Stock Market Sentiment Analysis datasets were applied with some success to real-life problems. The best models reached accuracies of 73% in training and 69% in certain test datasets. In a simulation, a model was able to provide a Return on Investment of 4.4%. The results contribute to understanding how to process Big Data efficiently using Deep Learning and specialized hardware techniques.

Breastfeeding media coverage and beliefs during the COVID-19 pandemic in Mexico: implications for breastfeeding equity.

BACKGROUND: Because breastfeeding offers short- and long- term health benefits to mothers and children, breastfeeding promotion and support is a public health priority. Evidence shows that SARS-CoV-2 is not likely to be transmitted via breastmilk. Moreover, antibodies against SARS-CoV-2 are thought to be contained in breastmilk of mothers with history of COVID-19 infection or vaccination. WHO recommends direct breastfeeding as the preferred infant feeding option during the COVID-19 pandemic, even among women with COVID-19; but conflicting practices have been adopted, which could widen existing inequities in breastfeeding. This study aims to describe how information about breastfeeding was communicated in Mexican media during the pandemic and assess Mexican adults' beliefs regarding breastfeeding among mothers infected with COVID-19. METHODS: We conducted a retrospective content analysis of media coverage on breastfeeding in Mexico between March 1 and September 24, 2020, excluding advertisements. For the content analysis, we performed both a sentiment analysis and an analysis based on strengths, weaknesses, opportunities, and threats (SWOT) for breastfeeding promotion. Additionally, we conducted a descriptive analysis of nationally representative data on adults' beliefs about breastfeeding from the July 2020 round of the ENCOVID-19 survey in Mexico and stratified the results by gender, age, and socioeconomic status. RESULTS: A total of 1014 publications on breastfeeding were identified on the internet and television and in newspapers and magazines. Most information was published during World Breastfeeding Week, celebrated in August. The sentiment analysis showed that 57.2% of all information was classified as positive. The SWOT analysis indicated that most information focused on current actions, messages, policies, or programs that enable breastfeeding (i.e., strengths) or those not currently in place but that may enable breastfeeding (i.e., opportunities) for breastfeeding promotion. However, ENCOVID-19 survey results showed that 67.3% of adults living in households with children under 3 years of age believe that mothers with COVID-19 should not breastfeed, and 19.8% do not know whether these mothers should breastfeed. These beliefs showed differences both by gender and by socioeconomic status. CONCLUSIONS: While the Mexican government endorsed the recommendation on breastfeeding during the COVID-19 pandemic, communication was sporadic, inconstant and unequal across types of media. There was a widespread notion that mothers with COVID-19 should not breastfeed and due to differences on beliefs by socioeconomic status, health inequities could be exacerbated by increasing the risk of poorer breastfeeding practices and preventing vulnerable groups from reaping the short and long-term benefits of breastfeeding.

Stock Price Movement Prediction Using Sentiment Analysis and CandleStick Chart Representation.

Determining the price movement of stocks is a challenging problem to solve because of factors such as industry performance, economic variables, investor sentiment, company news, company performance, and social media sentiment. People can predict the price movement of stocks by applying machine learning algorithms on information contained in historical data, stock candlestick-chart data, and social-media data. However, it is hard to predict stock movement based on a single classifier. In this study, we proposed a multichannel collaborative network by incorporating candlestick-chart and social-media data for stock trend predictions. We first extracted the social media sentiment features using the Natural Language Toolkit and sentiment analysis data from Twitter. We then transformed the stock's historical time series data into a candlestick chart to elucidate patterns in the stock's movement. Finally, we integrated the stock's sentiment features and its candlestick chart to predict the stock price movement over 4-, 6-, 8-, and 10-day time periods. Our collaborative network consisted of two branches: the first branch contained a one-dimensional convolutional neural network (CNN) performing sentiment classification. The second branch included a two-dimensional (2D) CNN performing image classifications based on 2D candlestick chart data. We evaluated our model for five high-demand stocks (Apple, Tesla, IBM, Amazon, and Google) and determined that our collaborative network achieved promising results and compared favorably against single-network models using either sentiment data or candlestick charts alone. The proposed method obtained the most favorable performance with 75.38% accuracy for Apple stock. We also found that the stock price prediction achieved more favorable performance over longer periods of time compared with shorter periods of time.