Evolving Perceptions of Mental Health on Social Media and their Medical Impacts

Mental health is an ever-growing issue of concern, especially in light of the COVID pandemic. In this context, we study big data from social media over a 7-year time span to gauge evolving perceptions of mental health, and discuss our research findings, potentially useful for decision support in healthcare. We deploy topic modeling and sentiment analysis to estimate public perceptions of mental health issues, focusing on Twitter as the social media site. We claim that it is important to consider polarity as well as subjectivity in sentiment analysis to comprehend two different aspects of sentiment, i.e. orientation in the emotion, and extent of fact vs. opinion. We assert that ranking via topic modeling is beneficial to fathom the relative importance of issues over the years. We harness tools/techniques from natural language processing and data mining to discover knowledge from big data on social media, related to mental health. Some of our findings reveal that the sentiment around mental health has remained positive overall, but has decreased since the beginning of the COVID pandemic. Major events, such as elections and the pandemic, greatly impact the conversation surrounding mental health. Some topics have remained consistent throughout the years. In other topics, the tone of the public discussions has shifted. The outcomes of our study would be useful to a variety of professionals, ranging from data scientists to epidemiologists and psychologists. This work impacts big healthcare data in general. © 2022 IEEE.

Inferring Phylogenetic Relationships using the Smith-Waterman Algorithm and Hierarchical Clustering

All biological species undergo change over time due to the evolutionary process. These changes can occur rapidly and unpredictably. Due to their high potential to spread quickly, it is critical to be able to monitor changes and detect viral variants. Phylogenetic trees serve as good methods to study evolutionary relationships. Complex big data in biomedicine is plentiful in regards to viral data. In this paper, we analyze phylogenetic trees with reference to viruses and conduct dynamic programming using the Smith-Waterman algorithm, followed by hierarchical clustering. This methodology constitutes an intelligent approach for data mining, paving the way for examining variations in SARS-Cov-2, which in turn can help to discover knowledge potentially useful in biomedicine. © 2022 IEEE.

My-Covid-Safe-Town: A mobile application to support post-Covid recovery of small local businesses

The Covid-19 pandemic growth has led to a large desire for safety restrictions among citizens near or in Covid-19 affected areas. This includes requiring the use of masks when outdoors and an occupancy limit being placed when indoors. Some of these restrictions have been enforced by the government and can lead to infraction charges on those who choose to ignore them, but some restrictions are up to the decision of the respective individuals. This has led to varying levels of safety being applied when outside. This is especially concerning when some businesses may not be taking proper precautions to avoid the spread of Covid-19. To counterbalance this issue while also spreading awareness of the businesses that are careful enough to follow such precautions, the app My-Covid-Safe-Town (MCST) is created. MCST allows for individuals (i.e., patrons) to find businesses that fit the standard of safety and to specifically point out the steps being taken by each business to avoid the spread of the pandemic.

Understanding the Information Disseminated Using Twitter During the COVID-19 Pandemic

Twitter, with its ever-growing influence, has continued to serve as a means of spreading information and often providing early warnings to the situations that the world is encountering. The COVID-19 pandemic is no exception. With this disease resulting in hundreds of thousands of deaths, it is valuable that an analysis is conducted regarding the source of information posted on social media sites such as Twitter. In this study, we specifically analyze the source-URLs being posted by influential Twitter accounts. Our main goal in this study is to understand the kind of online materials, i.e., external weblinks that Twitter users prefer to promote/share about COVID-19.

SeVa: A Food Donation App for Smart Living

An important goal in our world today is to eliminate food waste by reutilizing available food sources within local communities: leftover food items in restaurants, stores and food distribution centers that may be approaching expiration;and any perishable items not used in entirety within their desired period. This is highly significant, particularly during crises such as the COVID-19 pandemic. This paper focuses on creating an interesting mobile application (app) called SeVa that provides a ubiquitous platform wherein users can visualize available food resources in their local area and consequently gain access to food, thereby tackling two major issues, i.e. hunger and food waste. This app is pertinent to the UN SDGs (United Nations Sustainable Development Goals) and fits the general realm of AI for Smart Living in Smart Cities. In addition to entailing IoT (Internet of Things) and ubiquitous computing, this work makes positive impacts on both healthcare and environment by reducing hunger and food waste respectively. We describe our SeVa app development using principles from AI, and especially HCI (Human Computer Interaction), along with its evaluation encompassing user surveys. We also list some open issues with the scope for future work.

Transfer learning for decision support in Covid-19 detection from a few images in big data

The novel coronavirus (Covid-19) has spread rapidly amongst countries all around the globe. Compared to the rise in cases, there are few Covid-19 testing kits available. Due to the lack of testing kits for the public, it is useful to implement an automated AI-based E-health decision support system as a potential alternative method for Covid-19 detection. As per medical examinations, the symptoms of Covid-19 could be somewhat analogous to those of pneumonia, though certainly not identical. Considering the enormous number of cases of Covid-19 and pneumonia, and the complexity of the related images stored, the data pertaining to this problem of automated detection constitutes big data. With rapid advancements in medical imaging, the development of intelligent predictive and diagnostic tools have also increased at a rapid rate. Data mining and machine learning techniques are widely accepted to aid medical diagnosis. In this paper, a huge data set of X-ray images from patients with common bacterial pneumonia, confirmed Covid-19 disease, and normal healthy cases are utilized for AI-based decision support in detecting the Coronavirus disease. The transfer learning approach, which enables us to learn from a smaller set of samples in a problem and transfer the discovered knowledge to a larger data set, is employed in this study. We consider transfer learning using three different models that are pre-trained on several images from the ImageNet source. The models deployed here are VGG16, VGG19, and ResNet101. The dataset is generated by gathering different classes of images. We present our approach and preliminary evaluation results in this paper. We also discuss applications and open issues.

Item-Based Collaborative Filtering and Association Rules for a Baseline Recommender in E-Commerce

In the ever-growing data-driven world today, data increases in many forms, e.g. e-commerce sites uploading new products, streaming services adding TV shows and movies, and music platforms uploading new songs. It would be highly infeasible for end users to quickly browse all this data. Hence recommender systems can benefit end users (individuals as well as companies) in efficiently finding suitable products. Rather than making end users search through a vast array of items, recommender systems can suggest suitable items to users based on popularity of the items and the respective users' buying behavior. Accordingly, in this paper we explore two techniques widespread in recommender systems, i.e. item-based collaborative filtering and association rule mining, over Amazon review data on cellphones and accessories, and build a baseline recommender system scalable to larger data. Association rule mining is explored using the Apriori algorithm to find patterns in the data from transaction history. Item-based collaborative filtering is deployed using a correlation matrix to find similar products. Both these techniques yield useful results as evident from our baseline experiments. This work constitutes an exploratory study with longtime products in e-commerce and sets the stage for mining online data on relatively new products pertinent to the Covid-19 pandemic. These include face masks, hand sanitizers, disinfectant sprays, antibacterial wipes etc. Since multiple vendors are designing such crucial products today, it is important to provide recommendations to potential buyers. An ultimate goal in our work is to build a recommender app for e-commerce based on interesting results from our findings. This work constitutes intelligent data mining scalable over big data in e-commerce. It makes broader impacts on smart cities, since this fits the smart living and smart economy characteristics. © 2020 IEEE.