Analysis Of Social Media Data Research Articles

EXPRESS: Spring Forward = Fall Back? the Effect of Daylight Saving Time Change on Consumers’ Unhealthy Behavior

Prior research documents deleterious consequences of the annual clock change to daylight saving time in many contexts, but little is known about the effect the policy has on consumer behavior. While policy debates around ending seasonal clock changes continue, millions of consumers worldwide are potentially adversely affected by the time change. Drawing on the notions of sleepiness and self-control, the authors propose a framework of how the onset of daylight saving time increases unhealthy behavior. The hypotheses are tested via two studies cast in the difference-in-differences modeling framework capturing consumption before and after the time change and across consumers who experience the transition versus who do not. Results of the first study suggest that the onset of daylight saving time increases calorie consumption from packaged snacks that are largely unhealthy, specifically in the evening and on cloudy days. The effect of the end of daylight saving time is not significant, suggesting an overall asymmetric effect of the time change on unhealthy behavior. Study 2 reveals that the onset of daylight saving time decreases fitness center visits, particularly for consumers without healthy consumption habits and with high transaction costs. Analysis of social media data suggests that consumers find the time change disruptive. Overall, the findings imply that public policy makers and businesses should find ways to support consumers around the onset of daylight saving time.

SARS-CoV-2 variant introduction following spring break travel and transmission mitigation strategies.

University spring break carries a two-pronged SARS-CoV-2 variant transmission risk. Circulating variants from universities can spread to spring break destinations, and variants from spring break destinations can spread to universities and surrounding communities. Therefore, it is critical to implement SARS-CoV-2 variant surveillance and testing strategies to limit community spread before and after spring break to mitigate virus transmission and facilitate universities safely returning to in-person teaching. We examined the SARS-CoV-2 positivity rate and changes in variant lineages before and after the university spring break for two consecutive years. 155 samples were sequenced across four time periods: pre- and post-spring break 2021 and pre- and post-spring break 2022; following whole genome sequencing, samples were assigned clades. The clades were then paired with positivity and testing data from over 50,000 samples. In 2021, the number of variants in the observed population increased from four to nine over spring break, with variants of concern being responsible for most of the cases; Alpha percent composition increased from 22.2% to 56.4%. In 2022, the number of clades in the population increased only from two to three, all of which were Omicron or a sub-lineage of Omicron. However, phylogenetic analysis showed the emergence of distantly related sub-lineages. 2022 saw a greater increase in positivity than 2021, which coincided with a milder mitigation strategy. Analysis of social media data provided insight into student travel destinations and how those travel events may have impacted spread. We show the role that repetitive testing can play in transmission mitigation, reducing community spread, and maintaining in-person education. We identified that distantly related lineages were brought to the area after spring break travel regardless of the presence of a dominant variant of concern.

Fine grain emotion analysis in Spanish using linguistic features and transformers

Mental health issues are a global concern, with a particular focus on the rise of depression. Depression affects millions of people worldwide and is a leading cause of suicide, particularly among young people. Recent surveys indicate an increase in cases of depression during the COVID-19 pandemic, which affected approximately 5.4% of the population in Spain in 2020. Social media platforms such as X (formerly Twitter) have become important hubs for health information as more people turn to these platforms to share their struggles and seek emotional support. Researchers have discovered a link between emotions and mental illnesses such as depression. This correlation provides a valuable opportunity for automated analysis of social media data to detect changes in mental health status that might otherwise go unnoticed, thus preventing more serious health consequences. Therefore, this research explores the field of emotion analysis in Spanish towards mental disorders. There are two contributions in this area. On the one hand, the compilation, translation, evaluation and correction of a novel dataset composed of a mixture of other existing datasets in the bibliography. This dataset compares a total of 16 emotions, with an emphasis on negative emotions. On the other hand, the in-depth evaluation of this novel dataset with several state-of-the-art transformers based on encoder-only and encoder-decoder architectures. The analysis compromises monolingual, multilingual and distilled models as well as feature integration techniques. The best results are obtained with the encoder-only MarIA model, with a macro-average F1 score of 60.4771%.

Social Media Data Analytics in the Automotive Industry: A Study of the Interactive Impact of Marketing Strategies and User Ratings

Social Media Data Analytics in the Automotive Industry: A Study of the Interactive Impact of Marketing Strategies and User Ratings

A General Overview of Recent Big Data Applications and Social Media Platforms

The exponential expansion of technology in recent years and rising data production are primarily changing the way businesses and individual industries are working. Technical advances have led to a major amount of data related to various fields which is currently generated in our daily life. Governments, businesses, and research institutions are beginning to understand how crucial it is to use this data to further their missions. As a result, Big Data research has become increasingly popular among academics working in various fields of study. We provide an overview of big data and its potential applications across a range of industries in this paper. Social media feeds are full of impending for analysis and data mining. Platform providers are beginning to limit unrestricted access to this kind of data as they become aware of its potential. This change presents significant difficulties for social inventers and other nonprofit researchers that examine public posts in an effort to better understand human behavior and enhance human welfare. This paper pursues to outline some of the topical modifications in social media data analysis. Some of the most influential and popular social media platforms are also discussed.

Empirical Study of the Impact of Social Media Data Analytics on Marketing Strategy

Social Media Data Analytics (SMDA) has emerged as a dynamic and growing field across various disciplines, including marketing. However, practitioners and researchers in the marketing domain have realized that harnessing the full potential of SMDA for guiding marketing strategies necessitates a clear understanding of the relevant SMDA metrics. A significant challenge lies in the lack of clear guidance on which SMDA metrics are most relevant for enhancing marketing strategies. This study aims to empirically evaluate the impact of SMDA on marketing strategies. To achieve this goal, the study carried out a questionnaire for data collection and employs an empirical investigation using the PLS-SEM methodology. The results show that the impact of SMDA on marketing strategy depends on SMDA metrics (data type, platforms and analysis methods) and also on marketing strategy type. The results suggest a valid conceptual model introducing novel metrics for the SMDA concept. These results present a broader perspective on how SMDA affects marketing strategies and suggest that future research should focus on a specific type of marketing strategy and study SMDA metrics in a different and more in-depth way.

Social Media and the DIY Politics in Thailand's 2023 Election

This article argues that Thailand's 2023 parliamentary election was the first election in which social media played a decisive factor in the electoral outcomes. Prior to this election, social media was an important campaign tool, but it was unclear whether it made a difference in the electoral results. Based on our original post-election survey data (n = 1,249), social media was the most important media in governing vote choice. Social media was a crucial space for activation and conversion—motivating the undecided to become partisans and converting partisan voters to shift their allegiances. Thailand's 2023 election was also marked by a rise in the personalization of political campaigning, wherein citizens felt free to decide how and what their political participation looked like, and parties that encouraged inclusive and open engagement with politics were best poised to win in the electoral arena. Drawing on social network analysis of social media data, this article demonstrates how the Move Forward Party's (MFP) loosely structured and inclusive social media campaigns allowed both their candidates and supporters to mobilize individualized large-scale collective action, in contrast to their rivals who focused on traditional top-down style campaigning. Despite the MFP's winning social media campaigning that produced electoral victories, the party was unable to come to power due to an entrenched authoritarian political system designed to maintain the power of the country's autocratic elites. The Thai case demonstrates powerfully how autocrats might lose an election due to social media, yet still manage to hang on to power through entrenched authoritarian institutions.

Trends in sentiment of Twitter users towards Indonesian tourism: analysis with the k-nearest neighbor method

This research analyzes the sentiment of Twitter users regarding tourism in Indonesia using the keyword "wonderful Indonesia" as the tourism promotion identity. The aim of this study is to gain a deeper understanding of the public sentiment towards "wonderful Indonesia" through social media data analysis. The novelty obtained provides new insights into valuable information about Indonesian tourism for the government and relevant stakeholders in promoting Indonesian tourism and enhancing tourist experiences. The method used is tweet analysis and classification using the K-nearest neighbor (KNN) algorithm to determine the positive, neutral, or negative sentiment of the tweets. The classification results show that the majority of tweets (65.1% out of a total of 14,189 tweets) have a neutral sentiment, indicating that most tweets with the "wonderful Indonesia" tagline are related to advertising or promoting Indonesian tourism. However, the percentage of tweets with positive sentiment (33.8%) is higher than those with negative sentiment (1.1%). This study also achieved training results with an accuracy rate of 98.5%, precision of 97.6%, recall of 98.5%, and F1-score of 98.1%. However, reassessment is needed in the future as Twitter users' sentiment can change along with the development of Indonesian tourism itself.

Trends in sentiment of Twitter users towards Indonesian tourism: analysis with the k-nearest neighbor method

This research analyzes the sentiment of Twitter users regarding tourism in Indonesia using the keyword "wonderful Indonesia" as the tourism promotion identity. This study aims to gain a deeper understanding of the public sentiment towards "wonderful Indonesia" through social media data analysis. The novelty obtained provides new insights into valuable information about Indonesian tourism for the government and relevant stakeholders in promoting Indonesian tourism and enhancing tourist experiences. The method used is tweet analysis and classification using the K-nearest neighbor (KNN) algorithm to determine the positive, neutral, or negative sentiment of the tweets. The classification results show that the majority of tweets (65.1% out of a total of 14,189 tweets) have a neutral sentiment, indicating that most tweets with the "wonderful Indonesia" tagline are related to advertising or promoting Indonesian tourism. However, the percentage of tweets with positive sentiment (33.8%) is higher than those with negative sentiment (1.1%). This study also achieved training results with an accuracy rate of 98.5%, precision of 97.6%, recall of 98.5%, and F1-score of 98.1%. However, reassessment is needed in the future as Twitter users' sentiments can change along with the development of Indonesian tourism itself.

Mitigating healthcare supply chain challenges under disaster conditions: a holistic AI-based analysis of social media data

A key advantage of social media is the real-time exchange of views with large communities. In disaster situations, such bidirectional information exchange is most useful to victims and support teams, especially in communications with authorities, volunteers, and the public. This paper addresses challenges faced by the healthcare supply chain during the COVID-19 pandemic with analyses of Twitter data using an Artificial Intelligence-driven multi-step approach. We investigate tweets for information about healthcare supply chains, such as the scarcity of testing kits, oxygen cylinders, and hospital beds during the pandemic. We deployed machine learning to classify such tweets into imperative and non-imperative categories based on need severity. The study sought to predict the location of victims requesting help based on their imperative tweets if geo-tag information was missing. The proposed approach used four steps: (1) keyword-based informative tweet search, (2) raw tweet pre-processing, (3) content analysis to identify tweet trends, public sentiment, topics related to healthcare supply chain challenges, and crisis classification to label imperative and non-imperative tweets, (4) locating the point-of-crisis from imperative tweets to facilitate coordination of help operations. The pre-processing of tweets, trend analysis, and sentiment analysis relied on natural language processing and machine learning for topic modelling (K-mean clustering), crisis classification (random forest), and point-of-crisis detection (Markov chain). Results demonstrate the potential to capture significant, timely, and actionable information on healthcare supply chain challenges to respond quickly and appropriately in a pandemic.

A machine learning approach for detecting customs fraud through unstructured data analysis in social media

Goods and services are sold through social media by individuals not authorized as legitimate dealers, resulting in lost taxes and customs duties to governments. This study proposes a model called SHIELD for detecting these violations through unstructured data in social media. The process involves collecting 2,373,570 records of commercial goods from social media platforms such as Twitter and Facebook in three phases. In Phase 1, keywords for labeling are collected for text classification. Three categories of results are defined: Red Line for smuggled goods, unpaid duty, prohibited goods, and restricted goods; Green Line for non-commercial goods; and Inspect for goods that cannot be identified from the text and require further investigation. Phase 2 and Phase 3 use keywords to detect smugglers from unstructured social media data for labeling grouped by three algorithms of Logistic Regression (LR), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM), employed to classify imported illegal products. The results of all tests show that the LSTM technique had the best accuracy of 99.44% and the best average F1 score of 90.55%. Using algorithms and techniques such as LR, GRU, and LSTM demonstrates the potential of machine learning and natural language processing in detecting illegal activities and promoting economic security.

Disastrous Event and Sub-Event Detection From Microblog Posts Using Bi-Clustering Method

Social media has become a nondetachable part of our life, with the exponential growth of usage in the past decade. Social sites like Twitter, Facebook, Instagram, Flickr, Weibo, etc., with their millions of user base, apart from being a source of entertainment, has proven to be a very useful mean for public opinion generation, news propagation and information broadcasting by authorities. Social media data analysis has been a popular research area for the past few years. Detecting subevents from social media posts to identify an unusual event that requires special attention, especially in a disaster situation, is one of the key researches in this domain. In this article, we have proposed a novel biclustering-based subevent detection method from the Twitter dataset for retrospective analysis of disaster events. First, we have clustered the data matrix using spectral co-clustering. Then we identified subevents (words) and formulated a ranking framework to find the top-ranked subevents within the clusters. Finally, through statistical analysis, we have shown that the proposed framework works better than other existing subevent detection methods.

Social Media Analytics and Business Intelligence: Leveraging Management Information System for Competitive Advantage

In today's ever-evolving business environment, the confluence of social media, analytics, and business intelligence has emerged as a powerful and transformative factor, fundamentally altering the way organizations function and compete. This summary provides an overview of the crucial function that Management Information Systems (MIS) serve in harnessing the potential of social media analytics and business intelligence to attain a competitive edge. The widespread adoption of social media platforms has led to an unprecedented influx of data, offering businesses profound insights into consumer behavior, preferences, and market dynamics. Nonetheless, the sheer scale of this data can be daunting in its raw state. MIS assumes a pivotal role in the collection, processing, and conversion of this data into actionable insights. This research delves into how organizations can effectively employ social media analytics, in synergy with business intelligence tools, to elevate their decision-making processes. Through the analysis of social media data, companies can gain a more profound comprehension of their target audience, keep a close watch on their brand's reputation, and pinpoint emerging trends and market opportunities. Business intelligence tools enable the visualization and interpretation of this data, providing stakeholders with the necessary information to make data-driven decisions. The competitive advantage derived from this approach is multifaceted. It allows organizations to respond proactively to market changes, align their products and services with customer demands, and allocate resources effectively. Furthermore, it enables organizations to optimize marketing campaigns, measure their ROI, and create personalized customer experiences, thereby improving customer satisfaction and loyalty. This study also examines the difficulties and moral factors linked to employing social media analytics and business intelligence. Matters of privacy, data security, and the ethical handling of customer data are pivotal elements that organizations need to confront in order to uphold public confidence and adhere to legal requirements. To sum it up, the amalgamation of social media analytics and business intelligence within the framework of Management Information Systems provides a potent set of tools for organizations striving to gain a competitive edge in the digital era. Leveraging the insights gained from social media data can lead to improved decision-making, enhanced customer experiences, and a sustainable edge in an ever-evolving market. This abstract outline the foundation for a comprehensive study that explores the practical implementation and strategies for harnessing these technologies effectively.

Evaluating random sampling bias in sentiment analysis of social media data

In this age marked by a wealth of information, the relevance of social networks has increased in a manner that is analogous to an exponential growth curve. Notably, the content that is shared on these platforms has the potential to act as a reflection of the emotional states that people are now experiencing. The importance of emotions is brought to light in the research presented here, which makes use of a technique based on a review of the relevant literature to analyze the problem of random sample bias and the effects that it has on sentiment analysis. It is possible to draw the conclusion, on the basis of the findings of the research, that the problem of random sample propensity is not a sporadic or insignificant one. In addition, the findings of the study indicate the presence of multiple types of prejudice. Because of the potential repercussions that could result from doing a distorted sentiment analysis, it is really necessary to keep your method focused.

Social Media as a Tool for Understanding the Role of Motor Differences in Neurodivergent Identity and Lived Experience.

Social media offers an exciting opportunity for the field of motor development and behavior research. With platforms such as Twitter offering access to historical data from users' public bios and posts, there is untapped potential to examine community perspectives on the role of motor differences in identity and lived experience. Analysis of online discourse offers advantages over traditional qualitative methods like structured interviews or focus groups, including a less-contrived setting, global geographic and cultural representation, and ease of sampling. The aim of this special section is to present a pipeline for harvesting and analysis of Twitter data related to users' identities and discourse characteristics, specifically situated in the context of motor development and behavior. This pipeline is demonstrated in two independent studies, one on autistic users and one on developmental coordination disorder (DCD)/dyspraxic users. These studies demonstrate the utility of Twitter data for research on neurodivergent and disabled people's perspectives on their motor differences, and whether they are expressed as part of their identity. Implications of results are discussed for each study, as well as in the larger context of future research using a variety of approaches to analysis of social media data, including those from predominantly image- and video-based platforms.

Utilizing Social Media Data for Estimating Transit Performance Metrics

In this paper, a methodology using text and sentiment analysis of social media data is proposed to determine performance metrics that customers frequently mentioned when riding the New York Transit system and how they compare to those reported by the transit agency. This method is carried out by analyzing Twitter data collected from users mentioning their transit experience and recognizing trends regarding sentiment. The results show that customers mostly express negative over positive experiences about their transit services in terms of perceptions and expectations. Transit users are more critical about wait times and delays and notice the positive factors during service, such as system aesthetics, train speed, station cleanliness, and safety (in that order). The data analyzed also provides insights on locations and transit lines where there are frequent occurrences of customer issues. The proposed methodology provides a relevant contribution from a practical viewpoint because performance metrics are important factors to consider by transit operators which are exploring new practices to retain and attract ridership, given that transit systems are generally considered among the sustainable modes of transportation.

Stock Market Prediction Using Deep Reinforcement Learning

Stock value prediction and trading, a captivating and complex research domain, continues to draw heightened attention. Ensuring profitable returns in stock market investments demands precise and timely decision-making. The evolution of technology has introduced advanced predictive algorithms, reshaping investment strategies. Essential to this transformation is the profound reliance on historical data analysis, driving the automation of decisions, particularly in individual stock contexts. Recent strides in deep reinforcement learning algorithms have emerged as a focal point for researchers, offering promising avenues in stock market predictions. In contrast to prevailing models rooted in artificial neural network (ANN) and long short-term memory (LSTM) algorithms, this study introduces a pioneering approach. By integrating ANN, LSTM, and natural language processing (NLP) techniques with the deep Q network (DQN), this research crafts a novel architecture tailored specifically for stock market prediction. At its core, this innovative framework harnesses the wealth of historical stock data, with a keen focus on gold stocks. Augmented by the insightful analysis of social media data, including platforms such as S&P, Yahoo, NASDAQ, and various gold market-related channels, this study gains depth and comprehensiveness. The predictive prowess of the developed model is exemplified in its ability to forecast the opening stock value for the subsequent day, a feat validated across exhaustive datasets. Through rigorous comparative analysis against benchmark algorithms, the research spotlights the unparalleled accuracy and efficacy of the proposed combined algorithmic architecture. This study not only presents a compelling demonstration of predictive analytics but also engages in critical analysis, illuminating the intricate dynamics of the stock market. Ultimately, this research contributes valuable insights and sets new horizons in the realm of stock market predictions.

A Critical Review of the Effectiveness of Machine Learning & Deep Learning Approaches in Forecasting Stock Market Trends

For a long time, traders as well as researchers have been actively interested in financial market forecasting. A financial market prediction has an interest for investors & researchers since long time. An existing method for predicting stock prices often rely on technical and fundamental analysis, which have limitations in handling the complexity and volume of financial data. To handle complex data sets for forecasting the value of stock using new emerging learning techniques. The most commonly used approach such as artificial neural networks (ANN), neural network techniques, SVM, decision trees algorithm, and random forests. These techniques can capture complex nonlinear relationships between variables and adjust to changing market conditions. The machine learning & deep learning analyze the trend for the future values of stock prediction and provides observation for making decision. The importance of feature selection and data preprocessing are used for improving the prediction accuracy of stock value. The genetic method feature selection concept can reduce the dimensionality of the data and remove irrelevant features, while data preprocessing techniques such as normalization and scaling can improve the stability and convergence of the algorithms. Sentiment analysis of social media data can capture market sentiment and investor behavior, while news articles can provide insights into company performance and industry trends. The accuracy of predictions tends to decrease as the prediction horizon increases and the prediction accuracy varies across different stock markets. A lot of significant work, the most recent stock market-related prediction system includes multiple limitations. Now the conclusion, the projection of stock markets is a hybrid approach & certain parameters for stock market forecasting should be as accurate as possible.

What are the general public’s needs, concerns and views about energy efficiency retrofitting of existing building stock? A sentiment analysis of social media data

Energy efficiency retrofitting of existing buildings (EEREB) is critical to combating climate change. While policy interventions that seek to encourage widespread EEREB adoption benefit from a deeper understanding of public retrofit decision behaviour, studies that comprehensively evaluate the general public’s sentiments towards EEREB are lacking, contributing to a lack of understanding of the public’s needs, concerns and views. This study aims to evaluate the general public’s needs, concerns and views about EEREB. A total of 3,306 data of the general public’s views were collected from the social media platform YouTube, pre-processed and analyzed using the Model-based clustering and a text mining technique. Results showed nine areas of public concerns: ventilation, energy efficiency, indoor environment quality, comfort and occupant behaviour, cost involved, community engagement, technology use, implementation knowledge, and social impact. The general intention to retrofit is mostly driven by personal choices, not regulations per se, although some climate-dependant factors strongly impact public sentiments. Moreover, the recognition of benefits and public support for EEREB was attached to the understanding of cost saving and payback period and finding reliable supply-side actors for retrofit works, respectively. Overall, the public reported positive sentiments (56%) toward EEREB. Novel insights into the general public’s needs, concerns and views have been uncovered in this study, which policymakers can utilize to better advocate for EEREB.

Social Media Data Analysis: A Focus on the Government–Citizen Dynamic

Social Media Data Analysis: A Focus on the Government–Citizen Dynamic