Analysis Of Social Data Research Articles

Efficient graph-based event detection scheme on social media

As various opinions and thoughts of users are shared on social media, various events can be detected through social media data analysis. The graph-based event detection scheme may eliminate event duplication detection by clustering words related to an event. In this paper, we propose a graph-based event detection scheme for detecting various events in the real world through social media analysis. The proposed scheme expresses the simultaneous occurrence of words mentioned with an event in graph form. Therefore, it can convey the information about the detected event and avoid duplicate detection. A keyword graph is constructed and keywords related to an event are clustered by analyzing the collected social data. By considering user interest calculated through changes in social activities of users on social media, the proposed scheme can detect event results that receive more responses from users and improve the reliability of the results by excluding indiscriminate advertisements or malicious posts from the results. We assign a weight to the generated keyword graph by considering user interest and calculate an event detection coefficient to determine the event values of the candidate event graphs. We perform various evaluations to demonstrate the superiority of the proposed scheme.

Pelatihan Strategi Menarik Konsumen Melalui Konten Media Sosial pada Pelaku Usaha

Social media content strategy training has become a necessity for business owners in the rapidly evolving digital era. The aim of this training is to help business owners understand more effective ways to promote their products or services through social media. In Mataram, this training has had a positive impact on business owners. During the training, participants are taught how to create content that is engaging and relevant to their target market. In addition, the training also helps business owners understand social media data analysis, so they can measure the effectiveness of their campaigns and make more informed decisions in their marketing strategies. As a result of this training, business owners in Mataram can expand their market reach, increase brand awareness, and boost sales. However, it should be noted that this training is not an instant solution to all marketing problems. It takes time and effort to build a strong and consistent online presence, as well as continuously updating marketing strategies to keep up with changing trends and market needs.

Public opinion about Finland joining NATO: analysing Twitter posts by performing natural language processing

ABSTRACT The announcement of Finland’s decision to join NATO in May 2022 has provoked many public discussions and debates both inside and outside Finland. The aim of this study is to process natural language in Twitter data collected between 12 May and 3 April 2023 and to analyse the public sentiment on Finland’s decision to join NATO. A total of 28,993 tweets were collected and analysed using the VADER algorithm for sentiment analysis and the LDA algorithm for topic modelling. The results show that overall sentiment towards Finland’s NATO membership was mostly positive. Topic modelling revealed that the most prevalent topics of the tweets were related to Finland’s alliances, concerns, and general opinions of the NATO membership. The results suggest that the public discussion on Twitter focuses on the potential benefits and risks of Finland’s decision to join NATO, especially considering the recent tensions with Russia. The study provides insights into public opinion about Finland’s NATO membership and highlights the potential of natural language processing techniques for the analysis of social media data. These findings could help in further policy discussions about Finland joining NATO and provide a basis for further research into public opinion on NATO and other international organizations.

Integrated analysis of online signals and insight generation about digital conversations on COVID-19 vaccines in Eastern and Southern Africa: a longitudinal analysis of social listening data

BackgroundDuring the COVID-19 pandemic, social listening programs across digital channels have become an integral part of health preparedness and response planning, allowing to capture and address questions, information needs, and misinformation shared by users. This study identifies key social listening trends around COVID-19 vaccines in Eastern and Southern Africa and analyses how online conversations about this issue evolved over time.MethodsA taxonomy developed and refined in collaboration with social and behaviour change teams was used to filter online conversations into nine subtopic categories. The taxonomy was applied to online content tracked in 21 countries in Eastern and Southern Africa over the period December 1, 2020—December 31, 2021. Metrics captured included volume of posts or articles and related user engagement. Qualitative analysis of content was conducted to identify key concerns, information voids and misinformation.ResultsOver 300,000 articles and posts about COVID-19 vaccines shared by users or outlets geolocated in the region were analysed. These results generated over 14 million engagements on social media and digital platforms. The analysis shows how conversations about access and availability of vaccines represented the largest share of engagement over the course of the period. Conversations about vaccine effectiveness and safety represented the second and third largest share of engagement, with peaks observed in August and November 2021. Online interest in childhood vaccination increased over time as vaccine eligibility criteria expanded in some countries in the region. Conversations mentioning mandates and certificates peaked in the last quarter of 2021, as governments as private sector entities expanded vaccine requirements.ConclusionsFindings from this study show the importance of monitoring conversation trends over time and adjust social listening data collection systems to include emerging topics. The study also points to the need to consider concerns, information voids and misinformation around effectiveness and safety of vaccines in the context of overall concern for vaccine availability and access in Eastern and Southern Africa. This is fundamental to inform social and behaviour change strategies that promote vaccine demand effectively, without increasing public frustration over vaccine availability challenges and downplaying concerns around vaccine equity.

Practical Technologies for Analysis, Recommendation, and Visualization of User Behavior and Social Environment Data

Practical Technologies for Analysis, Recommendation, and Visualization of User Behavior and Social Environment Data

중국 소셜미디어 빅데이터 분석을 통한 NFT 가상패션의 담론과 디자인 표현 특성 연구

This study aims to analyze the discourse and design characteristics of ‘NFT virtual fashion’ through social media big data analysis. Data was collected using the keyword ‘NFT virtual fashion’ from Textom China, and the discourse of NFT virtual fashion was analyzed using CONCOR analysis. Cluster analysis was employed to examine the design characteristics of NFT virtual fashion. Four discourse groups emerged from the CONCOR analysis: Group 1 discussed the trends in NFT virtual fashion brands and its development, Group 2 explored the experiences and creation of NFT virtual fashion, Group 3 examined the market and investment trends of NFT virtual fashion in the fashion industry, while Group 4 focused on the subscribers desires and the presence of the sportswear brand Nike in NFT virtual fashion. Furthermore, eight design clusters were identified through cluster analysis, namely: Cluster 1 - ‘Boldness’, Cluster 2 - ‘Collaboration and High Quality’, Cluster 3 - ‘Artistry and Virtuality’, Cluster 4 - ‘Exaggeration and Technological Elements’, Cluster 5 - ‘Environmental Friendliness and Non-standardization’, Cluster6 - ‘Aesthetics and Interactivity’, Cluster 7 - ‘Non-contact’, and Cluster 8 - ‘Boundarylessness’. Finally, insights were drawn from the analysis of the discourse and design characteristics of NFT virtual fashion.

The Social Media Big Data Analysis for Demand Forecasting in the Context of Globalization

This paper aims to analyze the predictive effect of artificial intelligence on user demand in big data social media and to provide suggestions for developing enterprise innovation frameworks and implementing marketing strategies. In response to the inconsistency between the supply of enterprise products and services and market demand, deep learning algorithms have been introduced using social media big data analysis. This algorithm has been improved to construct a user demand prediction model in social media big data based on bidirectional long short-term memory (BiLSTM) fused with Word2Vec. The model uses data acquisition and pre-processing, Word2Vec algorithm to vectorization the data information, and BiLSTM network to model and train the sequence. Finally, the model is evaluated as an example.

An Investigation of Suicidal Ideation from Social Media Using Machine Learning Approach

Despite improvements in the detection and treatment of severe mental disorders, suicide remains a significant public health concern. Suicide prevention and control initiatives can benefit greatly from a thorough comprehension and foreseeability of suicide patterns. Understanding suicide patterns, especially through social media data analysis, can help in suicide prevention and control efforts. The objective of this study is to evaluate predictors of suicidal behavior in humans using machine learning. It is crucial to create a machine learning model for detection of suicide thoughts by monitoring a user's social media posts to identify warning signs of mental health issues. Through the analysis of social media posts, our research intends to develop a machine learning model for identifying suicide ideation and probable mental health problems. This study will help immensely to comprehend the environmental risk factors that influence suicidal thoughts and conduct across time. In this research the use of machine learning on social media data is an exciting new direction for understanding the environmental risk factors that impact an individual's susceptibility to suicide ideation and conduct over time. The machine learning algorithms showed high accuracy, precision, recall, and F1-score in detecting suicide patterns on social media data whereas SVM has the highest performance with an accuracy of 0.886.

Twitter Data Analysis and Text Normalization in Collecting Standard Word

is one of the most important data sources in social data analysis. However, the text contained on Twitter is often unstructured, resulting in difficulties in collecting standard words. Therefore, in this research, we analyze Twitter data and normalize text to produce standard words that can be used in social data analysis. The purpose of this research is to improve the quality of data collection on standard words on social media from Twitter and facilitate the analysis of social data that is more accurate and valid. The method used is natural language processing techniques using classification algorithms and text normalization techniques. The result of this study is a set of standard words that can be used for social data analysis with a total of 11430 words, then 4075 words with structural or formal words and 7355 informal words. Informal words are corrected by trusted sources to create a corpus of formal and informal words obtained from social media tweet data @fullSenyum. The contribution to this research is that the method developed can improve the quality of social data collection from Twitter by ensuring the words used are standard and accurate and the text normalization method used in this study can be used as a reference for text normalization in other social data, thus facilitating collection. and better-quality social data analysis. This research can assist researchers or practitioners in understanding natural language processing techniques and their application in social data analysis. This research is expected to assist in collecting social data more effectively and efficiently.

Using Social Media Camping Data for Evaluating, Quantifying, and Understanding Recreational Ecosystem Services in Post-COVID-19 Megacities: A Case Study from Beijing

Recreational ecosystem services (RESs) are the diverse recreational opportunities provided by nature to humans, which contribute to the improvement of public health and social well-being. The use of online social media is an efficient method for quantifying public perceptions of recreational ecosystem services (RESs) delivered by a given landscape. With the continuously changing demand for nature-focused outdoor recreational activities since COVID-19, camping has become the fastest-growing outdoor leisure activity in megacities and a key indicator for how people perceive and value the RESs provided by the landscape. Such unexpected changings triggered by COVID-19 have further led to an imbalance between demand and supply, which results in fierce conflicts in urban green space management. This study presents a spatial pattern analysis of how people perceive RESs in a megacity-scale case study of Beijing using geo-tagged camping notes posted on Little Red Book (LRB). We employed these camping notes in the context of a megacity to (i) map public camping behaviors patterns in urban green spaces, (ii) evaluate spatial clusters of high/low RESs, and (iii) investigate the relationship between RESs, local landscape features, and gender through correspondence analysis. Our results show that considerable spatial clustering of camping behaviors was observed in both suburban and urban green spaces. However, suburbs revealed a substantially higher RES value than central urban areas. In addition, water bodies were discovered to have remarkably low RES, while grassland and urban forests were found to have a close link with higher RES. In addition, significant gender preferences have been discovered, where female visitors prefer to camp in grassland, and male visitors favor bare ground and urbanized regions. Our findings would assist decision-makers in optimizing urban green space planning and management, adapting to fast-changing public camping demands in the context of the post-COVID-19 era. Findings also contribute to the literature by applying spatial analysis of social media data to understand public outdoor recreation activities and perceived value for megacities’ green space management.

Contextualizing Online Conversational Networks

Online social connections occur within a specific conversational context. Prior work in network analysis of social media data attempts to contextualize data through filtering. We propose a method of contextualizing online conversational connections automatically and illustrate this method with Twitter data. Specifically, we detail a graph neural network model capable of representing tweets in a vector space based on their text, hashtags, URLs, and neighboring tweets. Once tweets are represented, clusters of tweets uncover conversational contexts. We apply our method to a dataset with 4.5 million tweets discussing the 2020 US election. We find that even filtered data contains many different conversational contexts, with users engaging in multiple conversations. While users engage in multiple conversations, the overlap between any two pairs of conversations tends to be only 30-40%, giving very different networks for different conversations. Even accounting for this variation, we show that the relative social status of users varies considerably across contexts, with tau=0.472 on average. Our findings imply that standard network analysis on social media data can be unreliable in the face of multiple conversational contexts.

A Neural-Based Approach for Detecting the Situational Information from Twitter During Disaster

Each day, vast quantities of social media data is being produced and consumed in a constantly increasing price. A user’s digital footprint coming from internet sites or mobile products, such as comments, check-ins and Location traces contains valuable details about her behavior under normal and also emergency conditions. The collection and analysis of cellular and social media data before, during and after a tragedy opens new perspectives in areas such as for example real-time event detection, Emergency administration and personalization and valuable insights about the degree of the disaster, it is effect on the affected population and the rate of disaster recovery. Traditional storage space and processing systems cannot cope with how big is the collected data and the complexity of the applied analysis, thus distributed approaches are generally employed. In this function, we propose an open-source distributed platform that may serve while a backend for applications and solutions related to Emergency detection and administration by combining spatio-textual consumer generated data. The machine targets scalability and uses combination of state-of-the artwork Big Data frameworks. It presently supports the most popular internet sites, being easily extensible to any social system. The experimental evaluation of our prototype attests its overall performance and scalability even under large load, using different query types more than various cluster sizes.

Report on the 8th International Workshop on Mining Actionable Insights from Social Networks (MAISoN'22) - Special Edition on Mental Health and Social Media at TheWebConf 2022

The eighth edition of the workshop on Mining Actionable Insights from Social Networks (MAISoN 2022) took place virtually on April 26th, 2022, co-located with the ACM Web Conference 2022 (TheWebConf 2022). This year, we organized a special edition with focus on mental health and social media. The aim of this edition was to bring together researchers from different disciplines to discuss research that goes beyond descriptive analysis of social media data and instead investigate different techniques that use social media data for building diagnostic, predictive and prescriptive analysis models for mental health applications. This topic attracted a lot of interest from the community especially because of all the considerations surrounding the impact of social media during the COVID-19 pandemic which has impacted on people's mental health issues. Date: 26 April 2022. Website: https://2022.maisonworkshop.org/.

ІНТЕЛЕКТУАЛЬНИЙ АНАЛІЗ ВЕБКОНТЕНТУ ДЛЯ ФОРМУВАННЯ СОЦІАЛЬНО-ЦИФРОВОЇ ІДЕНТИЧНОСТІ ВЕБКОРИСТУВАЧА

The article discusses the growing need to analyze and understand web user behavior due to the unprecedented amount of digital content being generated and distributed on the Internet. Web content intelligence is presented as an effective way to explore and extract valuable information from online content, including websites, social media platforms, and other digital sources, to better understand web users' interests, preferences, and behaviors. The ability to identify web users based on their online behavior is important for industries such as marketing, psychology, and law enforcement. However, there are certain problems associated with this approach, such as ensuring the privacy and security of web users’ data, as well as assessing the accuracy and reliability of web content analysis tools. The purpose of the article is to review the current state of web content analysis, its potential applications in various industries, and its role in shaping the digital future. The article emphasizes the importance of an interdisciplinary approach to the study of virtual identification and self-presentation in online communities, taking into account the socio-demographic characteristics of a web personality involved in social interactions. The article also explores the latest trends and developments in the field of web data mining, including web content analysis, web structure analysis, web page usage analysis, and social media data analysis. A software solution for conducting intelligent analysis of web content is proposed to form a social and digital identity of a web user using a specialized dictionary of content markers of a web community member.

Application of the sustainable system-of-systems approach and econometric analysis to address China’s decarbonisation problem

The Sustainable system-of-systems (SSoS) approach, complemented with econometric analysis was used to address China’s decarbonisation problem, i.e. selecting fossil fuel consumption sources to be reduced in various regions to meet CO2 reduction targets with minimal effect on population and economic growth. In the SSoS, the micro-level system is represented by residents’ health expenditure, the meso-level system by industry’s CO2 emissions intensity, and the macro-level system by the government’s achievement of economic growth. Regional panel data from 2009 to 2019 were used in an econometric analysis conducted using structural equation modelling. The results show that health expenditure was affected by CO2 emissions from the consumption of raw coal and natural gas. To support economic growth, the government should reduce raw coal consumption. For CO2 emissions reduction, industry in the eastern region should reduce raw coal consumption. The key advantage is SSoS with econometrics offers a way to reach a common goal among stakeholders. Practitioner summary: This research shows that the use of the SSoS approach, complemented with an econometric analysis of key social, economic, and natural capital data, can address a complex decarbonisation problem facing a nation (China, in the present case) while considering the goals of all stakeholders (the government, industrial communities, and residential communities). Abbreviations: CEADs: Carbon Emissions Accounts and Datasets for Emerging Countries; CEIC: CEIC Global Database; GRPS: World Economic Forum’s Global Risks Perception Survey; HFE: human factors/ergonomics; ML-SEM: maximum likelihood estimation method; NDRC: National Development and Reform Commission of China; SEM: structural equation modelling; SSoS: Sustainable system-of-systems; TBL: triple bottom line

Sustainability of mining companies - analysis of social data as a scientific activity of Students

The main objective of the article is analyzing non-financial data of mining companies. The research part consists of an analysis of secondary data from the “social” domain, collected by the students from Faculty of Geoengineering, Mining and Geology Wrocław University of Science and Technology and organized according to the adopted criterion. The source of data were public reports of 8 mining entities. Social data were presented in relation to the selected information regarding corporate governance. The elaborated summary was used to present the tendency in the way of reporting non-financial data for the selected research group. At the same time, the aim of the work carried out is to reveal the potential of the group of students while combining the didactic process with scientific development during the process of creating the manuscript. The experimental approach to teaching by cooperating and the attempt to implement the perception of students as partners in higher education is a unique voluntary project at the Faculty of Geoengineering, Mining, and Geology.

Investigating the Relative Influence of Romantic Sex Partners and Close Friends on Adolescent Alcohol and Marijuana Use.

A large body of research has identified peer exposure as a key factor driving adolescent substance use. However, findings on the role of sex partners are less robust and mixed. This study aims to fill this gap by examining the independent contribution of close friends' and sex partners' alcohol and marijuana use on adolescents' use of these substances. A secondary data analysis of social network data collected in 2000-2002 from a household sample of African American youth (14-19years old) in the Bayview and Hunter's Point neighborhoods of San Francisco was conducted. Index participants and their nominated close friends and romantic sex partners (N = 104 triads) self-reported recent alcohol and marijuana use (defined as any use in the past 3months). Generalized estimated equations were used to estimate the independent association between adolescent's recent substance use and their friend's and sex partner's use. Adolescents with a marijuana-using romantic sex partner had a nearly six-fold higher odds of using marijuana compared to adolescents with a non-using partner, controlling for close friend's marijuana use and other confounders [OR:5.69, 95%CI: 1.94, 16.7]; no association with close friend's marijuana use was found. A similar pattern was observed for alcohol use. Adolescents with an alcohol-using romantic sex partner had increased odds of using alcohol compared to adolescents with a non-using partner, controlling for close friend's alcohol use and other confounders [OR:2.40, 95%CI: 1.02, 5.63]; no association with close friend's alcohol use was found. Romantic sex partners may play a unique and significant role in adolescent substance use. Peer-focused interventions may be more effective if they consider romantic sex partners. Future research should consider the role of romantic sex partners in changing social context related to substance use from adolescence to young adulthood.

A Review of Social Media Data Utilization for the Prediction of Disease Outbreaks and Understanding Public Perception

Infectious diseases take a large toll on the global population, not only through risks of illness but also through economic burdens and lifestyle changes. With both emerging and re-emerging infectious diseases increasing in number, mitigating the consequences of these diseases is a growing concern. The following review discusses how social media data, with a focus on textual Twitter data, can be collected and processed to perform disease surveillance and understand the public’s attitude toward policies around the control of emerging infectious diseases. In this paper, we review machine learning tools and approaches that were used to determine the correlation between social media activity in disease trends within regions, understand the public’s opinion, or public health leaders’ approaches to disease presentation. While recent models migrated toward popular deep learning methods, neural networks and algorithms that optimized existing models were also explored as new standards for social media data analysis in disease prediction and monitoring. As adherence to public health policies can be improved by understanding and responding to major concerns identified by sentiment analyses, the advancements and challenges in understanding text sentiment are also discussed. Recent sentiment classifiers include more complex classifications and can even recognize epidemiological considerations that affect the spread of outbreaks. The comprehensive integration of locational and epidemiological considerations with advanced modeling capabilities and sentiment analysis will produce robust models and more precision for both disease monitoring and prediction. Accurate real-time disease outbreak prediction models will provide health organizations with the capability to address public concerns and to initiate outbreak responses proactively rather than reactively.

Influence and Improvisation: Participatory Disinformation during the 2020 US Election

The 2020 US election was accompanied by an effort to spread a false meta-narrative of widespread voter fraud. This meta-narrative took hold among a substantial portion of the US population, undermining trust in election procedures and results, and eventually motivating the events of 6 January 2021. We examine this effort as a domestic and participatory disinformation campaign in which a variety of influencers—including hyperpartisan media and political operatives—worked alongside ordinary people to produce and amplify misleading claims, often unwittingly. To better understand the nature of participatory disinformation, we examine three cases of misleading claims of voter fraud, applying an interpretive, mixed method approach to the analysis of social media data. Contrary to a prevailing view of such campaigns as coordinated and/or elite-driven efforts, this work reveals a more hybrid form, demonstrating both top-down and bottom-up dynamics that are more akin to cultivation and improvisation.

Big social data analysis for impact of food quality on travelers’ satisfaction in eco-friendly hotels

Revealing customer satisfaction through big social data has been an interesting research topic in tourism and hospitality. Big data analysis is an effective way to detect customers’ behaviors in their decision-making. This study aims to perform big social data analysis to reveal whether food quality impacts the relationship between hotel performance criteria and travelers’ satisfaction. A two-stage methodology is developed to address the objectives of this study. The findings demonstrated that there is a positive relationship between eco-friendly hotels’ performance criteria and satisfaction. The results and implications for managers and future research directions are discussed.