Analysis Of Social Data Research Articles

A Systematic Review Towards Big Data Analytics in Social Media

The recent advancement in internet 2.0 creates a scope to connect people worldwide using society 2.0 and web 2.0 technologies. This new era allows the consumer to directly connect with other individuals, business corporations, and the government. People are open to sharing opinions, views, and ideas on any topic in different formats out loud. This creates the opportunity to make the “Big Social Data” handy by implementing machine learning approaches and social data analytics. This study offers an overview of recent works in social media, data science, and machine learning to gain a wide perspective on social media big data analytics. We explain why social media data are significant elements of the improved data-driven decision-making process. We propose and build the “Sunflower Model of Big Data” to define big data and bring it up to date with technology by combining 5 V's and 10 Bigs. We discover the top ten social data analytics to work in the domain of social media platforms. A comprehensive list of relevant statistical/machine learning methods to implement each of these big data analytics is discussed in this work. “Text Analytics” is the most used analytics in social data analysis to date. We create a taxonomy on social media analytics to meet the need and provide a clear understanding. Tools, techniques, and supporting data type are also discussed in this research work. As a result, researchers will have an easier time deciding which social data analytics would best suit their needs.

DASSL “Data Access Sharing Storage & Linkage” Proof-of-Concept: Health and Related Data Linkage in Ireland.

ObjectiveThe DASSL Model, conceived by the Health Research Board, aims to overcome challenges to linking data in Ireland including lack of unique patient identifiers, inconsistent application of legislation and siloed data. The objective of the Proof-of-Concept is to develop and test a demonstrator technical infrastructure to support this model. ApproachA stakeholder committee of representatives from government, health services, data controllers, patients/public and researchers was established. National and international data sharing and linkage landscapes were reviewed via interviews, scientific papers and grey literature. Five case studies were developed to demonstrate different linkages, data and research purposes, with synthetic data mimicking real health/social datasets generated using data dictionaries, data controller input, national statistics and Synthpop, Synthetic Data Vault and General Adversarial Networks. The technical infrastructure remains under development with linkage software being evaluated. Stakeholders will test this infrastructure and a final report will outline considerations for a national solution. ResultsSynthetic versions of administrative data, patient registries, electronic patient records, longitudinal cohorts, imaging and genomics are being generated. Matching variables and content data will be split and securely shared respectively with the Trusted Third Party (TTP) and Health Data Hub (HDH) on a project-by-project basis and at regular intervals. The selected linkage software will be used to match both unique identifiers and personally-identifiable data using probabilistic and deterministic techniques between datasets and with a population spine. The encrypted linkage key will be shared with the HDH, where the data view for each case study will be created by the Research Support Unit using the content data. A locked down virtual Safe Haven will support researcher access with disclosure control check on any outputs. ConclusionA DASSL infrastructure could support sharing, linking and analysis of health and social data in Ireland. However, high quality data including matching variables need to be collected to produce beneficial findings. A national rollout requires a governance and legislative model, improvements in data collection, further public engagement and significant resourcing.

Analysing community reaction to refugees through text analysis of social media data

ABSTRACT Understanding the social integration of refugees requires scholars and community leaders to understand the complex and varied political reaction of citizens to the prospect and reality of refugees entering their local communities. In this study, we apply the Structural Topic Model (STM) to characterise citizen-level discourse in comments posted in response to refugee-related news articles on Facebook in Lancaster, Pennsylvania, and Roanoke, Virginia, two cities with similar demographics and conservative partisanship, but sharply contrasting refugee-related policies and experiences. We find that, overall, commenters framed their arguments with an identity-based frame more often than economics, morality, security or legality frames, but that these tended to be blended in ways that obscure the basis in identity. We also find that comments within the discourse of the more refugee-experienced Lancaster community were more likely to involve substantive arguments than in Roanoke, more likely to use economics frames, less likely to use identity frames, less likely to involve incivility and less likely to feature a salient misinformation-influenced theme (refugees vs. homeless veterans). This suggests that host community discourse grows more substantive and positive as a function of hospitable refugee policies and refugee hosting experience, and we discuss how this research might be expanded beyond this pair of cases to evaluate this broader implication.

Application of the Deep Pretrained Language Model Processing Method in Social Network Sentiment Analysis

In social network, users can manage their social network and social identity, publish information on various topics, and obtain information published by other users through friend relationship. The resulting large amount of text data attract more and more scholars to study it. Text sentiment analysis has become a hot spot in social network data analysis and has important application value in academic field, social field, and business field. Based on the idea of pre-training, this paper improves the random word masking algorithm of deep pretraining task in the BERT (Bidirectional Encoder Representation) model to improve the efficiency and stability of model pretraining. Second, a new pretraining task of original sentence judgment is designed to enable the model to measure the degree of sentence smoothness, so that the BERT model can better understand the semantics of context. By referring to the idea of attention mechanism, a deep learning framework with attention weight added into gated convolution is constructed and the special attention weight method is adopted to enhance semantic information. Second, gating convolution and attention mechanism are combined to model aspect-related semantic information and text complete semantic information. Finally, classify the emotion classifier layer of social network, use Softmax function to complete negative, positive, and neutral multiple classifications and calculate the result of emotion classification. By applying the optimized convolutional neural network cyclic optimization network to single task and multitask in practice, the feasibility of applying the optimized convolutional neural network and cyclic neural network to social network sentiment analysis is verified.

Evolving norms: social media data analysis on parks and greenspaces perception changes before and after the COVID 19 pandemic using a machine learning approach

This study provides a novel approach to understand human perception changes in their experiences of and interactions with public greenspaces during the early months of COVID-19. Using social media data and machine learning techniques, the study delivers new understandings of how people began to feel differently about their experiences compared to pre-COVID times. The study illuminates a renewed appreciation of nature as well as an emerging but prominent pattern of emotional and spiritual experiences expressed through a social media platform. Given that most park and recreational studies have almost exclusively examined whether park use increased or decreased during the pandemic, this research provides meaningful implications beyond the simple extensional visit pattern and lends weight to the growing evidences on changing perceptions over and the positive psychological impacts of nature. The study highlights the preeminent roles parks and greenspaces play during the pandemic and guides a new direction in future park development to support more natural elements and nature-oriented experiences from which emotional and spiritual well-being outcomes can be drawn.

A New Perspective of Sustainable Perception: Research on the Smellscape of Urban Block Space

The smell of space is inseparable from the sustainable development of the living environment. The research on olfactory perception and smell landscape has a positive effect on landscape design and urban planning and contributes to the formation and design optimization of unique urban memory. This study combines urban smell tracking experiments with Internet social media data analysis to classify smells in the old city center of Guangzhou, China, and analyzes the study within the inner ring and six historic districts. Based on the research results, the smell map was drawn, and the reliability of the smell map was tested through social data and semantic analysis. The emotional score heat map of smell and emotion in six regions was constructed, highlighting the impact of smell in key neighborhoods on the environment. In the conclusion to the study, the thematic routes of green urban design are proposed: sightseeing routes, cultural routes, and food routes, as well as improvement strategies to promote the integration of smell and urban operation activities and the sustainable development of urban regional characteristics.

The Impact of Mortality Salience, Negative Emotions and Cultural Values on Suicidal Ideation in COVID-19: A Conditional Process Model.

As suicides incurred by the COVID-19 outbreak keep happening in many countries, researchers have raised concerns that the ongoing pandemic may lead to “a wave of suicides” in society. Suicidal ideation (SI) is a critical factor in conducting suicide intervention and also an important indicator for measuring people’s mental health. Therefore, it is vital to identify the influencing factors of suicidal ideation and its psychological mechanism during the outbreak. Based on the terror management theory, in the present study we conducted a social media big data analysis to explore the joint effects of mortality salience (MS), negative emotions (NE), and cultural values on suicidal ideation in 337 regions on the Chinese mainland. The findings showed that (1) mortality salience was a positive predictor of suicidal ideation, with negative emotions acting as a mediator; (2) individualism was a positive moderator in the first half-path of the mediation model; (3) collectivism was a negative moderator in the first half-path of the mediation model. Our findings not only expand the application of the terror management theory in suicide intervention but provide some insights into post-pandemic mental healthcare. Timely efforts are needed to provide psychological interventions and counseling on outbreak-caused negative emotions in society. Compared with people living in collectivism-prevailing regions, those living in individualism-prevailing regions may be more vulnerable to mortality salience and negative emotions and need more social attention.

A Hybrid Method for Customer Segmentation in Saudi Arabia Restaurants Using Clustering, Neural Networks and Optimization Learning Techniques.

Dining out is one of the biggest expenditures for travelers worldwide and is essential for tourism-dependent destinations. Market segmentation gives industries the potential to classify similar customers and categorize their preferred target markets to ensure marketing expenses' operative management. It has been a practical approach for business improvement in tourism and hospitality. Big data are fundamentally changing the management of the hospitality sector and the relationship between the customer and business by simplifying the decision-making process based on large amounts of data. The data provided in social media have played an important role in customer segmentation. In fact, the data provided by the customers in social media have been a valuable source for decision-makers to precisely discover the customers' satisfaction dimensions on their services. Therefore, there is a need for the development of data-driven approaches for social data analysis for customers segmentation. This research aims to develop a new data-driven approach to reveal customers' satisfaction in restaurants. Specifically, k-means and Artificial Neural Network (ANN) with the aid of the Particle Swarm Optimization (PSO) technique are, respectively, used in data clustering and prediction tasks. In this research, the data of customers on the service quality of restaurants are collected from the TripAdvisor platform. The results of the data analysis are provided. We evaluate the prediction model through a set of evaluation metrics, Mean Squared Error (MSE) and coefficient of determination (R2), compared with the other prediction approaches. The results showed that k-means-PSO-ANN (MSE = 0.09847; R2 = 0.98764) has outperformed other methods. The current study demonstrates that the use of online review data for customer segmentation can be an effective way in the restaurant industry in relation to the traditional data analysis approaches.

Sentiment analysis of COVID-19 social media data through machine learning.

Pandemics are a severe threat to lives in the universe and our universe encounters several pandemics till now. COVID-19 is one of them, which is a viral infectious disease that increased morbidity and mortality worldwide. This has a negative impact on countries’ economies, as well as social and political concerns throughout the world. The growths of social media have witnessed much pandemic-related news and are shared by many groups of people. This social media news was also helpful to analyze the effects of the pandemic clearly. Twitter is one of the social media networks where people shared COVID-19 related news in a wider range. Meanwhile, several approaches have been proposed to analyze the COVID-19 related sentimental analysis. To enhance the accuracy of sentimental analysis, we have proposed a novel approach known as Sentimental Analysis of Twitter social media Data (SATD). Our proposed method is based on five different machine learning models such as Logistic Regression, Random Forest Classifier, Multinomial NB Classifier, Support Vector Machine, and Decision Tree Classifier. These five classifiers possess various advantages and hence the proposed approach effectively classifies the tweets from the Twint. Experimental analyses are made and these classifier models are used to calculate different values such as precision, recall, f1-score, and support. Moreover, the results are also represented as a confusion matrix, accuracy, precision, and receiver operating characteristic (ROC) graphs. From the experimental and discussion section, it is obtained that the accuracy of our proposed classifier model is high.

Deep learning based topic and sentiment analysis: COVID19 information seeking on social media

Social media platforms have become a common place for information exchange among their users. People leave traces of their emotions via text expressions. A systematic collection, analysis, and interpretation of social media data across time and space can give insights into local outbreaks, mental health, and social issues. Such timely insights can help in developing strategies and resources with an appropriate and efficient response. This study analysed a large Spatio-temporal tweet dataset of the Australian sphere related to COVID19. The methodology included a volume analysis, topic modelling, sentiment detection, and semantic brand score to obtain an insight into the COVID19 pandemic outbreak and public discussion in different states and cities of Australia over time. The obtained insights are compared with independently observed phenomena such as government-reported instances.

Preterm birth: the impact of risk factors on pregnancy outcomes

BACKGROUND: Despite the achievements of modern obstetrics and neonatology, the problem of preterm birth remains one of the most pressing.
 AIM: The aim of this study was to evaluate the influence of risk factors on the outcome of threatened preterm birth.
 MATERIALS AND METHODS: This prospective cohort study included the analysis of clinical and anamnestic data of 130 patients delivered at various gestational ages. The main group comprised 68 women with preterm delivery, with the control group consisting of 62 women with timely delivery.
 RESULTS: The outcome of preterm birth is adversely affected by overweight in the group of modifiable risk factors, by history of premature birth in the immediate family in the group of non-modifiable risk factors, and by a previous COVID-19, anemia and autonomic nervous system disorders in the group of potentially modifiable risk factors. The most reliable prognostic marker for the development of preterm labor was the shortening of the cervical length of less than 2.5 cm according to ultrasound.
 CONCLUSIONS: The formation of risk groups based on the analysis of clinical, anamnestic, medical, and social data, as well as somatic and gynecological diseases can help avoid the development of adverse outcomes of preterm birth.

The economic limits of empathy? Analysing variation in the attitudes of oppressed minority groups towards refugees

ABSTRACT How do group characteristics differentially moderate attitudes towards refugees on humanitarian, sociocultural, and economic issues? Building on recent research on group empathy and perspective-taking, we argue that oppressed minority groups will display more positive attitudes towards refugees than dominant majority groups due to empathy triggered by a shared experience of oppression. However, there are economic limits of empathy. Specifically, the empathetic response will not extend to attitudes regarding the economic impact of refugees due to the perceived zero-sum nature of economic competition. Analysis of granular data in Turkey supports the argument, with Kurds (i.e. oppressed group) displaying more positive attitudes on sociocultural and humanitarian issues but not economic. The generalisability of this argument is underscored by a similar analysis of European Social Survey data from 37 countries. The results highlight the importance of group characteristics in understanding attitudes towards refugees, particularly how views vary across groups and topics.

Transformer-based deep learning models for the sentiment analysis of social media data

Sentiment analysis (SA) is a widely used contextual mining technique for extracting useful and subjective information from text-based data. It applies on Natural Language Processing (NLP), text analysis, biometrics, and computational linguistics to identify, analyse, and extract responses, states, or emotions from the data. The features analysis technique plays a significant role in the development and improvement of a SA model. Recently, GloVe and Word2vec embedding models have been widely used for feature extractions. However, they overlook sentimental and contextual information of the text and need a large corpus of text data for training and generating exact vectors. These techniques generate vectors for just those words that are included in their vocabulary and ignore Out of Vocabulary Words (OOV), which can lead to information loss. Another challenge for the classification of sentiments is that of the lack of readily available annotated data. Sometimes, there is a contradiction between the review and their label that may cause misclassification. The aim of this paper is to propose a generalized SA model that can handle noisy data, OOV words, sentimental and contextual loss of reviews data. In this research, an effective Bi-directional Encoder Representation from Transformers (BERT) based Convolution Bi-directional Recurrent Neural Network (CBRNN) model is proposed with for exploring the syntactic and semantic information along with the sentimental and contextual analysis of the data. Initially, the zero-shot classification is used for labelling the reviews by calculating their polarity scores. After that, a pre-trained BERT model is employed for obtaining sentence-level semantics and contextual features from that data and generate embeddings. The obtained contextual embedded vectors were then passed to the neural network, comprised of dilated convolution and Bi-LSTM. The proposed model uses dilated convolution instead of classical convolution to extract local and global contextual semantic features from the embedded data. Bi-directional Long Short-Term Memory (Bi-LSTM) is used for the entire sequencing of the sentences. The CBRNN model is evaluated across four diverse domain text datasets based on accuracy, precision, recall, f1-score and AUC values. Thus, CBRNN can be efficiently used for performing SA tasks on social media reviews, without any information loss.

The Theoretical Topology and Implementation of Enterprise Social Security in the Digital Age Based on Big Data and Artificial Intelligence

At present, there are some problems in the social security of employees in enterprises, such as incomplete security and low reliability. According to this background, this paper studies a topological method for enterprise social security data analysis based on data adaptive analysis strategy and strong learning data stream coprocessing. According to this background, this paper studies a topology method of enterprise social security data analysis based on data adaptive analysis strategy and strong learning data flow and designed a convolutional neural network method based on mutual interference deepening strategy and advanced learning classification mode convolution neural network based on mutual interference deepening strategy and intensive learning classification pattern. According to the coverage error strategy of different types of data, the high-precision matching analysis of enterprise employee social security data is realized, and the Cartesian formula is used to correct the error and topology analysis of the analysis results. According to the experimental data and results, the topology method of enterprise social security data analysis is based on the experimental data and results. We can know that the topological method of enterprise social security data analysis is based on convolutional neural network. Enterprise social security theory can effectively improve the scope and speed of social security. This theory effectively completes the high-precision matching of different types of data and indirectly improves employees’ cognition of enterprise values.

Trends and patterns of life satisfaction and its relationship with social support in Canada, 2009 to 2018

The present study aims to explore the trends and patterns of life satisfaction in Canada from 2009 to 2018 and to examine changes in the associations between social support and life satisfaction over time. Data were from ten annual Canadian Community Health Surveys (CCHS). Each survey represents 97% of the Canadian population. Point estimates and 95% confidence intervals (CIs) of life satisfaction were calculated at the population level. Generalized linear regression was used to explore the relationship between life satisfaction and social support both nationally and in different population subgroups. The annual life satisfaction score gradually increased both at national and provincial levels from 2009 to 2018. Individuals who were women, aged between 12 and 19 years, living in rural areas, were most satisfied with their lives. There was a positive correlation between social support and life satisfaction for the provinces and the study years for which information on social support was available. Our findings suggest strengthening social support could be a public health target for promoting greater life satisfaction. Timely availability and analysis of life satisfaction and social support data could better inform policy and promote wellbeing at a population level.

Social Media Data Analytics for Marketing Strategies

The analysis of social media data to extract new insights has attracted much attention, especially in the field of Marketing. Few researchers, however, have studied both the concepts of Social Media Data Analytics (SMDA) and Marketing Strategies. Previous publications have only focused on a particular technique or a well-defined Marketing Strategy in a specific context. To address this gap, this paper aims to explore how Social Media Data Analytics can guide and affect Marketing Strategies, and provide an overview of the range of Social Media Data Analytics techniques related to Marketing Strategies. We conducted a systematic review of 120 papers published between 2015 and 2021 on SMDA in Marketing. The findings are presented in terms of the main social media platforms, publication date, journal quality, social media data types, analytical techniques, fields of application, firm size, and related Marketing Strategies. The SMDA techniques are classified into six categories: Sentiment Analysis, Artificial Intelligence, Data Mining, Statistics, Coding and Modelling, and Simulation. A set of detailed Marketing Strategies guided by SMDA are also presented, as well as an integrative framework mapping how SMDA creates value. The results highlight several SMDA techniques that still lack exploration and outline their relevance.

Social media data analysis framework for disaster response

This paper presents a social media data analysis framework applied to multiple datasets. The method developed uses machine learning classifiers, where filtering binary classifiers based on deep bidirectional neural networks are trained on benchmark datasets of disaster responses for earthquakes and floods and extreme flood events. The classifiers consist of learning from discrete handcrafted features and fine-tuning approaches using deep bidirectional Transformer neural networks on these disaster response datasets. With the development of the multiclass classification approach, we compare the state-of-the-art results in one of the benchmark datasets containing the largest number of disaster-related categories. The multiclass classification approaches developed in this research with support vector machines provide a precision of 0.83 and 0.79 compared to Bernoulli naïve Bayes, which are 0.59 and 0.76, and multinomial naïve Bayes, which are 0.79 and 0.91, respectively. The binary classification methods based on the MDRM dataset show a higher precision with deep learning methods (DistilBERT) than BoW and TF-IDF, while in the case of UnifiedCEHMET dataset show a high performance for accuracy with the deep learning method in terms of severity, with a precision of 0.92 compared to BoW and TF-IDF method which has a precision of 0.68 and 0.70, respectively.

Towards a framework to design product service system-based mobile phone waste management: A social media data analysis perspective

ABSTRACT Today, extensive universal concern about sustainable development, strict environmental legislation, and extended producer responsibility has become important incentives to consider end-of-life (EOL) products. Thus, the tremendous volume of mobile phone waste worldwide calls for the design of plans for managing products duringconsumption and the EOL phases to achieve sustainable treatment and betterenvironmental performance. Therefore, a product-service system (PSS) as a sustainable solution has received great attention. To achieve this goal, companies have shifted their focus to continuous improvement of PSS that contributes to better environmental performance and minimizing waste generation during the product life cycle. In this regard, this study suggests a new decision support system (DSS) model that supports the PSS design; that the proposed DSS analyzes the Twitter platform using an ontology-based text mining approach and a data mining-based technique based on the self-organizing map (SOM) to collect mobile phone defects from the Twitter database. Finally, a multi-objective optimization model was used to optimize economic and environmental impacts during the consumption and EOL phase based on mobile phone defects. This study shows that the PSS concepts can prevent mobile phone waste from arising in today’s modern worldby using social media data.

Social influence-based contrast language analysis framework for clinical decision support systems

Depression is a leading mental health problem affecting 300 million people globally. Recent studies show that social networks provide a tremendous potential for mental health professionals as a source of supplemental information about their patients. This study presents a methodological framework for clinical decision support systems (CDSSs) through analysis of social network data to distinguish the language usage of individuals with early signs of depression (i.e., contrast language analysis). By analyzing the contrast language patterns of different user groups, we are able to uncover constructive and actionable insights into the pain points and characteristics of users with signs of depression as decision support mechanisms for clinicians during intervention, (early) diagnosis and treatment plans. First, we discover terms that represent contrasting language by analyzing the percentage difference of terms in two user groups, labeled as”depressed” and”non-depressed” for ease of reference. Second, by building topic models based on social network contents, the topic-level contrast features are discovered. Finally, we consider the structure of the social network to discover the network-level contrast features. To illustrate the effectiveness of the proposed framework, we present a case study on early depression detection using a real-world dataset. The proposed framework has methodological contributions in enhancing the features and functionalities of CDSS for clinicians. It also contributes to evidence-based health research through cost-effective data and analytical insights that can supplement or improve the traditional survey and time-consuming interview methods.

Man and Woman - the Dilemma of Marital Evolution

Although in the social discourse, men and women are characterized by values that are specific to modernity or postmodernity, however, the analysis of social data often shows that the process of evolution must be located rather at the intersection between tradition and modernity. Thus, the status of men and women is in the process of being reconstructed and this is not a comfortable stage, especially for men. Marital modernity requires, as a matter of priority, a re-evaluation of the role structure and gender relations in the direction of equity, and in this endeavor, the greatest challenge is felt by men, who have to relinquish the old advantages of their traditional status. In this respect, a first hypothesis would be to consider women as having the main role in stimulating this action, and men as being less motivated to give up, by their own accord, the advantages offered by the traditional marital framework. 
 From another point of view, we rhetorically ask whether women are ready for this challenge and to what extent the social context becomes supportive in this transition of role and gender relations.
 The study aims to make an analysis of gender and marital role relations, in order to identify the challenges of functionality in the contemporary transitional couple.