Big Social Media Research Articles

Opinion mining and machine learning analysis : What emotions twitter data tell us about telemedicine?

The Covid-19 pandemic has made telemedicine one of the most relevant topics in recent years, so data mining about telemedicine obtained from Twitter offers a unique opportunity. The motivation of this study is to identify the emotional groupings of Twitter data users’ opinions for telemedicine using opinion mining techniques such as Sentiment Analysis combined with high-dimensional data classification and prediction methods. Data was collected from Twitter in August and September of 2021 related to telemedicine and official World Health Organization and World Bank documents for the years 2018 and 2021, respectively. Sentiment Analysis showed that 56.2% (n = 5351 tweets) of the sample had predominantly positive emotions toward telemedicine. Telemedicine, telehealth, and ivermectin are the most frequent words in the word cloud. Twitter data users’ opinions consist of nine mood classes (SIL index = 0.80) and the differences between these classes are statistically significant in terms of positive (p < 0.05), negative (p < 0.05), and neutral (p < 0.05) emotions. Neural Network (AUC = 0.842, F1 = 0.492) and Random Forest (AUC = 0.841, F1 = 0.494) are the best predictors of Twitter users’ mood classes compared with other machine learning techniques. The pythagorean tree generated by Random Forest showed that retweet is the best predictor of Twitter users’ opinions and emotional classes towards telemedicine. Future studies will create big social media datasets for a deep understanding of the emotional classes of individuals towards telemedicine technologies.

Global online social response to a natural disaster and its influencing factors: a case study of Typhoon Haiyan

The global public interest in a natural disaster event will help disaster-stricken areas obtain post-disaster international relief and assistance. However, knowledge gaps still exist in regard to global online social responses and their socioeconomic influencing factors. We used big social media data regarding the 2013 Super Typhoon Haiyan to explore global online social responses and to investigate the socioeconomic factors influencing this behavior based on the Geographical Detector (Geodetector) model and geographically weighted regression (GWR) model. The results show that global online social responses have little relation with geographical distance and follow the disaster’s development. In addition to the most response in the disaster-affected countries, Western countries and neighboring countries have more online social response to the disaster than other regions. Among all the influencing factors, economic factors have the strongest effect on public interest both before and after the typhoon’s landfall. Our findings indicate that online social users are of great potential for volunteers and donors.

Uncover Social Media Interactions On Cryptocurrencies Using Social Set Analysis (SSA)

Cryptocurrencies are decentralized digital currencies that use blockchain technology to create a secure and decentralized environment. In the decade since the inception of social media, it has created revolutions and connected people with interests. Social media platforms such as Twitter allow users worldwide to share opinions, emotions, and news. Twitter is one of the most used social media platforms worldwide, where millions of users share tweets continuously every second. By leveraging 1724328 tweets, this research-in-progress paper aims to understand the dynamics of social media users’ interactions on cryptocurrencies using social set analysis (SSA). The findings reveal that Twitter users are more positive about cryptocurrencies. The analysis also shows an existing relationship between events and the interaction of users, where cryptocurrency-related events shift the emotion, sentiment, and discussion topics of the users. The research-in-progress paper also contributes to demonstrating the effectiveness of the social set analysis framework to analyse and visualize a big social media data.

Mapping Growth of the Russian Domestic Propaganda Apparatus on Telegram

As a part of Western sanctions against Russia, big social media companies i.e., Facebook, Twitter, and YouTube, have been limiting their functionalities available to Russians and suspending and limiting reach of Russian influencers. Many Russian propagandist, aware of the risk of becoming deplatformed, were already looking for social media platforms with less moderation before the February 24th. With many Russians using Telegram as their preferred communicator, Telegram became the natural choice. Russian government, by blocking access to Western social media platforms by Russian users and by directing state influencers to migrate their domestic audiences to Telegram, has accelerated this trend. Despite many advantages, Telegram is limited in ease with which new content and channels can be discovered. Telegram search for channels is based on exact string matching and Telegram has no content search or content recommendation functionality built into it. Telegram’s advertising mechanism is still in its infancy. To enable quick growth of the key state propaganda channels, Russians employed several tactics. They have selected a few existing influencers, such as Vladimir Soloviev, to substitute for the absent search and recommendation engine. Soloviev’s Telegram channels has been heavily advertised on legacy media, starting with TV stations carrying his programs, to serve as an onramp to Telegram. Soloviev has regularly featured reviews of other smaller channels, endorsing, and promoting their pro-conflict content, becoming the missing recommendation engine for Russians. All the above resulted in creating a vast, Telegram-based apparatus of domestic state propaganda. In this paper, we trace the growth of Russian pro-conflict Telegram communities and quantify the impact of centralized endorsement by state influencers on the growth of other smaller, specialized Telegram channels.

Are Crime and Collective Emotion Interrelated? A “Broken Emotion” Conjecture from Community Twitter Posts

A neighborhood’s social cohesion, referring to the emotional and social connection of people within it, tends to have an influential impact on its crime level. Traditional approaches to measuring social cohesion and collective efficacy are mostly interviews and surveys, which are usually costly in time, money, and other resources. Big social media data provides us with a new and cost-effective source of such information. We believe the combination of spatial and contextual information of geotagged Twitter posts (tweets) can gauge the residents’ collective emotions in a neighborhood. The positivity and negativity of these collective emotions may be used to approximate the collective efficacy of the community. Inspired by the broken window theory, we propose a broken emotion conjecture to explain the relationship between collective emotion and crime. To test this conjecture, we collected data on four types of crime (assaults, burglaries, robberies, and thefts) and all public geotagged tweets ( N = 778,901) in Cincinnati, Ohio, USA in 2013. We extracted innovative variables from tweets’ spatial and contextual information to explain community crime and enlighten new criminology theory. Results of negative binomial models show: (1) with necessary socio-economic and land-use factors controlled, the more negative the collective emotion of a neighborhood, the more the crime (except for theft); (2) however, the positivity of the collective emotion of a neighborhood does not have any statistically significant influence on crime. These correspond well with signal detection theory in psychology. The proposed broken emotion conjecture is supported with data from Cincinnati and its general applicability should be tested in other regions.

Migrating social event recommendation over microblogs

Real applications like crisis management require the real time awareness of critical situations. However, the services using traditional methods like phone calls can be easily delayed due to busy lines, transfer delays or limited communication ability in disaster areas. Existing social event analysis solutions enhanced the situation awareness of systems. Unfortunately, they cannot recognize the complex migrating social events that are first observed in social media at a specific time, place and state, but have further moved in space and time, which may affect the system comprehension. While the discussion on events appears in microblogs, their movement over different contexts is unavoidable. So far, the problem of migrating social event analysis from big media is not well investigated yet. To address this issue, we propose a novel framework to monitor and deliver the migrating events in big social media data, which fully exploits the social media information over multiple attributes and their inherent interactions among events. Specifically, we first propose a Concept TF/IDF model to capture the content that is constrained by the time and location of media without costly learning process. Then, we construct a novel Maximal User Influence Graph (MUIG) to extract the social interactions. With MUIG, the event migrations over space and time are well identified. Finally, we design efficient query strategies over Apache Spark for recommending events in real time. Extensive tests over big media are conducted to prove the high effectiveness and efficiency of our approach.

Mr J and his 'Insta' Account: Aaron Builds big Social Media Following to Inspire Other Teachers

Mr J and his 'Insta' Account: Aaron Builds big Social Media Following to Inspire Other Teachers

Explicit quantification of coastal cultural ecosystem services: A novel approach based on the content and sentimental analysis of social media

Ecosystem service assessments have been conducted for coastal management with a primary focus on tangible natural capital. Thus far, the explicit variation of cultural ecosystem services (CESs) and particularly the sentiments of CES-related ecotourism are not well understood. This paper takes advantage of big social media data to unravel the patterns of CESs and visiting sentiments in coastal areas of Hong Kong. Through machine-learned keyword labels, we employed content analysis to derive visual information for geotagged photographs. Applying natural language processing to apps with machine learning in cloud computing, we derived the sentiments based on user-generated textual content associated with coastal ecotourism. Based on regression analysis and multiple comparisons analysis, we identify the association between critical demographic and temporal factors with CES and related visiting sentiments. Referring to previous studies, we identified the main intangible benefits into six basic divisions based on 424 keyword labels for coastal areas. Our results show that hotspots of CESs are spatially concentrated in both cultural attractions and protected areas, which are critical for coastal ecosystem management and protection. More specifically, these areas of high CES value have good spatiotemporal accessibility, high infrastructure coverage, and spatially explicit population and economic growth. Furthermore, we discover that sentiments related to coastal CESs vary based on social media characteristics. Our study renews the indicators of quantitative CES evaluation based on crowdsourcing geospatial data.

How Big Data Analytics, AI, and Social Media Marketing Research Boost Market Orientation

ABSTRACT Overview: Previous research has shown that market-oriented firms outperform their peers. Why are some firms such outstanding performers in market orientation (MO)? This study identifies three categories of new technology tools that have emerged in the past few years—big data analytics, artificial intelligence (AI), and social media marketing research—and assesses how each category enhances MO. The empirical evidence from 442 firms indicates that all three categories have significant impacts on MO, with AI being the most effective, followed by big data analytics and social media marketing research, respectively. We outline how very successful firms adopt these new technology tools and offer managerial implications that can guide senior executives looking to increase MO.

The Borderless Integration of Financial Management Innovation Using Big Data Analysis of Social Media

This article mainly studies the innovation of borderless integrated financial management in big data social media in the era of wireless communication networks. For evaluating company A’s financial sharing capabilities, five first-level indicators are divided into four dimensions: quality, efficiency, cost, and safety, and are allowed to score the financial sharing center capabilities. First of all, system integration takes performance appraisal as the core, and through the establishment of a reasonable appraisal system, performance appraisal for the members of the financial team is carried out. Secondly, team members need to accept two-way leadership, two-way assessment, and two-way incentives from the finance and business departments. The experimental factors were analyzed, and the results showed that the cumulative variance contribution rate with common factors reached 89.339%. The importance of the first-level indicators is in order of process reengineering (27.08%), operation management (22.33%), information system (20.24%), personnel management (17.178%), and strategic planning (12.46%).

Ethical issues of collecting, storing, and analyzing geo-referenced tweets for mental health research.

Spatial approaches to epidemiological research with big social media data provide tremendous opportunities to study the relationship between the socio-ecological context where these data are generated and health indicators of interest. Such research poses a number of ethical challenges, particularly in relation to issues such as privacy, informed consent, data security, and storage. While these issues have received considerable attention by researchers in relation to research for physical health purposes in the past 10 years, there have been few efforts to consider the ethical challenges of conducting mental health research, particularly with geo-referenced social media data. The aim of this article is to identify strengths and limitations of current recommendations to address the specific ethical issues of geo-referenced tweets for mental health research. We contribute to the ongoing debate on the ethical implications of big data research and also provide recommendations to researchers and stakeholders alike on how to tackle them, with a specific focus on the use of geo-referenced data for mental health research purposes. With increasing awareness of data privacy and confidentiality issues (even for non-spatial social media data) it becomes crucial to establish professional standards of conduct so that compliance with ethical standards of conducting research with health-related social media data can be prioritized and easily assessed.

Assaults on Freedom of Speech: Why Social Studies Must Defend the First Amendment

Freedom of expression is the core political ideal undergirding American democracy and recent attacks on freedom of speech are a direct threat to the liberties and rights guaranteed in the United States Constitution. Freedom of expression is essential for participatory democracy, scientific progress, individualism, and civic education in K-12 schools and universities. Citizens must have access to all opinions, empirical evidence, historical information, and competing narratives to make informed decisions regarding political candidates, policies, and issues. This necessitates the right to express offensive, controversial, repugnant, and radical opinions and values that that are shocking to government or specific groups. Indeed, this is the primary purpose of the First Amendment’s protection of freedom of speech and the press. However, this freedom is experiencing a withering assault from special interest groups, Big Tech social media entities, and most ironically, universities, ostensibly the ultimate guardians of freedom of expression. “Hate” speech codes and other attempts at censorship are anathema to democracy. Attacks on freedom of expression are an existential threat to social studies education. Thus, it is incumbent upon all social studies professors and K-12 social studies educators to combat this dangerous attack on the First Amendment.

Implications of Twitter in Health-Related Research: A Landscape Analysis of the Scientific Literature.

Background: Twitter, representing a big social media network, is broadly used for the communication of health-related information. In this work, we aimed to identify and analyze the scientific literature on Twitter use in context of health by utilizing a bibliometric approach, in order to obtain quantitative information on dominant research topics, trending themes, key publications, scientific institutions, and prolific researchers who contributed to this scientific area.Methods: Web of Science electronic database was searched to identify relevant papers on Twitter and health. Basic bibliographic data was obtained utilizing the “Analyze” function of the database. Full records and cited references were exported to VOSviewer, a dedicated bibliometric software, for further analysis. A term map and a keyword map were synthesized to visualize recurring words within titles, abstracts and keywords.Results: The analysis was based on the data from 2,582 papers. The first papers were published in 2009, and the publication count increased rapidly since 2015. Original articles and reviews were published in a ratio of 10.6:1. The Journal of Medical Internet Research was the top journal, and the United States had contributions to over half (52%) of these publications, being the home-country of eight of the top ten most productive institutions. Keyword analysis identified six topically defined clusters, with professional education in healthcare being the top theme cluster (consisting of 66 keywords). The identified papers often investigated Twitter together with other social media, such as YouTube and Facebook.Conclusions: A great diversity of themes was found in the identified papers, including: professional education in healthcare, big data and sentiment analysis, social marketing and substance use, physical and emotional well-being of young adults, and public health and health communication. Our quantitative analysis outlines Twitter as both, an increasingly popular data source, and a highly versatile tool for health-related research.

A Study in Anxiety of the Dark

A Study in Anxiety of the Dark

Dealing With Statistical Significance in Big Data: The Social Media Value of Game Outcomes in Professional Football

The identification of relevant effects is challenging in Big Data because larger samples are more likely to yield statistically significant effects. Professional sport teams attempting to identify the core drivers behind their follower numbers on social media also face this challenge. The purposes of this study are to examine the effects of game outcomes on the change rate of followers using big social media data and to assess the relative impact of determinants using dominance analysis. The authors collected data of 644 first division football clubs from Facebook (n = 297,042), Twitter (n = 292,186), and Instagram (n = 312,710) over a 19-month period. Our fixed-effects regressions returned significant findings for game outcomes. Therefore, the authors extracted the relative importance of wins, draws, and losses through dominance analysis, indicating that a victory yielded the highest increase in followers. For practitioners, the findings present opportunities to develop fan engagement, increase the number of followers, and enter new markets.

"When they say weed causes depression, but it's your fav antidepressant": Knowledge-aware attention framework for relationship extraction.

With the increasing legalization of medical and recreational use of cannabis, more research is needed to understand the association between depression and consumer behavior related to cannabis consumption. Big social media data has potential to provide deeper insights about these associations to public health analysts. In this interdisciplinary study, we demonstrate the value of incorporating domain-specific knowledge in the learning process to identify the relationships between cannabis use and depression. We develop an end-to-end knowledge infused deep learning framework (Gated-K-BERT) that leverages the pre-trained BERT language representation model and domain-specific declarative knowledge source (Drug Abuse Ontology) to jointly extract entities and their relationship using gated fusion sharing mechanism. Our model is further tailored to provide more focus to the entities mention in the sentence through entity-position aware attention layer, where ontology is used to locate the target entities position. Experimental results show that inclusion of the knowledge-aware attentive representation in association with BERT can extract the cannabis-depression relationship with better coverage in comparison to the state-of-the-art relation extractor.

Escaping to nature during a pandemic: A natural experiment in Asian cities during the COVID-19 pandemic with big social media data

As global communities respond to the spread of coronavirus disease 2019 (COVID-19), urban residents worldwide have reduced their mobility, which may have incidentally kept people away from greenspaces. Surprisingly, anecdotal evidence suggests greenspace use surged in Asian cities. In this study, we used the COVID-19 pandemic as a natural experiment to investigate individuals' behavioral changes in greenspace use before and during the pandemic. We created a longitudinal panel dataset comprising Instagram posts from 100,232 users relating to 1185 greenspaces in four Asian cities: Hong Kong, Singapore, Tokyo, and Seoul. We found a 5.3% increase in the odds of people using greenspaces for every 100-case increase in weekly new cases. The models also revealed that people prefer nature parks that are large and close to city centers. In summary, because of the established physical and mental health benefits of greenspaces, people have been escaping to nature to cope with the pandemic in Asian cities.

Multimodal approach to analysing big social and news media data

Multimodal analysis traditionally involves conceptualising abstract frameworks for language, images, and other resources and their intersemiotic relations (e.g. text and image relations) and then demonstrating these frameworks with some examples. This scenario has changed with the recent move towards multimodal approaches to big data analytics which will involve empirically testing and validating multimodal theory and frameworks through the analysis of large data sets. However, large training sets of analysed texts are required to develop computational models based on multimodal theory. Therefore, an alternative approach which involves integrating multimodal frameworks with existing computational models for big data, cloud computing, natural language processing, image processing, video processing, and contextual metadata is proposed. The integration of these disparate fields has the potential to dramatically improve computational tools and techniques, thus placing multimodality at the forefront of research aimed at mapping and understanding multimodal communication. As a step forward in this direction, we explore how existing computational tools and approaches can be integrated into a multimodal analysis platform (MAP) with facilities for searching, storing and analysing text, images and videos in online media, together with dashboards for visualising the results. Preliminary analyses and classifications of text and images about COVID-19 and George Floyd in five online newspapers and Twitter postings show how media patterns can be studied using existing computational tools. The study highlights (a) the benefits and current limitations of big data approach to multimodal discourse analysis and (b) the need to incorporate knowledge about language, images, metadata, and other resources as semiotic systems (rather simply sets of symbols and pixels) to improve computational techniques for big data analytics.

Suggestion Mining from Opinionated Text of Big Social Media Data

Suggestion Mining from Opinionated Text of Big Social Media Data

Social Media Socialism: People’s Tech and Decolonization for a Global Society in Crisis

Recent proposals by the neo-Brandeisian School of antitrust seek to ameliorate harms to society created by social media monopolies. While this initiative sounds great on paper, their solutions are inadequate, as they leave the proprietary, profit-seeking structure of social media networking intact. As a result, the neo-Brandeisian framework fails to cope with the harms of Big Social Media networks, such as privacy harms, user manipulation, the amplification of sensational content, the problems of online advertising, digital colonialism, and environmental degradation. This Article argues that social media socialism based on a democratic commons should replace Big Social Media networks. It suggests an interlocking set of tools to decentralize social networks, including network interoperability, data portability, data decentralization, a fully Free and Open Source Software stack, and socialist legal solutions. The guiding framework is based on a People’s Tech model that places ownership and control of social media directly into the hands of the global public. It proposes solutions to (1) force interoperability, data portability, data decentralization, and a Free and Open Source Software stack on social media providers; (2) put rules in place to prevent new business practices that concentrate wealth and power; (3) abolish or amend laws inconsistent with social media socialism; (4) pass strong privacy laws; (5) subsidize the social media commons through a Digital Tech New Deal; (6) form regulatory bodies to regulate social media; (7) formulate solutions jointly with the international community within a decolonial framework designed for global equality, reparations, and environmental sustainability. The Article begins by outlining the harms produced by social media monopolies. Next, it provides a socialist critique of neo-Brandeisian philosophy and its proposals to fix social media. Following that, it explains how commons-based social media decentralization works -- including its history, philosophy, and core components -- using the Fediverse and LibreSocial as case examples. The final section outlines a People's Tech model for social media socialism and addresses possible challenges.