Social Media Analysis Research Articles

Preserving and Promoting Indigenous Languages: Social Media Analysis of Punjabi and Setswana Languages

A treasure of knowledge is lost when a language dies and it is irretrievable. While the majority of indigenous languages are endangered, it is difficult for these languages to survive in the 21st century socially diverse world. This study examines the role of social media in the preservation and promotion of indigenous languages, particularly Punjabi and Setswana, within the context of social media platforms Facebook and X (formally called Twitter). The qualitative approach, using a content analysis method, investigates the linguistic content shared on these platforms. These languages act as channels for language preservation and promotion, navigating time, place and identity in the digital era. Social media platforms, such as X and Facebook, have the potential to rejuvenate and conserve indigenous and endangered languages. The study reveals a rich tapestry of participation, expression, and community development in the digital arena, highlighting the potential of both platforms to preserve and promote indigenous languages. The study also explores aspects such as prosocial impacts, social norms and convincing representations. Overall, this study emphasizes the importance of making fundamental decisions about social media and indigenous language preservation and promotion, emphasizing the mitigation of challenges.

Sentiment analysis of multi social media using machine and deep learning models: a review

Sentiment analysis of multi social media using machine and deep learning models: a review

Fixing things from the outside? Diaspora politicians and transnational political engagement

ABSTRACT Scholarship on diaspora political engagement is unfolding in novel ways exploring the participation of second-generation diaspora individuals and engagement patters of authoritarian and hybrid regimes. Focusing on the unique role of diaspora politicians, I contend that these individuals adeptly leverage their identity to impact politics and advocate for change. The article demonstrates their adaptability in different settings and evolving advocacy strategies. The article employs a multilingual analysis of social media, public interviews, and public appearances in Germany and Bosnia and Herzegovina using an exploratory case study of a German-Bosnian politician. This exploration underscores their flexibility and evolving advocacy dynamics. Furthermore, it illustrates the way these politicians enhance their profiles within the countries where they’ve been elected and in countries of their descent. This serves to strengthen their chances of re-election on one hand while also drawing attention to authoritarian tendencies, potentially clearing a path for democratic advancement on the other.

From attention to affect: gendered practices of status-seeking among Instagram content creators

ABSTRACT This article explores the dynamics of status gaining and signalling among Instagram micro-influencers. The article posits that within the influencer industry, the process of status acquisition is undergoing a shift from attention to affect, where the collection and display of public expressions of sentiment have become central to accruing social status. The emphasis on affective responses and interactions, however, goes hand in hand with the constant quantification and commercialisation of affect, which becomes conflated into measurements of engagement. Furthermore, the concept of calibrated femininity is introduced to account for the gendered dimension of status-seeking practices and highlight their entanglement with a fine-tuned representation of the self and the body in accordance with social media analytics. The empirical research consists of qualitative interviews (n = 25) with Instagram micro-influencers, as well as insights emerging from digital ethnography. The results show how content creators construct social status as affect through three interconnected practices: the nurturing of their audience, the calibration of femininity, and the display of affective responses as status symbols.

Public perceptions of justification in the deadly police shootings of black men: a content analysis of social media posts in 2016 and 2020

The proliferation of information technologies has revolutionized how people around the world consume news. By 2021, an estimated 8.6 billion mobile subscriptions existed worldwide. In the United States, a majority (84%) of Americans access their news digitally. On social media platforms, Facebook is the most used network for obtaining news. The three major news sources in the United States, CNN, Fox News, and MSNC, have a strong presence on Facebook. The current study analyzes public comments posted on Facebook involving the deadly police shootings of four Black men (i.e., Alton Sterling, Philando Castile, Jonathan Price, Rayshard Brooks) to identify reactions at two points in time. Our work centers on public comments to these posts, not the posts themselves. Using a summative qualitative analysis, we analyzed the first 20 Facebook comments from CNN, Fox News, and MSNBC that are listed as most relevant (e.g., highest number of likes, reactions, replies) to the most recently posted news story regarding the incident. This resulted in a sample size of 223 posts. Public comments were categorized as justifying the killing, perceiving the killing as not justified, or expressing neutrality as to whether the killing was justified or not. We found that most comments, regardless of time period, did not engage in victim-blaming. Overall, the majority (N = 139 or 62%) of all comments perceived these deadly police shootings as not justified. Most (54%) posts on Fox News justified this violence, while the majority of posts on CNN or MSNBC felt the police had used excessive violence. There were more negative comments of Black men and victim-blaming after the Trump presidency (in 2020) than in 2016 (before Trump took office), which may be related to the racial rhetoric of the times.

Pseudo-positive Information and COVID-19: Reasons behind Sharing Fake News (Georgian Social Media Analysis)

A plethora of studies state that a perceptible gap can be observed concerning disinformation influence analysis, which is presented by a lack of research on this phenomenon. In a crisis precipitated by the pandemic disruption, the necessity to scrutinize these topics becomes particularly transparent, as an individual’s critical thinking is incapacitated, which leads to a surge in fake news sharing. The article aims to expose and investigate the characteristics of a new, pseudo-positive disposition of false information and the reasons behind its extensive dissemination. By analyzing the original sources of fake news published on "Facebook", conducting an in-depth interview with eight field experts, integrated with a small survey of 204 Georgians, we identify that to overcome the pandemic-induced stress and create an optimistic environment, any positive information that is apprehensible under these conditions becomes effortlessly shareable and consequently, pseudo-positivity is utilized as a manipulator to foment a wave of disinfodemy. Keywords: disinformation, pseudo-positivity, social media, COVID-19, manipulation, crisis, Facebook, mental health, media psychology

A Predictive Model Based on TripAdvisor Textual Reviews: Early Destination Recommendations for Travel Planning

Although many studies have considered the effects of online reviews on tourists’ decisions, none have directly investigated how to leverage open data analyses to create early choice sets and facilitate destination planning. This paper illustrates how salient characteristics can be mined from the shared experiences embedded in review data and incorporated into a predictive model to build a travel counseling approach. The model is designed by first defining a prediction-based mechanism from online reviews and then generating a multinomial classification problem on all candidate destinations of interest. The model is implemented by applying Natural Language Processing (NLP) and Deep Learning (DL) technologies to review textual features. The model is validated using 75,315 reviews from TripAdvisor along with destinations from 257 U.S. national parks. Empirical results indicate a best classification accuracy of 67%, outperforming two previous approaches. Findings shed light on how to exploit past tourists’ experiences to generate early destination recommendations to identify items for choice sets and reduce tourists’ travel-planning effort. Theoretical and managerial implications regarding social media analytics are provided based on online review meta-data in touristic management.

The shitposting scattergun approach: A multimodal analysis of the first wave COVID-19 social media messaging from UKGov

This article analyses the type and style of the UK government social media messaging during the first wave of the COVID-19 pandemic using multimodal and social semiotic analysis. Images improve health communication by increasing comprehension of information, enhancing recall of instructions, encouraging positive self-protective attitudes and behaviour and are beneficial to those with low health literacy skills. When done well, visual material can meaningfully improve health outcomes. UKGov’s social media during COVID-19 reveals that production of mental noise and feed flooding can affect perceptions of risk. Recognizing the impact that both visuals and social media campaigns can have in crisis communication, this article first explores the steps in creating the social communication and then analyses social media posts during the first four months of the pandemic from UKGov Facebook and Instagram accounts. This article employs a multimodal social semiotic methodology to organize, code and make sense of the often contradictory and ambiguous meanings contained in a vast trove of visual data. Ultimately, this article argues that the UKGov’s ‘scattergun’ approach to the first wave COVID-19 infographics enhanced polysemic meanings and flooded social media feeds with ‘shitposting’ philosophy, which decreased clarity of understanding and potentially impacted health literacy amongst the UK populous.

Exploring Causal Relationships in Mental Health Literacy Through Twitter Content: A Machine Learning Approach

IntroductionThe concept of Mental Health Literacy (MHL) is inherently multidimensional. However, the interrelationships among its various dimensions remain insufficiently elucidated. In recent years, the textual analysis of social media posts has emerged as a promising methodological approach for longitudinal research in this domain.ObjectivesThis study aimed to investigate whether temporal causal associations exist between recognition of mental illness (R), mental illness stigma (S), help-seeking efficacy (HE), maintenance of positive mental health (M), and help-seeking attitude (HA).MethodsTweets were collocted at three distinct time points: T1, T2, and T3, spanning the period from November 1, 2021, to December 31, 2022. We employed a machine-learning approach to categorize the posts into five MHL facets. Using these facets, we trained a machine learning model, specifically Bidirectional Encoder Representations from Transformers (BERT), to determine the MHL scores. To be eligible, an account must have an R facet score at T1, and M, S, HE facet scores at T2, as well as an HA facet score at T3. In total, we retrieved 4,471,951 MHL-related tweets from 941 users. We further employed structural equation modeling to validate the causal relationships within the MHL framework.ResultsIn the evaluation, BERT achieved average accuracy scores exceeding 89% across the five MHL facets in the validation set, along with F1-scores ranging between 0.75 and 0.89. Among the five MHL facets—maintenance of positive mental health, recognition of mental illness, help-seeking efficacy, and help-seeking attitudes—each demonstrated a statistically significant positive correlation with the others. Conversely, mental illness stigma exhibited a statistically significant negative correlation with the remaining four facets. In the analysis using single-mediation models, each of the individual mediator variables—namely, mental illness stigma, help-seeking efficacy, and maintenance of positive mental health—exhibited significant indirect effects. In the multiple-mediation model, two mediator variables—help-seeking efficacy and maintenance of positive mental health—demonstrated significant indirect effects. These findings suggested that the recognition of mental illness exerted an influence on help-seeking attitudes through one or more of these mediators.ConclusionsBy leveraging machine learning techniques for the textual analysis of social media and employing a longitudinal research design with panel data, this study elucidates the potential mechanisms through which the MHL framework influences attitudes toward seeking mental health services. These insights hold significant implications for the design of future interventions and the development of targeted policies aimed at promoting help-seeking behaviors.Disclosure of InterestNone Declared

540 Diversifying SC CTSI’s Message: Successfully Leveraging Multi-Platform Social Media for Multi-Audience Dissemination

OBJECTIVES/GOALS: We explain our multi-platform, multi-audience approach to stakeholder engagement/communication, discuss KPIs for our Instagram accounts, and highlight five top performing posts. Finally, we provide tips to Hubs who would like to tailor and optimize their social media approach. METHODS/STUDY POPULATION: We employed Uses & Gratifications theory and formative research with stakeholders to inform our social media strategy. We run two Instagram accounts (main CTSI & Community Engagement [CE]), one Facebook page (CE), and one Twitter/X page (main CTSI). To understand impact, we collected social media analytics on both Instagram accounts (main CTSI and Community Engagement-specific accounts) to ascertain four social media-related Key Performance Indicators since the inception of the two accounts: reach, impressions, growth rate, and engagement. Additionally, we examined the five top-performing posts on each account that gave us insights into trending topics and ideas for future content. RESULTS/ANTICIPATED RESULTS: From January 2023 to October 2023, the reach for the main account was 3,578 and 38,235 for CE. The number of profile visits for the main account was 474 and 2,703 for CE. Engagement data on Instagram is only available for the last 90 days. For the main account, the number of post likes, comments and shares was 622 and 2,700 for CE. The views and reach for the five top-performing posts on the main and CE accounts ranged in the thousands. The content of the top-performing posts for the main CTSI account varied between highlighting our KL2 scholars' accomplishments, recap of campus-wide research events, and advertisements for upcoming educational webinars. CE’s top posts varied between highlighting their work in a South LA housing community, recaps of large community health events, and interviews with local key leaders. DISCUSSION/SIGNIFICANCE: CTSA Hubs have an ethical obligation to keep their local academic and community audiences apprised of their activities. Creating a formative research and theoretically-informed social media plan that varies by platform, and regularly evaluating performance insights allows us to track the type of content that appeals to our multiple audiences.

Text-Based Content Analysis on Social Media Using Topic Modelling to Support Digital Marketing

This study aims to create Social Media Analytics (SMA) tools to help Digital Marketers or Content Creators create content topics for creating text-based Instagram content and support digital marketing strategy. Since no SMA tools can provide topic discovery for text-based Instagram content, this research aims to make an SMA tool. The data requirements to make an SMA tool include content text, content caption text, likes, comments, upload time, and content category obtained through the Instascrapper. The method used in this study is the Topic Modelling method using the Latent Dirichlet Allocation (LDA) approach to find the most dominant topic in the content. Optical Character Recognition (OCR) performs an image transformation process to extract text from text-based Instagram content images. The results of SMA tool creation are tested on three expert users, which shows that 93% of test participants could use the SMA to find topic references, and 85% can still be used by users even though they find it difficult. Since the test result shows that SMA tools still need development, for further research, SMA tools can focus on developing the user experience to increase the value of user acceptance by paying attention to the ease of the SMA tools. Also, SMA tools can focus on target users such as Data Analysts, Business Intelligence Analysts, or others within a company to support decision-making for the marketing department.

Public Relations Strategies for Non-Profit Organizations

Purpose: This study aimed to examine how different public relations strategies affect the effectiveness of non-profit organizations' communication and relationships with their stakeholders.
 Methodology: The study adopted a desktop research methodology. Desk research refers to secondary data or that which can be collected without fieldwork. Desk research is basically involved in collecting data from existing resources hence it is often considered a low cost technique as compared to field research, as the main cost is involved in executive’s time, telephone charges and directories. Thus, the study relied on already published studies, reports and statistics. This secondary data was easily accessed through the online journals and library.
 Findings: The findings reveal that there exists a contextual and methodological gap relating to public relations strategies for non- profit organizations. The yielded valuable insights into the multifaceted landscape of non-profit PR. Through diverse empirical studies, it was found that effective PR strategies played a pivotal role in shaping organizational visibility, credibility, and impact. Key conclusions drawn from the research included the transformative potential of digital platforms in amplifying reach and mobilizing support, the importance of stakeholder engagement and strategic storytelling in fostering donor loyalty and conveying organizational impact, the critical role of transparency and proactive communication in navigating crises, and the significance of strategic partnerships in enhancing organizational capacity and impact. Overall, the findings underscored the importance of adopting a holistic and strategic approach to non-profit PR to achieve mission-driven objectives and effect positive change.
 Unique Contribution to Theory, Practice and Policy: The Systems theory, Stakeholder theory and Diffusion of Innovation theory may be used to anchor future studies on public relations strategies for non- profit organizations. The study provided several key recommendations to enhance PR practices in the non-profit sector. It recommended that NPOs invest in advanced social media analytics tools, cultivate authentic donor relationships, develop robust crisis communication plans, seek out strategic corporate partnerships, engage in rigorous advocacy planning, invest in storytelling resources and training, and leverage digital advocacy tools. These recommendations aimed to improve PR effectiveness by emphasizing evidence-based decision-making, donor-centric approaches, proactive crisis management, strategic collaboration, and leveraging digital platforms for advocacy and storytelling. Through these recommendations, the study contributed to both theory and practice in the non-profit sector, offering actionable insights to enhance organizational communication strategies.

Global South Responses to China’s BRI Projects: A Case Study of Jakarta-Bandung High-Speed Railway Project

China's rise as a global power in the 21st century, marked by its economic growth and political influence, has been exemplified through initiatives like the Belt and Road Initiative (BRI). The BRI has extended China's geoeconomic and geopolitical influence across Asia, Africa, Latin America, and Europe. While existing literature predominantly focuses on China's actions, this study shifts the spotlight to Global South nations' responses and strategic policies, particularly Indonesia, in the context of China's BRI projects. Drawing upon in-depth interviews, literature review, and social media analysis, this research examines how Indonesia has actively shaped the Jakarta-Bandung High-Speed Railway project within the BRI framework to pursue its objectives and interests. The study's findings highlight that the Indonesian government, in alignment with the principles of the BRI, is actively utilizing the Jakarta-Bandung High-Speed Railway project to advance its New Developmentalism approach under President Jokowi's administration. This approach embodies a narrow perspective of development by focusing on infrastructure and economic growth while ignoring political and environmental considerations. Concurrently, the project has encountered resistance from local communities, underscoring the contrasting interests between the government and the public and adding a nuanced layer to the dynamics of the BRI. This case study sheds light on the complex interplay of interests and power dynamics within the context of China's BRI projects in the Global South. It underscores the importance of considering the responses and agency of host nations and local communities in shaping the outcomes of BRI initiatives.

Machine learning and deep learning-based sentiment analysis of IMDB user reviews

Movie reviews have always been a popular and enduring subject of interest among researchers. Sentiment analysis plays a significant role in this domain. The utilization of machine learning and natural language processing techniques can provide valuable insights into the emotional responses of audiences towards movies, as well as facilitate the appraisal of their reputation and market potential. This is achieved through the analysis of sentiment expressed in movie reviews. Furthermore, this approach is highly valuable in various application domains such as data mining, web mining, and social media analysis. This paper aims to conduct a comparative analysis by utilizing typical models based on machine learning and neural networks, along with the integration of natural language processing techniques. The IMDB database, which contains 50,000 reviews, will be used, and data preprocessing will be performed before applying these models. By comparing the accuracy of each model, insights regarding movie reviews can be derived.

Supporting spatial planning with a novel method based on participatory Bayesian networks: An application in Curaçao

Land use change is a major driver of environmental degradation, necessitating appropriate planning to navigate trade-offs between societal objectives and ecological impacts. Sound planning is limited in some regions by data scarcity and incomplete scientific knowledge on local dynamics shaping development of land. In this paper, we present a novel expert-based participatory approach that uses Bayesian networks to determine land use suitability and potential conflicts for emerging land uses. This method encompasses a workshop phase for building suitability models for different sectors, data assembly and preparation, spatialization of networks, and iterative validation with experts. Mapped suitabilities for all land uses were used to assess potential competition for land across sectors and to quantify alignment of the expert-modeled outcomes with established land use policy. Applied to Curaçao, a data-poor environment in the Caribbean facing high land use competition, the method enabled the construction and parameterization of 5 Bayesian networks driven by 35 spatial input datasets generated through various methods from participatory mapping to social media analysis. Overlap in suitable locations for conservation and tourism development along segments of the coastline and roadsides of the western island highlight potential conflict stemming from coincidence of desirable natural amenities and ecologically sensitive areas. Results yield key insights that can drive discussion and inform policymakers and spatial planners as they navigate tradeoffs and seek optimal use of limited land resources. Process-based suitability predictions and knowledge of underlying drivers can also enable exploratory analysis into possible future scenarios of change.

Paucity of Online Information About Gender-Affirming Surgery Fellowships in the United States.

Despite growing demand for gender-affirming surgery (GAS), there are few formal GAS fellowships in the United States. Paucity of online information about GAS fellowships may discourage potential applicants and decrease the visibility of the field. Thus, it is important to analyze the existing online information about GAS fellowships to improve fellow recruitment and patient outcomes. To identify the number of GAS fellowship websites (GASFWs) and evaluate their robustness. Second, to report the social media presence of GAS fellowships. To identify GASFWs, existing databases sponsored by plastic surgery associations and Google query were used between April and May 2023. Thirty-five independent variables based on previously published data were evaluated for presence in a bivariate fashion on GASFWs. Accounts on popular social media websites were also identified by Google query. Website and social media analysis were also done for GAS fellowships that were offered by departments/specialties other than plastic surgery. In total, only 6 GASFWs associated with plastic surgery departments were identified and analyzed. Eight nonplastic surgery GASFWs were included for analysis. Overall, both categories of GASFWs were not robust; key information such as previous fellow listing and selection criteria was often missing. Furthermore, important topics specifically related to GAS such as community engagement and programmatic building are often not found on GASFWs either. In addition, none of the fellowships had any independent Facebook, Instagram, or Twitter. To ensure patient safety and quality outcomes, it is important to promote GAS by recruiting more applicants for specialized training beyond residency. With increased Internet use, improving GASFWs and social media presence as well as considering the use of a centralized database or match system can foster the growth of the field.

External power dynamics and international climate governance in a crises-constrained world

ABSTRACT This paper explores equity in the United Nations Framework Convention on Climate Change (UNFCCC) negotiations during a time of multiple overlapping global crises. Drawing on a combination of semi-structured interviews and a roundtable with key negotiators and observers engaged in the UNFCCC process during the COVID-19 pandemic as well as a collaborative ethnographic study and social media analysis on the 27th United Nations Climate Change Conference (COP27), we find that inequities within the UNFCCC process reflect the broader social and geopolitical inequities at international and intranational levels. Multiple intersecting crises reinforce and compound these inequities for particularly marginalized and vulnerable groups and slow progress in tackling climate change in an equitable manner. Applying a critical climate justice lens, we show that in order for the climate negotiations to be resilient to global crises, the process needs to go beyond a surface-level attempt at achieving justice through representation and move towards a more active shifting of power to poor and climate-vulnerable countries and populations.

Social Media Marketing at Islamic Higher Education: Reactions, Posts, and Brand Post Contents

Social media have used by Higher Education Institution (HEI) for marketing communication and promotion purpose. Thus, some studies show that social media as a marketing tool in universities has not been widely practiced in predominantly Muslim countries. This paper aims to show Islamic universities in Muslim countries in various regions use social media as marketing tools, with focus on platforms utilization, engagement with users, and content analysis based on brand post categories. The data collected from the number of social media followers, reactions, and posts from top 12 Islamic universities in Muslim countries based on rank released by UniRank in 2021 and analyse with the software FanpageKarma. The time frame (2021) was chosen because the pandemic Covid-19 at that time has risen the social media usage by users. This papers also offers information about content analysis for social media posts on Instagram and Facebook, and describe it based on the experience brand posts, brand community, and brand resonance.

Social Media Analytics of User Evaluation for Innovative Digital Cultural and Creative Products: Experiences Regarding Dunhuang Cultural Heritage

Social media platforms play an increasingly important role in cultural communication as society develops, attracting promotions and discussions about digital cultural and creative products (CACPs). This research investigates the cultural collaboration between Tencent and Dunhuang Research Academy (Dunhuang Academy) and analyzes user evaluation of integrating cultural heritage education into CACPs. We obtained data through Weibo and compared user evaluations and semantic social network analysis of digital CACPs, including interactive products, games, and music. Results indicated that users were more interested in landscapes, dubbing, and user-generated content (UGC) for interactive products, character versions, posters and skills for games, and singers and songs for concerts. Semantic social network analysis was also used to explore the Dunhuang CACP Circle. Scant studies evaluate the usefulness of integrating cultural heritage into different digital CACPs, especially in Asia. Our suggestions help promoters understand user needs for digital CACPs and better user experience and value.

Utilizing Technology Acceptance Model in Technical and Usability Evaluation of The Developed Tourism SMEs Social Media Analytics Tool

Utilizing Technology Acceptance Model in Technical and Usability Evaluation of The Developed Tourism SMEs Social Media Analytics Tool