Social Media Analysis Research Articles

The Impact of Social Media Analytics on SME Strategic Decision Making

In the digital age, the emergence of social media has transformed the operational landscape of small and medium enterprises (SMEs). Recognized as a tool that generates comprehensive insights, social media analytics supports strategic decision-making. However, the concrete impact of social media analytics on strategic decisions in SMEs still requires further exploration. This study aims to assess the impact of social media analytics on strategic decision-making in SMEs, considering mediating variables such as organizational innovation and adaptability. Employing Structural Equation Modeling (SEM) with SmartPLS 4.1 software, the study analyzed data collected from 200 SMEs actively using social media for operations and marketing. The findings reveal that social media analytics significantly enhances organizational innovation and adaptability, which in turn positively affects strategic decision-making. This analysis underscores the importance of social media as a strategic resource in a dynamic business environment. The study provides valuable insights for SME owners on the critical role of social media analytics in enhancing strategic decisions. Theoretically, it extends the literature on social media analytics and strategic management within the SME context. Practically, the results serve as a foundation for SMEs to integrate social media analytics technology into their decision-making processes, thereby boosting adaptability and innovation in their operations.

Emotion detection using Word2Vec and convolution neural networks

<div>Emotion detection from text plays a very critical role in different domains, including customer service, social media analysis, healthcare, financial services, education, human-to-computer interaction, psychology, and many more. Nowadays, deep learning techniques become popular due to their capabilities to capture inherent complex insights and patterns from raw data. In this paper, we have used the Word2Vec embedding approach that takes care of the semantic and contextual understanding of text making it more realistic while detecting emotions. These embeddings act as input to the convolution neural network (CNN) to capture insights using feature maps. The Word2Vec and CNN models applied to the international survey on emotion antecedents and reactions (ISEAR) dataset outperform the models in the literature in terms of accuracy and F1-score as model evaluation metrics. The proposed approach not only obtains high accuracy in emotion detection tasks but also generates interpretable representations that contribute to the understanding of emotions in textual data. These findings carry significant implications for applications in diverse domains, such as social media analysis, market research, clinical assessment and counseling, and tailored recommendation systems.</div>

USING SOCIAL MEDIA ANALYTICS AND PARSING PROGRAMS TO IDENTIFY AND ANALYZE THE TARGET AUDIENCE

Social media analytics is the backbone of successful marketing. It allows you to accurately find and understand the target audience of the company. However, this requires analyzing a huge amount of publicly available data. This is where software tools come to the rescue, allowing such analysis to be carried out in real time. Nevertheless, there are a large number of software products on the market, each of which has a different set of functions - from complex products to highly specialized ones. A wide or vice versa narrow range of functions makes it difficult to choose a specific software solution for a specific task. For this reason, the main purpose of the article is to make a comparative analysis of the functions of the most popular social media analytics software tools designed to identify and analyze the target audience.

What makes the difference? Social media platforms and party characteristics as contextual factors for political parties’ use of populist political communication

Abstract Social media has contributed to the spread of populist political communication, yet we still lack systematic knowledge of the contextual factors affecting its use. In this study, we investigated how and to what degree platforms (Facebook, Instagram, Twitter) and party characteristics (populist vs. non-populist parties; political ideology) affected the use of populist communication by Norwegian political parties on social media during the 2021 national election campaign. Based on a tripartite conceptualisation of populist communication consisting of people-centrism, anti-elitism, and the exclusion of out-groups, we conducted a standardised content analysis of the official social media accounts of nine parties and their party leaders. Populist communication was overall rather rare, being most widespread on Facebook and least widespread on Twitter. Which parties used populist communication the most depended on the platform, and it was not always the populist Progress Party [Fremskrittspartiet] that communicated in the most populist manner. Parties located towards the fringes of the political party spectrum used more populist communication. Anti-elitism was more widespread among left-wing parties, and almost exclusively the right-wing Progress Party excluded out-groups.

Digital Channels of Employer Brand Formation

Relevance. In modern conditions of high competition in the labor market, new forms of work are becoming particularly relevant, in particular, the creation of an HR brand as a tool for maintaining the company's image and attracting employees. The development of digital technologies has allowed companies to use new channels of employer brand formation – digital. However, despite the existing need, the features of their use have not been fully studied. Social networks and career sites as the main platforms for the formation of an employer's brand are rapidly developing and transforming, which requires their comprehensive research. The purpose is to identify the features of the use of career sites and social networks as the main digital channels for the formation of an employer's brand. Objectives: to reveal the essence and identify the main elements of the employer's brand; to conduct a comparative study of the use of career sites and social networks of four Russian companies: Dodo Pizza, Gulfstream, Chulakov.ru, Exness. Methodology. The methodological basis of the study was the work of G. Martin, S. Hat Trick, T. Ambler, S. Burrow. As a technical tool for the study of social networks, the system of multifactorial analysis of social media "Cribrum" was used, the method of content analysis was used in the study of career websites of companies. Results. As a result of the study, the authors identified the main components of the HR brand broadcast by digital channels focused on basic and additional values. The analysis of digital channels by selected elements revealed the specifics of their use in the formation of the employer's brand. Career sites to a greater extent broadcast additional values of the company, forming a holistic positive image for the general public, without highlighting the target categories of recruiting. Social networks mainly demonstrate the basic values of the company, their content is more specific, focused on certain categories of recruiting. Conclusion. Creating a successful employer brand requires a competent combination of the digital channels considered, taking into account their specifics and the category of recruiting, which will allow HR branding to become a long-term HR strategy for attracting and retaining target groups of employees.

The flip side of social media: unveiling the effects of social media on mental health

Mental health, commonly known as behavioral health, is the psychological, emotional, and social well-being of an individual. It mostly affects a person’s ideas, emotions, behaviors, and relationships with other people. The idea that social media use and mental health are inextricably related appears to be the most intricate and varied. The effect of social media on mental health is a complicated topic with many moving parts. According to a countrywide survey carried out in India, as of 2023, approximately 67.5% of adults in the country utilize at least one social networking site; this percentage may be steadily increasing over time. Despite its numerous benefits, social media has also been connected to problems in society and poor mental health outcomes. People need to be aware of the potential risks of social media like disinformation, addiction, cyberbullying, data security and privacy concerns, and its possible effects on mental health. This review offers a thorough analysis of social media’s effects on mental health, and it demonstrates how crucial it is to develop a thoughtful and balanced relationship with our digital life to ensure that the advantages of connection do not come at the expense of our mental health.

Informal and revolutionary feminist placemaking.

Urban spaces, often emerging outside formal, recognized boundaries, underscore the pivotal role women play in shaping these environments. Despite the enduring influence of patriarchal and hierarchical structures that render these spaces overtly gendered, it is within these contexts that women's actions become particularly transformative. Drawing from feminist urban theories of the global south, this paper investigates informal placemaking, feminist urban activism, revolutionary placemaking, online protest movements, and the networks that support women's solidarity groups. Employing a mixed-methods approach that includes case studies, interviews with activists, and social media analysis, this research focuses on Iran, with a specific emphasis on the recent 'Women, Life, Freedom' movement. This study not only highlights how women navigate, contest, and reshape urban spaces through feminist urban activism and informal revolutionary placemaking but also anticipates the broader implications of these actions for urban planning and policy. By analyzing and comparing these case studies, we aim to uncover the commonalities, differences, challenges, and opportunities between informal/formal, state-led/bottom-up, and revolutionary feminist placemaking practices in Iran. The findings of this paper are expected to contribute valuable insights into the dynamics of feminist urbanism and suggest avenues for future research in enhancing the inclusivity and responsiveness of urban spaces to gendered needs and activism.

Who is responsible for fixing the food system? A framing analysis of media reactions to the UK's National Food Strategy

PurposeHigh levels of child obesity alongside rising stunting and the absence of a coherent food policy have deemed UK’s food system to be broken. The National Food Strategy (NFS) was debated intensely in media, with discussions on how and who should fix the food system.Design/methodology/approachUsing a mixed methods approach, the authors conduct framing analysis on traditional media and sentiment analysis of twitter reactions to the NFS to identify frames used to shape food system policy interventions.FindingsThe study finds evidence that the media coverage of the NFS often utilised the tropes of “culture wars” shaping the debate of who is responsible to fix the food system – the government, the public or the industry. NFS recommendations were portrayed as issues of free choice to shift the debate away from government action correcting for market failure. In contrast, the industry was showcased as equipped to intervene on its own accord. Dietary recommendations made by the NFS were depicted as hurting the poor, painting a picture of helplessness and loss of control, while their voices were omitted and not represented in traditional media.Social implicationsBritish media’s alignment with free market economic thinking has implications for food systems reform, as it deters the government from acting and relies on the invisible hand of the market to fix the system. Media firms should move beyond tropes of culture wars to discuss interventions that reform the structural causes of the UK’s broken food systems.Originality/valueAs traditional media coverage struggles to capture the diversity of public perception; the authors supplement framing analysis with sentiment analysis of Twitter data. To the best of our knowledge, no such media (and social media) analysis of the NFS has been conducted. The paper is also original as it extends our understanding of how media alignment with free market economic thinking has implications for food systems reform, as it deters the government from acting and relies on the invisible hand of the market to fix the system.

Business analytics in CRM: A comparative review of practices in the USA and Africa

In the dynamic landscape of global business, Customer Relationship Management (CRM) has emerged as a crucial strategy for organizations aiming to enhance customer satisfaction and loyalty. This study delves into the realm of Business Analytics (BA) within CRM, examining the diverse practices employed in the USA and Africa. The purpose is to identify similarities, differences, and potential areas for improvement, with the overarching goal of fostering more effective CRM strategies. The American business landscape, characterized by advanced technological infrastructure and matured data analytics capabilities, provides a fertile ground for sophisticated CRM practices. A comprehensive analysis of leading companies in the USA reveals a strong reliance on predictive analytics, machine learning, and artificial intelligence to glean actionable insights from vast datasets. Such approaches empower organizations to personalize customer experiences, optimize marketing strategies, and drive overall business growth. In contrast, the African business environment exhibits unique challenges and opportunities. While certain regions may face infrastructural constraints, innovative CRM practices tailored to local contexts are emerging. This study sheds light on the utilization of mobile technology, social media analytics, and localized data collection methods as crucial tools in the African CRM landscape. These adaptive strategies not only address challenges but also present opportunities for leapfrogging traditional CRM models. The comparative review uncovers key areas of convergence and divergence between the two regions, highlighting the need for a nuanced approach to global CRM strategies. By synthesizing insights from the USA and Africa, organizations can develop a more holistic understanding of effective CRM practices. This research contributes valuable insights to the ongoing discourse on global business analytics, offering a roadmap for organizations to navigate the intricacies of CRM implementation in diverse and dynamic markets.

Real-Time Sentiment Analysis

Natural Language Processing (NLP) is a computerized method to text interpretation that is founded on a set of ideas as well as a set of technology. This is a very active field of study and development, there is no universally accepted definition that satisfies everyone, but there are several elements that any intelligent person would consider a person's interpretation. Sentiment analysis or opinion mining is one of the important aspects of NLP (Natural Language Processing). In recent years, sentiment analysis has received a lot of attention. Sentiment analysis has a wide range of applications, including social media analytics, which simply means creating opinions for individuals on social media by analyzing their sentiments or ideas, which they express through text. It is also an example of how you can review customer feedback and responses. Thus identify the negative comments and reasons why the customers have issues with your product or service. Sentiment analysis enables you to respond to matters promptly before the customer leaves you altogether! In this paper, we aim to tackle the problem of Real-Time sentiment analysis, which is one of the dominant applications of sentiment analysis. Real-time sentiment analysis is an AI-powered solution to analyze the input provided by the user with the help of a pre-trained Machine Learning model. We have used a dataset of 1600000 tweets with 6 different attributes to build our model with the help of machine learning algorithms such as Naïve Bayesian classifier, Neural networks, and VADER. This paper is about the techniques and machine learning algorithms used to analyze the effectiveness of such models. Keywords: Sentiment Analysis; Machine Learning Algorithms; Naïve Bayesian classifier; Neutral Networks; VADER.

The role of social networks in communication in the scientific research community

Social networks have grown rapidly in recent years, enabling the application of social web technologies to the scientific process and creating platforms that enhance communication between researchers. The aim of this research is to go one step further and investigate whether the use of more general social networks, such as Twitter or Facebook, is also becoming more widespread for scientific research, thus contributing to the visibility of scientists and their collaborative networks. Social media analysis is carried out using the Brandwatch platform to assess the use of generalist social networks in research and compared with the use of scientific social networks through an online survey of university professors. The resulting conclusions show that scientific mentions in networks are rare and that, despite the importance of researchers having a profile in a social network, which allows them to give greater visibility to their results and receive feedback from their colleagues, many of them are still unaware of its usefulness.

Patriotic Agenda in the Information Flows of Russian Universities: Key Areas of Efficiency Improvement

The article presents the results of an empirical study of the patriotic agenda in the information flows of the largest Russian universities. The relevance of the study is determined by the set of global socio-political challenges facing the state at the current stage of development. Based on modern methods and tools of social media analytics, the authors determine the basic characteristics of thematic information flows in social media and make a comprehensive assessment of their effectiveness in interacting with target groups of students. Based on the results of the study the authors differentiate contexts and discourses regarding the level of engagement and personal involvement of young people in patriotic activities, as well as achievement practical results in such work. The main directions for improving the information work of higher educational institutions as subjects of formation and promotion of patriotic information flows in the new media should be focused on systemic activities that simultaneously consider the current external contexts and the needs of student youth.

Public conversation on vaccines during the covid-19 pandemic in Argentina, 2021-2022

In the face of declining vaccination coverage and the dissemination of health-related information, conversations in the public/mediatic digital sphere constitute a relevant study area for the field of health communication. Through a qualitative study based on the analysis of government publications, digital press, and social media, we characterize the public conversation on vaccines - in terms of topics, moments, axes, and framings in Argentina during the 2020-2021 period - marked by the debate on covid-19 vaccines. The results show that public conversation focused on covid-19 vaccination, structured in two distinct moments (vaccine production and vaccination campaign), and under moral framings grounded in vaccination as a care practice and science as an authoritative voice. Simultaneously, doubts about the safety and efficacy of vaccines shaped arguments of vaccine hesitancy, which we understand as part of extended practices associated with distrust towards institutions and reinterpretations of scientific knowledge and care.

Revolutionizing Research in Social Sciences: The Transformative Potential of ChatGPT

This paper explores ChatGPT's transformative impact on social science research, focusing on its language generation capabilities. It emphasizes the tool's proficiency in data analysis, idea generation, and questionnaire development, investigating its role in unravelling human behaviour, social dynamics, and cultural phenomena. Notably, ChatGPT integrates into social media analysis, illuminating trends and sentiment shifts. The study critically examines its contribution to streamlining qualitative analysis, highlighting the benefits and risks of automated coding. Ethical considerations, such as bias and algorithmic transparency, are rigorously scrutinized, advocating for interdisciplinary collaboration to fortify ethical foundations. The paper delves into ChatGPT's influence on policy-making, emphasizing caution in relying on AI-generated recommendations in healthcare and education. It calls for a balanced synergy between AI capabilities and human expertise, recognizing their unique strengths. In conclusion, the paper asserts the critical importance of fostering a symbiotic relationship between AI and human researchers as an essential factor for advancing research responsibly within the dynamic technological landscape.

Periacetabular osteotomy: an analysis of social media to determine the most common questions asked by the periacetabular osteotomy population

BackgroundThe Bernese Periacetabular Osteotomy (PAO) has become a popular surgery for fixing development dysplasia of the hip, yet the most common concerns of the PAO population remains ambiguous. The aim of this study was to investigate Facebook, Instagram and Twitter to further understand what the most common preoperative and postoperative questions patients undergoing PAO are asking. We hypothesized most questions would be asked by patients in the preoperative timeframe with regards to education surrounding PAO surgery.MethodsFacebook, Instagram and Twitter were queried consecutively from February 1, 2023 to November 23, 2011. Facebook was searched for the two most populated interest groups; “Periacetabular Osteotomy (PAO)” and “Periacetabular Osteotomy Australia”. Instagram and Twitter were queried for the most popular hashtags: “#PAOwarrior”, “#PAOsurgery”, “#periacetabularosteotomy”, “#periacetabularosteotomyrecovery”, and “#paorecovery”. Patient questions were categorized according to preoperative and postoperative questions. Questions were further placed into specific themes in their respective preoperative or postoperative question types.ResultsTwo thousand five hundred and fifty-nine posts were collected, with 849 (33%) posts containing 966 questions. Of the 966 questions, 443 (45.9%) and 523 (54.1%) were preoperative and postoperative questions, respectively. The majority of questions were postoperative complication related (23%) and symptom management (21%). Other postoperative questions included recovery/rehabilitation (21%), and general postoperative questions (18%). The most common preoperative questions were related to PAO education (23%). Rehabilitation (19%), hip dysplasia education (17%), and surgeon selection (12%) were other preoperative questions topics included. Most questions came from Facebook posts. Of 1,054 Facebook posts, 76% were either preoperative or postoperative questions and from the perspective of the patient (87%).ConclusionThe majority of patients in the PAO population sought advice on postoperative complications and symptom management. Some patients asked about education surrounding PAO surgery. Understanding the most common concerns and questions patients have can help providers educate patients and focus on more patient-relevant perioperative conversations.

Social media analysis of pain outcomes following targeted muscle reinnervation

AimTMR was developed to improve myoelectric prosthesis control for amputees; however, it has become an area of interest in pain modulation. Studies show evidence that this procedure alleviates chronic pain in amputees. The primary objective of this study is to utilize social media analysis to understand patients’ post-operative pain, satisfaction, and recovery time after TMR. MethodsData was collected from one Facebook group via posts and comments referencing TMR. Posts published between January 1st, 2020, and March 24th, 2023, were analyzed. Data collected included pain prior to surgery, pain in immediate post-op period, and how pain changed after surgery. Results43 individuals commented on their TMR experience. 31 had favorable surgical outcomes, 7 felt surgery worsened their pain or there was not significant change in their pain levels, and the remaining 5 commented during the initial post-operative period. 24 patients described their pain in the immediate post-operative period and 100% said that post-operative pain was worse than chronic pain. Of 28 authors who commented on overall reduction in chronic pain, 24 reported TMR reduced their pain, while 4 had no change or worsened pain. ConclusionsThe 24 patients who reported improvement in chronic pain aligns with current literature suggesting that TMR is a viable treatment option for pain. Current medical management of similar conditions leaves up to 80% of patients unsatisfied with pain control. This analysis supports the evidence that TMR is an effective treatment for patients who are experiencing post-amputation pain.

Place-oriented digital agency: Residents’ use of digital means to enhance neighbourhood change

The smart city literature mostly focusses on digital initiatives from above. However, digitalisation also reshapes the city from below. Residents use digital means and platforms to empower their agency in the city. This paper aims to explore how residents utilise digital tools to activate their agency and influence local politics. The paper focusses on one neighbourhood in the city of Tel Aviv where different groups of residents struggle to promote their desired political-spatial vision. The main question is whether digitalisation produces new forms of agency on the neighbourhood scale. The paper argues that: (1) digitalisation provides residents with new forms of connective action, creating digital networks at different scales, using representational practices and forming new spaces for political negotiation; (2) through these practices, they manage to influence the symbolic and political status of the neighbourhood and reframe the struggle over its character and future; (3) groups with higher digital agency gain wider visibility of their claims and needs with politicians, the media and public officials. Importantly, this does not only serve middle-class groups. (4) Ultimately, residents become predominant political actors through digital agency. Methodologically, this paper includes two methods: (i) interviews with residents and municipal workers and (ii) social media analysis and online ethnography. The conclusion elaborates the concept of place-oriented digital agency as a particular type of agency aimed at determining change in a specific locale.

Predictive Analytics in Mental Health Leveraging LLM Embeddings and Machine Learning Models for Social Media Analysis

The prevalence of stress-related disorders has increased significantly in recent years, necessitating scalable methods to identify affected individuals. This paper proposes a novel approach utilizing large language models (LLMs), with a focus on OpenAI's generative pre-trained transformer (GPT-3) embeddings and machine learning (ML) algorithms to classify social media posts as indicative or not of stress disorders. The aim is to create a preliminary screening tool leveraging online textual data. GPT-3 embeddings transformed posts into vector representations capturing semantic meaning and linguistic nuances. Various models, including support vector machines, random forests, XGBoost, KNN, and neural networks, were trained on a dataset of >10,000 labeled social media posts. The top model, a support vector machine, achieved 83% accuracy in classifying posts displaying signs of stress.

Sentiment Analysis of Finnish Twitter Discussions on COVID-19 During the Pandemic

With the outbreak of the COVID-19 pandemic, researchers have studied how people reacted on social media during the pandemic. Sentiment analysis has been leveraged to gain insight. However, much of the research conducted on both sentiment analysis and social media analysis of COVID-19 often focuses on widespread languages, such as English and Chinese. This is partly due to the scarcity of resources for natural language processing and sentiment analysis for morphologically complex and less prevalent languages such as Finnish. This paper aims to analyze sentiments on Twitter in the Finnish language during the COVID-19 pandemic. We manually annotate with sentiments a random sample of 1943 tweets about COVID-19 in Finnish. We use it to build binomial and multinomial logistic regression models with Lasso penalty by exploiting ngrams and two existing sentiment lexicons. We also build two similar models using an existing (pre-COVID-19) Twitter dataset for comparison. The best-performing model for the Finnish language is then used to determine the trends of positive, negative, and neutral opinions on a collection of tweets in Finnish extracted between April 21 and June 18, 2020. The best sentiment polarity prediction model for the Finnish language attain 0.785 AUC, 0.710 balanced accuracy, and 0.723 macro-averaged F1 for predicting positive and negative polarity (binomial classification), and 0.667 AUC, 0.607 balanced accuracy, and 0.475 F1 when adding neutral tweets (multinomial classification). On the other hand, the pre-COVID-19 model trained on the same number of tweets exhibits higher accuracy for the multinomial model (0.687 balanced accuracy, and 0.588 F1). We hypothesize that this loss of performance is due to the COVID-19 context that makes sentiment analysis of neutral tweets more difficult for the machine learning algorithm to predict. Running the model on all the extracted Finnish tweets, we observe a decrease in negativity and an increase in positivity over the observed time as the Finnish government lifts restrictions. Our results show that applying an existing general-purpose sentiment analyzer on tweets that are domain-specific, such as COVID-19, provides lower accuracy. More effort in the future needs to be invested in using and developing sentiment analysis tools tailored to their application domain when conducting large-scale social media analysis of specific medical issues, such as a global pandemic.

Unleashing the power of AI: a systematic review of cutting-edge techniques in AI-enhanced scientometrics, webometrics and bibliometrics

PurposeThe study aims to analyze the synergy of artificial intelligence (AI), with scientometrics, webometrics and bibliometrics to unlock and to emphasize the potential of the applications and benefits of AI algorithms in these fields.Design/methodology/approachBy conducting a systematic literature review, our aim is to explore the potential of AI in revolutionizing the methods used to measure and analyze scholarly communication, identify emerging research trends and evaluate the impact of scientific publications. To achieve this, we implemented a comprehensive search strategy across reputable databases such as ProQuest, IEEE Explore, EBSCO, Web of Science and Scopus. Our search encompassed articles published from January 1, 2000, to September 2022, resulting in a thorough review of 61 relevant articles.Findings(1) Regarding scientometrics, the application of AI yields various distinct advantages, such as conducting analyses of publications, citations, research impact prediction, collaboration, research trend analysis and knowledge mapping, in a more objective and reliable framework. (2) In terms of webometrics, AI algorithms are able to enhance web crawling and data collection, web link analysis, web content analysis, social media analysis, web impact analysis and recommender systems. (3) Moreover, automation of data collection, analysis of citations, disambiguation of authors, analysis of co-authorship networks, assessment of research impact, text mining and recommender systems are considered as the potential of AI integration in the field of bibliometrics.Originality/valueThis study covers the particularly new benefits and potential of AI-enhanced scientometrics, webometrics and bibliometrics to highlight the significant prospects of the synergy of this integration through AI.