Social Media Data Mining Research Articles

Social Media Data Mining in Public Relations Research

ABSTRACT Data mining represents a suite of data collection, management, and analysis approaches to elicit novel findings from large behavioral data sets. Prior to collecting data, researchers should define the population and consider whether a sample is sufficient. Especially large data sets may require sophisticated data management approaches such as database architectures. Computational resources likewise facilitate an array of cross-sectional and longitudinal analyses. While data mining is not appropriate for every research problem, it constitutes an invaluable set of research techniques that is well-suited to the online domain, making it a vital resource for PR researchers to employ in the future.

Public Participation Monitoring: Social Media Data Mining and Analysis of User Engagement Patterns

Social Media Platforms (SMP) like Twitter and Facebook have become public influencing medium in today’s digital age which facilitate community interactions. These necessitates the monitoring of public participation in these SMP. This work performs such an study by examining the user engagement patterns in social media in Indonesia during the national elections (#Pemilu2024), Ramadan celebrations (#Ramadan2024), and climate change discussions (#ClimateChange). The data for the study was collected during a period of six months from (January to June 2024) using event-specific hashtags and keywords. To identify the user engagement patterns datamining and Natural Language Processing (NLP) tools were utilized. The findings show that the Twitter platform has higher user engagement in morning with news updates and visual updates at evening. The Facebook show user engagement in afternoon with videos and evening engagement with shared articles. The Sentiment Analysis (SA) and network analysis was performed over the dataset and the findings have shown that higher positive sentiments towards elections and Ramadan but argumentative towards climate change discussions. The Twitter show rapid communication effectiveness compared to Facebook. Further the youth prefer faster update and older expect detailed content sharing.

Analyzing public sentiment on sustainability: A comprehensive review and application of sentiment analysis techniques

In the contemporary context of escalating environmental concerns, understanding public sentiment toward sustainability initiatives is crucial for shaping effective policies and practices. This research explores the efficacy of sentiment analysis in mining social media data to gauge public attitudes toward sustainability efforts. This study employs a variety of machine learning and deep learning models to perform sentiment analysis utilizing a dataset comprising tweets related to human perception towards environmental sustainability. The aim is to transform unstructured social media text into structured sentiment scores. The comparative analysis includes pre-trained sentiment analysis models like VADER, TextBlob, and Flair with traditional machine learning models such as Logistic Regression, SVM, Decision Tree, Naive Bayes, Random Forest, alongside advanced deep learning techniques like LSTM and pre-trained models BERT and GPT-2. Our results reveal significant variations in model performance, underscoring the importance of selecting appropriate sentiment analysis tools that align with the nuanced domain of sustainability. The study further emphasizes the role of transparent and reproducible research practices in advancing trustworthy AI applications. By providing insights into public opinions on sustainability, this research contributes to the broader discourse on leveraging AI to foster environmental responsibility and action. This work not only illustrates the potential of sentiment analysis in understanding public discourse but also highlights the critical need for tailored approaches that consider the specificity of the sustainability context.

How do consumers evaluate sponsorship in the aftermath of sport celebrity scandals? Uncovering evidence on social media data mining

PurposeThe purpose of this study is to investigate the effects of sport scandals on consumer perceptions of the associated sponsors and sport and to provide a typology of sport celebrity scandals to guide management response tactics.Design/methodology/approachThe study conducted four focus groups that were followed by social media data mining. A total of 8,289 consumer comments were collected from 147 websites, and a total of 224 comments were analyzed in terms of themes and frequency.FindingsThe research found the impact of sport scandals on consumer perceptions of sponsorship evaluations depended on whether the scandal was gender related scandal, recreational drug use, gender violence, unplanned and planned on-field scandals. Gender violence and planned on-field scandals can have an overwhelmingly negative impact on sponsorship evaluations, while unplanned on-field scandals may result in positive effects. Consumer empathy may influence the impact of recreational drug use, and the gender of the sport celebrity can influence the impact of unplanned on-field scandals.Research limitations/implicationsThis study contributes to sponsorship theory by indicating the type of scandal affects consumer perceptions of associated sponsors and sport.Practical implicationsThe findings may guide management to develop response tactics to sport scandals. The response tactics may be based on consumer perceptions of the impact of the scandal on the associated sponsors and sport. Sponsor and sport management response tactics may be perceived as a differentiation of the sponsor and sport brands. It may be necessary that sponsorship agreements included pre-determined response tactics that contribute to value formation in the local community.Originality/valueThis study contributes to sponsorship theory by indicating the type of scandal affects consumer perceptions of sponsorship evaluations. Two additional factors may impact these influences: consumer empathy and the gender of the sport celebrity.

Research on the Public’s Intention to Use Shared Autonomous Vehicles: Based on Social Media Data Mining and Questionnaire Survey

While the emergence of shared autonomous vehicles can be an effective solution to improve transport issues and achieve sustainable development, the benefits associated with shared autonomous vehicles can only be realized when the public intends to use them. Therefore, it is necessary to conduct an in-depth study on the public’s intention to use shared autonomous vehicles and identify the key influencing factors. This study mined social media data to obtain real public perceptions. A qualitative exploratory analysis was used to identify thematic variables regarding social media data on shared autonomous vehicles, from which a research model of the public’s intention to use SAVs was proposed. Then, a questionnaire survey was conducted, and the structural equation model and Bayesian network were used to analyze the questionnaire data quantitatively. The findings reveal how perceived risk, social information, trust, perceived usefulness, and personality traits affect the public’s intention to use shared autonomous vehicles, and how to enhance the public’s intention to use them. This study will enrich the research on traveler psychology in the context of intelligent travel and provide theoretical basis and decision support for future policies to promote shared autonomous vehicles.

Brand reputation enhancement through data mining in social media

The rise of social media has provided a large range of data such as user behavior data, social relationship data and so on, which can be used for business analysis, and the use of analysis tools can obtain complex, extensive and continuously followed social media data to help enhance the reputation of brand. In this paper, the definition and potential relationship between data analysis, social media and brand reputation and how the analysis results can help enhance business reputation will be introduced. This paper uses the research methodology of review, collecting and analyzing a large amount of literature, and draws a series of effective conclusions, and concludes that data mining of social media can effectively help business analysis to expand brand reputation, indicating that data mining analysis brings a significant improvement in effectiveness of marketing activities[1].

Social Media Data Mining and Mental Health Status Assessment Based on Sentiment Analysis

The usage of the word Power quality in recent times acquired intensified interest due to the complex industrial processes. The usage of intelligent tools to improve power quality is increasing day by day, as assumption of present day power system as a linear model is unsatisfactory. This paper deals with analysis of Differential Evolution (DE), Hybrid Differential Evolution (HDE) and Variable Scaling Hybrid Differential Evolution for harmonic reduction in the source current with optimal tuning of PI controller gain values. Shunt Active power Filter is one of the better solution to suppress the source current harmonics which are induced into power system because of nonlinear loads. Current controller called HBCC is considered for gating operation of switches in Voltage Source Inverter. The Intelligent tuned PQ theory is used for reference current generation. The then obtained compensating currents are injected at point of common coupling for current disturbance mitigation. Simulations of MATLAB/SIMULINK environment of the present work shows the efficacy.

ChatGPT’s applications in marketing: a topic modeling approach

PurposeChatGPT is a versatile technology with practical use cases spanning many professional disciplines including marketing. Being a recent innovation, however, there is a lack of academic insight into its tangible applications in the marketing realm. To address this gap, the current study explores ChatGPT’s application in marketing by mining social media data. Additionally, the study employs the stages-of- growth model to assess the current state of ChatGPT’s adoption in marketing organizations.Design/methodology/approachThe study collected tweets related to ChatGPT and marketing using a web-scraping technique (N = 23,757). A topic model was trained on the tweet corpus using latent Dirichlet allocation to delineate ChatGPT’s major areas of applications in marketing.FindingsThe topic model produced seven latent topics that encapsulated ChatGPT’s major areas of applications in marketing including content marketing, digital marketing, search engine optimization, customer strategy, B2B marketing and prompt engineering. Further analyses reveal the popularity of and interest in these topics among marketing practitioners.Originality/valueThe findings contribute to the literature by offering empirical evidence of ChatGPT’s applications in marketing. They demonstrate the core use cases of ChatGPT in marketing. Further, the study applies the stages-of-growth model to situate ChatGPT’s current state of adoption in marketing organizations and anticipate its future trajectory.

Public emotions and visual perception of the East Coast Park in Singapore: A deep learning method using social media data

Social media data mining has become a prevailing approach to understanding people’s emotional response to, and perception of, public spaces. Drawing on Google Maps Reviews’ text reviews and shared images, this study develops a deep learning framework that combines Transformer BERT and CNN-VGG models to explore public emotions and visual perception of the East Coast Park (ECP) in Singapore. The results show that (1) public emotions of the ECP are predominantly joy, with minor emotional fluctuations in 2020 due to the pandemic lockdown; (2) CNN-VGG image classification is an effective tool to capture people’s visual preferences of public spaces, (3) public emotions across 12 specific public spaces are predominantly joy and neutral, but the results of people’s visual preference exhibited considerable diversity, and (4) image data is mostly associated with joy or neutral emotions, generally indicating users’ satisfaction of ECP public space, and for this reason, there is a lack of sound base to identify environmental factors associated with people’s negative emotions. This study shows that the proposed deep learning framework is effective in using social media data to understand the public's emotional response to and visual preference of urban public spaces.

A Study on the Construction of Mental Health Indicators for College Students Based on Social Media Data Mining and the Evaluation of Their Intervention Effects

Abstract The development of social media has brought many tests to the mental health education of college students, and some college students have fallen into network addiction and dependence, which greatly affects their physical and mental health. The article uses microblogging social media as the source of students’ mental health data and preprocesses the data using data de-emphasis and Chinese word separation. It also analyzes the problematic manifestations of students’ mental health in colleges and universities, extracts students’ mental health indicators by using the TF-IDF algorithm, and realizes the recognition of students’ mental health topics by using the BTM model. The CNN-LSTM-ATT model was established by introducing the attention mechanism and LSTM model to assess the mental health status of college students. The data was analyzed in terms of students’ mental health characteristics predictive validation and used to develop intervention strategies for students’ mental health. The text length of students’ mental health is [1,22], which occupies 86.98% of all sentences, and the AUC value corresponding to the BTM model is 0.946, and the prediction accuracy of the CNN-LSTMATT model for the assessment of students’ mental health in colleges and universities can reach up to 97.62%. The social media data can clarify the mental health status of college students and realize the construction of students’ mental health intervention strategies from the dimensions of students’ media literacy and regulatory mechanisms.

Extracting Consumers’ Perceptions for Indonesian Spice Drinks Using Social Media Data Mining and Kansei Engineering

Local factors and global influences shape consumers’ perceptions through social media. In this regard, spice drinks as an agribusiness product have received increasing attention due to the Covid-19 pandemic. Therefore, understanding consumers’ perceptions is crucial for promoting the development of spice drinks. This study aims to (1) extract consumers’ perceptions of spice drinks based on discussions on social media using sentiment analysis and (2) classify the factors influencing their perceptions using factor analysis. The input dataset was obtained through Twitter data to acquire Kansei words. The results disclosed that Twitter could extract Kansei words and validate consumers’ perceptions of spice drinks as an agribusiness product. The sentiment analysis revealed 78% positive and 13% neutral tweets. Subsequently, an online survey was conducted among 495 respondents aged 18 to 41, distributed through various social media platforms from June to August 2022. The respondents were Generation Z and Millennials, with Generation Z referring to individuals born between 1997 and 2012 and Millennials born between 1981 and 1996. Factor analysis identified four principal components influencing consumers’ perceptions toward spice drinks: positive attitudes were associated with the quick, milky, mixed, healthy, quality, energy, fresh, warm, and safe; benefits were affiliated with the words enjoy, rest, life, smile, and story; quality concerned easy, flavour, and spicy; and sensory dealt with sweet, aroma, and bitter.

Enhancing Indonesian customer complaint analysis: LDA topic modelling with BERT embeddings

Social media data can be mining for recommended systems to know the best trends or patterns. The customers have the freedom to ask questions about the product, tell their demands, and convey their complaints through social media. By mining social media data, companies can gain valuable insights into customer preferences, opinions, and sentiments. This information can be utilized to improve products and services, tailor marketing strategies, and enhance overall customer satisfaction. Topic modelling is a text mining technique that extracts the content from the raw and unlabelled data. Latent Dirichlet Allocation is popular for topic modelling research cause flexible and adaptive. But that method has issues with sparsity, performs poorly when documented in the short text and there is no correlation between topics that are actually important in text data. BERT is Bidirectional Encoder Representations from Transformer is designed to pre-train deep bidirectional representations from unlabelled text. The result of this research proves that Latent Dirichlet Allocation and BERT can be arranged on the topic of Indonesian customer complaints. BERT-Base Multilingual Cased and LDA have the highest coherence score. The combination of BERT-Base Multilingual Uncased and LDA has the highest silhouette score. BERT Multilingual are potential for improving the LDA method for Indonesian customer complaints topic modelling.

Data mining of social media for urban resilience study: A case of rainstorm in Xi'an

Disasters throughout the world have highlighted the urgent need for studies on urban resilience capacities. Individuals' collective responses to disasters provide significant insights into their capacity for catastrophes adaptation and an invaluable perspective for demonstrating urban resilience. Previous research on urban resilience has rarely assessed resilience on an urban scale based on individuals' collective responses. As social media data are both a personal expression of users and a subjective reflection of their surroundings, we developed a social media-based data mining method to reflect urban resilience. We examined the urban resilience with the case of a rainstorm in Xi'an on July 24, 2016. The temporal patterns of public behavioral and emotional dimensions were chosen to examine how the city tolerated the disruption and returned to normal conditions. The public's behavioral reactions peaked during the rainstorm and lasted for a long time, revealing a delayed and hysteretic response. After 33 h, the holistic sentiment index repaired from 0.412 to the baseline standard of 0.713, indicating relatively feeble urban resilience to such rainstorm disasters. Our research revealed the viability of using social media to quantify a city's resilience, which is significantly beneficial in supplementing previous research.

Анализ рынка продукции северного оленеводства России на основе анализа массивов больших данных

Reindeer products have become an integral element of the culture of indigenous peoples in the Arctic region, playing a significant role in human adaptation to extreme climatic conditions. This study investigated the online sales offerings of reindeer products to identify the Far North regions in Russia that most actively use information and communication technologies to promote their products in the domestic regional and interregional markets. It also aimed to analyze the range of traditional Arctic food products. The research methodology drew on the theoretical approaches of the spatial economics by A. G. Granberg and the free trade theory by P. R. Krugman. Methods for analyzing big data based on social media data mining were applied. The study utilized messages on the Internet related to the sale of reindeer products in Russia’s Far North regions in 2021–2022. The novelty of this study lies in the implementation of big data collection and analysis methods. It required adapting the PolyAnalyst platform to the needs of a specific research field and improving the analysis methodology. The analysis of online sales offerings revealed the most active Arctic regions: the Murmansk region, the Yamalo-Nenets Autonomous Okrug, the Komi Republic, and the Chukotka Autonomous Okrug. The growing interest in the Arctic has contributed to the formation of a wide range of ready-made dishes and venison processing methods, also becoming a catalyst for growth in Arctic food tourism. This creates important conditions for the economic growth of rural Arctic territories. Online platforms expand opportunities for Arctic ethnic entrepreneurship by overcoming the relative isolation of Arctic economic systems and providing a venue for selling products on the Internet. Consequently, future research prospects involve using big data analysis of the reindeer husbandry market to develop measures for managing the sales of reindeer products.

Patients' and caregivers' perceptions of bariatric surgery: A France and United States comparative infodemiology study using social media data mining.

People are conversing about bariatric surgery on social media, but little is known about the main themes being discussed. To analyze discussions regarding bariatric surgery on social media platforms and to establish a cross-cultural comparison of posts geolocated in France and the United States. Posts were retrieved between January 2015 and April 2021 from general, publicly accessed sites and health-related forums geolocated in both countries. After processing and cleaning the data, posts of patients and caregivers about bariatric surgery were identified using a supervised machine learning algorithm. The analysis dataset contained a total of 10,800 posts from 4,947 web users in France and 51,804 posts from 40,278 web users in the United States. In France, post-operative follow-up (n = 3,251, 30.1% of posts), healthcare pathways (n = 2,171, 20.1% of the posts), and complementary and alternative weight loss therapies (n = 1,652, 15.3% of the posts) were among the most discussed topics. In the United States, the experience with bariatric surgery (n = 11,138, 21.5% of the posts) and the role of physical activity and diet in weight-loss programs before surgery (n = 9,325, 18% of the posts) were among the most discussed topics. Social media analysis provides a valuable toolset for clinicians to help them increase patient-centered care by integrating the patients' and caregivers' needs and concerns into the management of bariatric surgery.

'The fall of a dry leaf is a warning to the green ones': Exploring the Twitter ban and the impending dangers of data politics, algorithmic governance, and mass surveillance in Nigeria

For many years, everyday Nigerians, activists, community advocates, political enthusiasts, human rights leaders, and groups saw and used social media, especially Twitter as their safe haven and a tool that gave them the unmitigated opportunities to air their opinions on topical issues of national interest, criticize the government of the day and speak truth to power — until 4 June 2021 when the Nigerian government suspended Twitter after the social media giant deleted a controversial tweet by President Muhammadu Buhari. That event is the thrust for this study as we believe that this newly realized understanding of the power of restrictive Internet policies could be a conduit for other technologically enhanced political and corrupt bureaucratic and, questionable practices such as the use of big data spying tools, digitally inclined electoral manipulation, and mass surveillance tools. As a result, we argue that the Twitter ban could be the beginning of digital authoritarianism in Nigeria. We explore the impending dangers of a dictatorial digital toolkit such as social media data mining and computational politics in social engineering with examples to buttress from patterns of foreign regimes.

Do we need to mine social media data to detect exotic vertebrate-pest introductions?

Invasive alien species are responsible for considerable biodiversity loss and environmental damage. Timely detection of new incursions is critical in preventing novel populations establishing. Citizen reports currently account for the majority of alien species detections, arising from the massive observation effort that the physical and digital ‘eyes and ears’ of citizens provide, in combination with crowd-sourced species identification. Because the reporting of alien species sightings is generally not mandatory, there is interest in whether mining social media data via image recognition and/or natural language processing can improve on existing passive citizen surveillance in a cost-effective manner. Here, we illustrate, using examples from Australia, how citizen surveillance for most vertebrate groups appears to currently be effective using existing voluntary reporting mechanisms. Where citizen surveillance is currently ineffective, for reasons of inadequate sampling, data mining of social media feeds will be similarly affected. We argue that mining citizens’ social media data for evidence of invasive alien species needs to demonstrate not only that it will be an improvement on the business as usual case, but also that any gains achieved cannot be achieved by alternative approaches. We highlight the potential role of education in increasing the surveillance effectiveness of citizens for detecting and reporting sightings of alien species. Should data mining of social media platforms be pursued, we note that the scale of the task in terms of the potential number of exotic vertebrate species to be classified is very large. The expected number of false positive classifications would present a considerable workload to process, possibly undermining the efficiency rationale for the use of data mining. Hence, prioritisation is needed, and we illustrate how the number of species to be classified can be reduced considerably. If we are to deploy data mining and analysis of social media data to help with detecting introductions of invasive alien species, we need to conduct it in a manner where it adds value and is trusted.

Enhancing Customer Relationship Management through Sentiment Analysis and Social Media Data Mining

Customer Relationship Management (CRM) is a crucial aspect of modern business that enables companies to maintain healthy relationships with their customers. In today's digital age, customers interact with companies through multiple channels, including social media, email, and phone. Therefore, analyzing customer feedback and sentiment has become increasingly important in understanding their needs and improving the overall customer experience. To this end, this work proposes a new system that applies deep learning for sentiment analysis in a way that improves the performance of CRM by analyzing customer feedback from various sources, companies can gain valuable insights into customer needs and preferences and identify areas for improvement in their products and services. Then, we present a case study of a company that implemented the proposed system in its CRM strategy. The results showed that our system could improve customer satisfaction and retention rates and enable the company to identify and address customer concerns more efficiently.Our approach can be applied as a powerful tool to enable companies to gain valuable insights into customer needs and preferences, identify areas for improvement in their products and services, and develop targeted marketing campaigns and personalized communication strategies.

An efficient hybrid stock trend prediction system during COVID-19 pandemic based on stacked-LSTM and news sentiment analysis

The coronavirus is an irresistible virus that generally influences the respiratory framework. It has an effective impact on the global economy specifically, on the financial movement of stock markets. Recently, an accurate stock market prediction has been of great interest to investors. A sudden change in the stock movement due to COVID -19 appearance causes some problems for investors. From this point, we propose an efficient system that applies sentiment analysis of COVID-19 news and articles to extract the final impact of COVID-19 on the financial stock market. In this paper, we propose a stock market prediction system that extracts the stock movement with the COVID spread. It is important to predict the effect of these diseases on the economy to be ready for any disease change and protect our economy. In this paper, we apply sentimental analysis to stock news headlines to predict the daily future trend of stock in the COVID-19 period. Also, we use machine learning classifiers to predict the final impact of COVID-19 on some stocks such as TSLA, AMZ, and GOOG stock. For improving the performance and quality of future trend predictions, feature selection and spam tweet reduction are performed on the data sets. Finally, our proposed system is a hybrid system that applies text mining on social media data mining on the historical stock dataset to improve the whole prediction performance. The proposed system predicts stock movement for TSLA, AMZ, and GOOG with average prediction accuracy of 90%, 91.6%, and 92.3% respectively.

Sentiment Analysis of Texts on Public Health Emergencies Based on Social Media Data Mining.

Background Since the COVID-19 pandemic, social media has become an important arena for the public to transmit and exchange messages, feelings, opinions, and information about the epidemic. In the era of social media, many UGC contents from self-media and various information about the epidemic on social media have strong emotional colors. These contents are not only rich in resources for text sentiment analysis but also reveal the laws and characteristics of the evolution of users' emotional tendencies in public health emergencies. It even ties together the interaction between media content and society. Objective As the Sina Weibo platform's characteristics of communication are real-time, open, and “many-to-many,” the objective of this study is to collect Weibo-blog contents tagged with the outbreak of COVID-19 in a certain metropolis in China and analyze the emotional evolution situation of Weibo-blogs of the unexpected public health emergency involved. This will provide a dynamic understanding of the mechanisms underlying the evolution of emotional conditions in the context of public health emergencies. Methods This paper uses a Python crawler, the SnowNLP sentiment analysis model, and correlation analysis to calculate the emotional tendencies of the event “Covid-19 outbreak in a Chinese metropolis” on the Sina Weibo platform. The study was carried out in terms of the evolutionary stages of the event and the factors which induce it. Results This paper revealed characteristics of time-varying laws and dynamic propagation of users' emotional evolution in public health emergencies. (1) This study refers to the life cycle model of COVID-19, combined with the statistics of the time series of the quantities of Weibo-blog posting, and divides the law of the quantities of Weibo-blog posting changing with the event into three stages: outbreak period, stalemate period, and resolution period. (2) Users' emotional tendencies are changeable and unstable which are easily induced by various factors. (3) There is a significant positive correlation between the reported confirmed cases and the quantities of Weibo-blog posts. (4) Individual emotional tendencies will have a positive changing trend with the public's average emotional tendencies after the event occurs. (5) There is no correlation between reposts, comments, and Weibo-blog emotional tendencies. Conclusion The research found that, given staged evolution and repeated fluctuations of emotional tendencies, relevant departments should effectively use this law and set up different response plans according to different stages. In addition, what is highly coupled with users' emotional tendencies is not only the information about the virus but more large-scale infected by different intensities of emotions.