Potential use of large language models for mitigating students’problematic social media use:ChatGPT as an example

The problematic use of social media has numerous negative impacts on individuals'daily lives,interpersonal relationships,physical and mental health,and more.Currently,there are few methods and tools to alleviate problematic social media,and their potential is yet to be fully realized.Emerging large language models(LLMs)are becoming increasingly popular for providing information and assistance to people and are being applied in many aspects of life.In mitigating problematic social media use,LLMs such as ChatGPT can play a positive role by serving as conversational partners and outlets for users,providing personalized information and resources,monitoring and intervening in problematic social media use,and more.In this process,we should recognize both the enormous potential and endless possibilities of LLMs such as ChatGPT,leveraging their advantages to better address problematic social media use,while also acknowledging the limitations and potential pitfalls of ChatGPT technology,such as errors,limitations in issue resolution,privacy and security concerns,and potential overreliance.When we leverage the advantages of LLMs to address issues in social media usage,we must adopt a cautious and ethical approach,being vigilant of the potential adverse effects that LLMs may have in addressing problematic social media use to better harness technology to serve individuals and society.

Validity,Reliability,and Measurement Invariance of the Thai Smartphone Application-Based Addiction Scale and Bergen Social Media Addiction Scale

Background:In recent years,there has been increased research interest in both smartphone addiction and social media addiction as well as the development of psychometric instruments to assess these constructs.However,there is a lack of psychometric evaluation for instruments assessing smartphone addiction and social media addiction in Thailand.The present study evaluated the psychometric properties and gender measurement invariance of the Thai version of the Smartphone Application-Based Addiction Scale(SABAS)and Bergen Social Media Addiction Scale(BSMAS).Method:A total of 801 Thai university students participated in an online survey from January 2022 to July 2022 which included demographic information,SABAS,BSMAS,and the Internet Gaming Disorder Scale-Short Form(IGDS9-SF).Results:Confirmatory Factor Analyses(CFAs)found that both the SABAS and BSMAS had a one-factor structure.Findings demonstrated adequate psychometric properties of both instruments and also supported measurement invariance across genders.Moreover,scores on the SABAS and BSMAS were correlated with scores on the IGDS9-SF.Conclusion:The results indicated that the SABAS and BSMAS are useful psychometric instruments for assessing the risk of smartphone addiction and social media addiction among Thai young adults.

Associations between Social Media Use and Sleep Quality in China:Exploring the Mediating Role of Social Media Addiction

Sleep quality is closely linked to people’s health,and during the COVID-19 pandemic,the sleep patterns of residents in China were notably poor.The lockdown in China led to an increase in social media use,prompting questions about its impact on sleep.Therefore,this study investigates the association between social media use and sleep quality among Chinese residents during the COVID-19 outbreak,highlighting the potential mediating role of social media addiction.Data were collected via questionnaires through a cross-sectional survey with 779 valid responses.Variance analysis was used to test for differences in social media use among different demographic variables.Bivariate correlation analysis was employed to explore the relationships between variables,while regression analysis investigated the correlations between various media factors and sleep quality.Additionally,Bootstrap sampling was utilized to analyze the potential mediating influence of social media addiction in the relationship between social media use and sleep.The study's findings reveal a significant correlation between social media use,particularly before bedtime,and sleep quality(p<0.01),with pre-sleep activity notably linked to poorer overall sleep scores(β=0.141,p=0.004).Although the daily use of social media did not directly impact most individuals’sleep quality,specific platforms like news apps,short video apps,dating apps,and content community platforms were associated with higher levels of social media addiction,subsequently negatively affecting sleep quality.Specifically,the use of news apps(B=0.068,95%CI[0.000,0.019]),short video apps(B=0.112,95%CI[0.001,0.031]),dating apps(B=0.147,95%CI[0.000,0.028]),and content community platforms(B=0.106,95%CI[0.001,0.028])was found to increase the risk of social media addiction,subsequently leading to adverse effects on sleep quality.The study underscores a notable link between social media use and sleep quality,suggesting that mindful social media habits,particularly before bedtime,and reducing addiction-associated apps could enhance sleep quality.

Social Media-Based Surveillance Systems for Health Informatics Using Machine and Deep Learning Techniques:A Comprehensive Review and Open Challenges

Social media(SM)based surveillance systems,combined with machine learning(ML)and deep learning(DL)techniques,have shown potential for early detection of epidemic outbreaks.This review discusses the current state of SM-based surveillance methods for early epidemic outbreaks and the role of ML and DL in enhancing their performance.Since,every year,a large amount of data related to epidemic outbreaks,particularly Twitter data is generated by SM.This paper outlines the theme of SM analysis for tracking health-related issues and detecting epidemic outbreaks in SM,along with the ML and DL techniques that have been configured for the detection of epidemic outbreaks.DL has emerged as a promising ML technique that adaptsmultiple layers of representations or features of the data and yields state-of-the-art extrapolation results.In recent years,along with the success of ML and DL in many other application domains,both ML and DL are also popularly used in SM analysis.This paper aims to provide an overview of epidemic outbreaks in SM and then outlines a comprehensive analysis of ML and DL approaches and their existing applications in SM analysis.Finally,this review serves the purpose of offering suggestions,ideas,and proposals,along with highlighting the ongoing challenges in the field of early outbreak detection that still need to be addressed.

Exploring impacts of COVID-19 on spatial and temporal patterns of visitors to Canadian Rocky Mountain National Parks from social media big data

COVID-19 posed challenges for global tourism management.Changes in visitor temporal and spatial patterns and their associated determinants pre-and peri-pandemic in Canadian Rocky Mountain National Parks are analyzed.Data was collected through social media programming and analyzed using spatiotemporal analysis and a geographically weighted regression(GWR)model.Results highlight that COVID-19 significantly changed park visitation patterns.Visitors tended to explore more remote areas peri-pandemic.The GWR model also indicated distance to nearby trails was a significant influence on visitor density.Our results indicate that the pandemic influenced tourism temporal and spatial imbalance.This research presents a novel approach using combined social media big data which can be extended to the field of tourism management,and has important implications to manage visitor patterns and to allocate resources efficiently to satisfy multiple objectives of park management.

Analyzing topics in social media for improving digital twinning based product development

Digital twinning enables manufacturers to create digital representations of physical entities,thus implementing virtual simulations for product development.Previous efforts of digital twinning neglect the decisive consumer feedback in product development stages,failing to cover the gap between physical and digital spaces.This work mines real-world consumer feedbacks through social media topics,which is significant to product development.We specifically analyze the prevalent time of a product topic,giving an insight into both consumer attention and the widely-discussed time of a product.The primary body of current studies regards the prevalent time prediction as an accompanying task or assumes the existence of a preset distribution.Therefore,these proposed solutions are either biased in focused objectives and underlying patterns or weak in the capability of generalization towards diverse topics.To this end,this work combines deep learning and survival analysis to predict the prevalent time of topics.We propose a specialized deep survival model which consists of two modules.The first module enriches input covariates by incorporating latent features of the time-varying text,and the second module fully captures the temporal pattern of a rumor by a recurrent network structure.Moreover,a specific loss function different from regular survival models is proposed to achieve a more reasonable prediction.Extensive experiments on real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods.

Integrating Neighborhood Geographic Distribution and Social Structure Influence for Social Media User Geolocation

Geolocating social media users aims to discover the real geographical locations of users from their publicly available data,which can support online location-based applications such as disaster alerts and local content recommen-dations.Social relationship-based methods represent a classical approach for geolocating social media.However,geographically proximate relationships are sparse and challenging to discern within social networks,thereby affecting the accuracy of user geolocation.To address this challenge,we propose user geolocation methods that integrate neighborhood geographical distribution and social structure influence(NGSI)to improve geolocation accuracy.Firstly,we propose a method for evaluating the homophily of locations based on the k-order neighbor-hood geographic distribution(k-NGD)similarity among users.There are notable differences in the distribution of k-NGD similarity between location-proximate and non-location-proximate users.Exploiting this distinction,we filter out non-location-proximate social relationships to enhance location homophily in the social network.To better utilize the location-proximate relationships in social networks,we propose a graph neural network algorithm based on the social structure influence.The algorithm enables us to perform a weighted aggregation of the information of users’multi-hop neighborhood,thereby mitigating the over-smoothing problem of user features and improving user geolocation performance.Experimental results on real social media dataset demonstrate that the neighborhood geographical distribution similarity metric can effectively filter out non-location-proximate social relationships.Moreover,compared with 7 existing social relationship-based user positioning methods,our proposed method can achieve multi-granularity user geolocation and improve the accuracy by 4.84%to 13.28%.

Predicting Users’ Latent Suicidal Risk in Social Media: An Ensemble Model Based on Social Network Relationships

Suicide has become a critical concern,necessitating the development of effective preventative strategies.Social media platforms offer a valuable resource for identifying signs of suicidal ideation.Despite progress in detecting suicidal ideation on social media,accurately identifying individuals who express suicidal thoughts less openly or infrequently poses a significant challenge.To tackle this,we have developed a dataset focused on Chinese suicide narratives from Weibo’s Tree Hole feature and introduced an ensemble model named Text Convolutional Neural Network based on Social Network relationships(TCNN-SN).This model enhances predictive performance by leveraging social network relationship features and applying correction factors within a weighted linear fusion framework.It is specifically designed to identify key individuals who can help uncover hidden suicidal users and clusters.Our model,assessed using the bespoke dataset and benchmarked against alternative classification approaches,demonstrates superior accuracy,F1-score and AUC metrics,achieving 88.57%,88.75%and 94.25%,respectively,outperforming traditional TextCNN models by 12.18%,10.84%and 10.85%.We assert that our methodology offers a significant advancement in the predictive identification of individuals at risk,thereby contributing to the prevention and reduction of suicide incidences.

An Adaptive Hate Speech Detection Approach Using Neutrosophic Neural Networks for Social Media Forensics

Detecting hate speech automatically in social media forensics has emerged as a highly challenging task due tothe complex nature of language used in such platforms. Currently, several methods exist for classifying hatespeech, but they still suffer from ambiguity when differentiating between hateful and offensive content and theyalso lack accuracy. The work suggested in this paper uses a combination of the Whale Optimization Algorithm(WOA) and Particle Swarm Optimization (PSO) to adjust the weights of two Multi-Layer Perceptron (MLPs)for neutrosophic sets classification. During the training process of the MLP, the WOA is employed to exploreand determine the optimal set of weights. The PSO algorithm adjusts the weights to optimize the performanceof the MLP as fine-tuning. Additionally, in this approach, two separate MLP models are employed. One MLPis dedicated to predicting degrees of truth membership, while the other MLP focuses on predicting degrees offalse membership. The difference between these memberships quantifies uncertainty, indicating the degree ofindeterminacy in predictions. The experimental results indicate the superior performance of our model comparedto previous work when evaluated on the Davidson dataset.

Spatial-temporal Patterns of Urban Parks’Effects on the Sentiments and Their Associated Factors Based on Social Media Data——a Case Study in Beijing

As the pivotal green space,urban parks play an important role in urban residents’daily activities.Thy can not only bring people physical health,but also can be more likely to elicit positive sentiment to those who visit them.Recently,social media big data has provided new data sources for sentiment analysis.However,there was limited researches that explored the connection between urban parks and individual’s sentiments.Therefore,this study firstly employed a pre-trained language model(BERT,Bidirectional Encoder Representations from Transformers)to calculate sentiment scores based on social media data.Secondly,this study analysed the relationship between urban parks and individual’s sentiment from both spatial and temporal perspectives.Finally,by utilizing structural equation model(SEM),we identified 13 factors and analyzed its degree of the influence.The research findings are listed as below:①It confirmed that individuals generally experienced positive sentiment with high sentiment scores in the majority of urban parks;②The urban park type showed an influence on sentiment scores.In this study,higher sentiment scores observed in Eco-parks,comprehensive parks,and historical parks;③The urban parks level showed low impact on sentiment scores.With distinctions observed mainly at level-3 and level-4;④Compared to internal factors in parks,the external infrastructure surround them exerted more significant impact on sentiment scores.For instance,number of bus and subway stations around urban parks led to higher sentiment scores,while scenic spots and restaurants had inverse result.This study provided a novel method to quantify the services of various urban parks,which can be served as inspiration for similar studies in other cities and countries,enhancing their park planning and management strategies.

Explosion of research on psychopathology and social media use after COVID-19:A scientometric study

BACKGROUND Despite advances in research on psychopathology and social media use,no comprehensive review has examined published papers on this type of research and considered how it was affected by the coronavirus disease 2019(COVID-19)outbreak.AIM To explore the status of research on psychopathology and social media use before and after the COVID-19 outbreak.METHODS We used Bibliometrix(an R software package)to conduct a scientometric analysis of 4588 relevant studies drawn from the Web of Science Core Collection,PubMed,and Scopus databases.RESULTS Such research output was scarce before COVID-19,but exploded after the pandemic with the publication of a number of high-impact articles.Key authors and institutions,located primarily in developed countries,maintained their core positions,largely uninfluenced by COVID-19;however,research production and collaboration in developing countries increased significantly after COVID-19.Through the analysis of keywords,we identified commonly used methods in this field,together with specific populations,psychopathological conditions,and clinical treatments.Researchers have devoted increasing attention to gender differences in psychopathological states and linked COVID-19 strongly to depression,with depression detection becoming a new trend.Developments in research on psychopathology and social media use are unbalanced and uncoordinated across countries/regions,and more indepth clinical studies should be conducted in the future.CONCLUSION After COVID-19,there was an increased level of concern about mental health issues and a changing emphasis on social media use and the impact of public health emergencies.

Location Prediction from Social Media Contents using Location Aware Attention LSTM Network

Location prediction in social media,a growing research field,employs machine learning to identify users' locations from their online activities.This technology,useful in targeted advertising and urban planning,relies on natural language processing to analyze social media content and understand the temporal dynamics and structures of social networks.A key application is predicting a Twitter user's location from their tweets,which can be challenging due to the short and unstructured nature of tweet text.To address this challenge,the research introduces a novel machine learning model called the location-aware attention LSTM(LAA-LSTM).This hybrid model combines a Long Short-Term Memory(LSTM) network with an attention mechanism.The LSTM is trained on a dataset of tweets,and the attention network focuses on extracting features related to latitude and longitude,which are crucial for pinpointing the location of a user's tweet.The result analysis shows approx.10% improvement in accuracy over other existing machine learning approaches.

Exploring the Reasons for Selfie-Taking and Selfie-Posting on Social Media with Its Effect on Psychological and Social Lives:A Study among Indian Youths

‘Selfie’taking was introduced to the common people by smartphones and has become a common practice across the globe in no time.With technological advancement and the popularity of smartphones,selfie-taking has grown rapidly within a short time.In light of the new trend set by the generation,this study aimed to explore reasons for selfie-taking and selfie-posting on social media and their effects on the social and psychological lives of young adults.A purposive sampling method was adopted to select 20 Indian citizens,between 18 and 24 years.The data were collected through semi-structured interviews and analysed using thematic analysis.Selfie-taking and posting on social media give positive feelings,and it acts as a mood modifier dependent mostly on the favourability and feedback about the post which in turn affects emotions and self-satisfaction.

A Study on the Influence of Social Media Use on Psychological Anxiety among Young Women

To explore the relationship between social influence,social comparison,clarity of self-concept,and psychological anxiety among young women during their usage of social networking sites,our study selected 338 young women aged 14-34 from the social site platforms of Little Red Book and Weibo for questionnaire surveys.The Passive Social Network Utilization Scale,Social Comparison Scale(SCS),Social Influence Questionnaire,Self-Concept Clarity Scale(SCCS),and Generalized Anxiety Disorder Scale(GAD-7)were employed to measure the subjects.Our results show that the frequency of passive social media use is positively related to the level of psychological anxiety.Social comparison,social influence,and unclear self-concepts under social media use are negatively predictive of psychological anxiety.The chain mediation effects indicate that social comparison and social influence under social media use negatively predict the clarity of self-concept,thus having a negative impact on the psychological health of young women.Therefore,young women should strengthen their self-concepts,control their frequency of social media usage,avoid addiction,and pay special attention to their frequency of passive use,in order to protect their psychological health.Our study provides some practical implications and insights regarding the relationship between young women’s social media use and psychological health.

The Impact of Social Media on Dietary Behaviors and Body Image of College Students: A Qualitative Approach

Background: The use of social media platforms for health and nutrition information has become popular among college students. Although social media made information readily accessible in different formats, nutritional misinformation promoted by influencers and non-experts caused negative impact on diet behavior and perception of body image. Previous research indicated that extensive use of social media was positively linked to disordered eating behaviors. Social media platforms like Facebook and Instagram that allow users to follow celebrities intensified exposure to influencers’ messages and images and resulted in negative moods and body dissatisfaction. Objective: This paper aims to explore the impact of social media on college students’ dietary behaviors and body image. Participants: 18 undergraduate students from a public university in the Southern United States were recruited through a mass email. Methods: A cross-sectional qualitative study of three focus groups was conducted. The focus groups were based on guiding open-ended questions. Atlas.ti was used to code and analyze the data using inductive and deductive codes. Results: Three main themes were identified. The conditions theme included elements that explain why and how social media influences the participants’ actions. The actions theme included eating behavior, physical activity, and dietary supplement intake. The consequences theme describes anticipated or actual outcomes of actions such as body image and ideal weight. Conclusions: Social media has had a negative influence on diet behaviors and a positive influence on physical activity. Evidence-based nutrition and weight management information is needed to thwart potential misinformation.

User Profile & Attitude Analysis Based on Unstructured Social Media and Online Activity

As social media and online activity continue to pervade all age groups, it serves as a crucial platform for sharing personal experiences and opinions as well as information about attitudes and preferences for certain interests or purchases. This generates a wealth of behavioral data, which, while invaluable to businesses, researchers, policymakers, and the cybersecurity sector, presents significant challenges due to its unstructured nature. Existing tools for analyzing this data often lack the capability to effectively retrieve and process it comprehensively. This paper addresses the need for an advanced analytical tool that ethically and legally collects and analyzes social media data and online activity logs, constructing detailed and structured user profiles. It reviews current solutions, highlights their limitations, and introduces a new approach, the Advanced Social Analyzer (ASAN), that bridges these gaps. The proposed solutions technical aspects, implementation, and evaluation are discussed, with results compared to existing methodologies. The paper concludes by suggesting future research directions to further enhance the utility and effectiveness of social media data analysis.

Perception,use of social media,and its impact on the mental health of Indian adolescents:A qualitative study

BACKGROUND Mental illness is a health challenge faced by adolescents that has grown worse after the Coronavirus disease 2019 pandemic.Research on social media and young people’s mental health has recently increased,and numerous studies have examined whether frequent use of social media is linked to issues such as anxiety,stress,depression,eating disorders,insomnia,frustration,feeling alone,and externalizing problems among adolescents.This influence of social media on adolescents’lives is clear,with many platforms like Facebook,Instagram,and YouTube playing an important role in daily interactions and self-expression.Even though social media offers numerous benefits,such as connectivity and information sharing,excessive usage can have detrimental effects on mental health,particularly among adolescents.AIM To study the impact of social media on the mental wellbeing of adolescents,and the associated potential dangers in India.METHODS A total of 204 adolescents aged 14 years to 23 years were included in the study.This study explored the intricate relationship between social media usage and adolescent mental health in India.The study employs a cross-sectional survey design to capture a snapshot of adolescent mental health and social media usage patterns.Data collection involved administering structured questionnaires and the analysis utilized quantitative methods,including descriptive statistics.RESULTS Excessive use of social media is correlated with increased stress,anxiety,and depression.Adolescents engage in compulsive behaviors such as scrolling in the middle of the night,which negatively impacts their mental and physical health,and leads to significant sleep disruption.Findings from the study aim to provide insights into the current state of adolescent mental health and inform strategies to promote positive wellbeing in the Indian population.CONCLUSION The study underscores the need for further research to better understand the complex interplay between social media and adolescent mental health,and need for effective strategies to combat online harassment.

Making the case for the evolving role of social media in health professions education and a literature review on the application of some in ophthalmology

Background and Objective:Social media(SoMe)has emerged as a tool in health professions education(HPE),particularly amidst the challenges posed by the coronavirus disease 2019(COVID-19)pandemic.Despite the academia’s initial skepticism SoMe has been gaining traction in supporting learning communities,and offering opportunities for innovation in HPE.Our study aims to explore the integration of SoMe in HPE.Four key components were outlined as necessary for a successful integration,and include designing learning experiences,defining educator roles,selecting appropriate platforms,and establishing educational objectives.Methods:This article stemmed from the online Teaching Skills Series module on SoMe in education from the Ophthalmology Foundation,and drew upon evidence supporting learning theories relevant to SoMe integration and models of education.Additionally,we conducted a literature review considering Englishlanguage articles on the application of SoMe in ophthalmology from PubMed over the past decade.Key Content and Findings:Early adopters of SoMe platforms in HPE have leveraged these tools to enhance learning experiences through interaction,dialogue,content sharing,and active learning strategies.By integrating SoMe into educational programs,both online and in-person,educators can overcome time and geographical constraints,fostering more diverse and inclusive learning communities.Careful consideration is,however,necessary to address potential limitations within HPE.Conclusions:This article lays groundwork for expanding SoMe integration in HPE design,emphasizing the supportive scaffold of various learning theories,and the need of furthering robust research on examining its advantages over traditional educational formats.Our literature review underscores an ongoing multifaceted,random application of SoMe platforms in ophthalmology education.We advocate for an effective incorporation of SoMe in HPE education,with the need to comply with good educational practice.

Impact of Social Media Challenges on Pediatric Single-Use Detergent Sacs and Diphenhydramine Ingestions Reported to United States Poison Control Centers

Background: Social media platforms are popular among children and often feature challenges that become viral. Notably, the Tide Pod® and Benadryl® challenges encouraged viewers to ingest these substances for their visual appeal and hallucinogenic effects, respectively. This study aimed to assess the clinical impact and outcomes of single-use detergent sacs (SUDS) and diphenhydramine challenges on pediatric ingestions reported to United States (U.S.) Poison Control Centers (PCCs). Methods: We conducted a retrospective review of pediatric exposures reported to U.S. PCCs using data from the National Poison Data System (NPDS). The study included intentional single-substance ingestions of both brand-name and generic forms of SUDS and diphenhydramine among children ≤ 19 years. We compared the number of calls, clinical effects, disposition, and management strategies for SUDS (pre: 01/01/17 to 12/31/17 vs. post: 01/01/18 to 12/31/18) and diphenhydramine (pre: 08/01/19 to 07/31/20 vs. post: 08/01/20 to 07/31/21) ingestions 12 months before and after the introduction of the respective social media challenges. Differences in proportions were compared using the Chi-square test. Results: During the study period, 469 ingestions of SUDS and 5,702 ingestions of diphenhydramine were reported. Post-challenge periods saw an increase in both SUDS (pre: 82 vs. post: 387;372% increase) and diphenhydramine ingestions (pre: 2,672 vs. post: 3,030;13% increase). While there were no significant changes in moderate or major clinical outcomes, hospitalizations increased post-challenge for both SUDS [pre: 4 (4.9%) vs. post: 33 (8.5%);p = 0.25] and diphenhydramine [pre: n = 904 (33.8%) vs. post: 1,190 (39.3%);p Conclusion: Pediatric ingestions reported to U.S. PCCs and hospitalizations increased coinciding with the introduction of Tide Pod® and Benadryl® challenges. While causality cannot be definitively established, it is essential for pediatricians and parents to be aware of these challenges and educate vulnerable children about the harmful effects of participation in such challenges.

Detection of Knowledge on Social Media Using Data Mining Techniques

In light of the rapid growth and development of social media, it has become the focus of interest in many different scientific fields. They seek to extract useful information from it, and this is called (knowledge), such as extracting information related to people’s behaviors and interactions to analyze feelings or understand the behavior of users or groups, and many others. This extracted knowledge has a very important role in decision-making, creating and improving marketing objectives and competitive advantage, monitoring events, whether political or economic, and development in all fields. Therefore, to extract this knowledge, we need to analyze the vast amount of data found within social media using the most popular data mining techniques and applications related to social media sites.