Accurate Information Research Articles

Fighting Medical Misinformation: What Physician Leaders Need to Know

The dangerous rise of misinformation and disinformation about health and healthcare undermines the work of physicians and other healthcare workers. Physicians are well-positioned to counter inaccurate information because their patients put a high degree of trust in them. Strategies at the individual and organizational levels are discussed.

Use of chatgpt-4 to explain kawasaki disease to parents and paediatric trainees

Abstract Background Paediatric trainees and parents of Kawasaki disease (KD) patients may face challenges when managing the disease due to insufficient accessibility to KD information. Chat Generative Pre-Trained Transformer (ChatGPT) based on large language models may help explain KD information to paediatric trainees and patient parents. Purpose This study aims to determine the usefulness of Chat Generative Pre- Trained Transformer -4 (ChatGPT-4) in explaining Kawasaki Disease (KD) and its management to parents and paediatric trainees managing KD patients. Methods We created 2 sets of clinical scenarios. In the first set, ChatGPT-4 was instructed to respond to 10 questions based on enquiries from parents of KD patients. Responses were scored in terms of "factual accuracy", "coherence", "comprehensiveness", and "humaneness" by 3 paediatric cardiologists using Likert scale of 0-10. Readability were calculated using Flesch reading-ease test. In the second set, ChatGPT-4 was instructed to respond to 8 KD-related questions based on enquiries from paediatric trainees. Responses are graded based on "relevance", "reliability" and "comprehensiveness" using Likert scale of 0-10 by 3 paediatric cardiologists independently. Reviewers would determine whether major advice from chatGPT-4 would be adopted in clinical judgement. Results For parent-targeted responses, ChatGPT-4 achieved the highest scores in ‘humaneness’ (median 9.00, IQR 8.00 to 9.00) and ‘coherence’ (median 8.00, IQR 7.00 to 8.00). Inaccurate information regarding disease prognosis, actions as well as prescription of medications and surgery is found in 80% of scenarios. Missing information regarding long-term coronary complications, antiplatelet management and cardiac assessments is found in all 10 scenarios. Mean readability of parent-targeted responses is 71.70 ± 6.26, a readability level easily understood by 12-year-olds. For paediatrician-targeted responses, ChatGPT-4 achieved the highest scores in ‘relevance’ (median 9.50, IQR 7.25 to 9.0). Inaccurate information regarding coronary interventions, patient education and immunization recommendations is spotted in 37.5% of the scenarios. Missing information regarding patient education and stress imaging is found in 25% of the scenarios. All reviewers would adopt ChatGPT-4’s advice in 87.5% of the scenarios. Conclusions ChatGPT-4 has significant limitations in accuracy and lacks salient information when providing KD recommendations for parents and paediatric trainees.Performance in parent-targeted questionsPerformance in trainee-targeted question

External Interventions: Bluffing and Adaptive Learning in Civil Wars

ABSTRACT This paper examines the effectiveness of bluffing about external intervention in shaping civil war dynamics using an agent-based model. It argues that warring parties’ initial information levels about interveners and their learning processes determine the success of bluffing. The model explores three scenarios: 1) accurate initial expectations and informative signals 2) inaccurate initial information and uninformative signals and 3) heterogeneous information sets and varied signal updates. Findings suggest bluffing is most effective when both sides start with inaccurate expectations and update slowly. The model’s implications are analyzed through cases in El Salvador, the Warsaw Uprising and South Vietnam negotiations.

The role of ChatGPT on academic research: perspectives from filipino students across diverse educational levels

With the emergence of technology, artificial intelligence (AI) is introducing a new wave of remarkable tools and transformations in education. One such technological development is ChatGPT, a dialogue system designed to collect and organize information, which is then converted into text-based inputs to address user inquiries. There is also a clear trend in which many Filipino students increasingly use ChatGPT for academic research. Filipino students' growing usage of ChatGPT demands immediate attention to examine its role in academic research within the Philippine educational setting. Thus, this study examines how ChatGPT is used in academic research by exploring students' perspectives and analyzing its perceived benefits and challenges. A descriptive cross-sectional design was conducted in the Eastern Visayas region of the Philippines, explicitly targeting selected secondary and tertiary schools. A total of 316 students were involved in the study, selected through convenience sampling. Results revealed ChatGPT to be moderately useful for various aspects of academic research and moderately influential in the student's academic performance. Receiving additional information or resources, getting help with mechanics, writing, paraphrasing, and generating ideas were found to be the benefits of using ChatGPT. Nonetheless, students commonly encountered issues such as redundant, inadequate, and inaccurate information provided by ChatGPT and concerns regarding its accessibility and the potential for plagiarism. To optimize advantages and address possible concerns, academic institutions should establish concise guidelines and regulations for responsible student utilization of ChatGPT

Inaccurate Borrower Information and Credit Risk: Evidence from Marketplace Loans

Abstract Inaccurate borrower-provided information in marketplace loans is informative about credit risk. An inaccuracy index constructed from the consistency of loan amount with outstanding credit balance, roundness of reported income, and roundness of chosen loan amount predicts the likelihood of default, and the additional default risk is not compensated by higher interest. Inaccurate information is more prevalent in areas with lower social capital and weaker social norms. It is also lower among borrowers whose professions are considered less honest, and among borrowers with higher income uncertainty. These results suggest that inaccuracy is driven by both deliberate misreporting and genuine uncertainty. (JEL D12, D91, G23, G41)

Digital sustainability tracing in smallholder context: Ex-ante insights from the Peruvian cocoa supply chain

Global demand for sustainable agri-food products creates opportunities for smallholder farmers. But on-farm verification of sustainable practices is costly, making third-party certification inaccessible to many poor farmers. Digital technologies for tracing agri-food products from farm to fork could help: novel traceability systems, based on blockchain technology, can make data about on-farm practices transparently available to downstream stakeholders, enabling them to verify sustainability claims without external audits. There is limited understanding, however, of how such digital tracing systems fit local needs and capacities in smallholder contexts. Through a grounded theory approach, we explore the potential of digital traceability for sustainability monitoring in a case study in the Ucayali region of Peru. Based on interviews with local cocoa sector stakeholders, we identify two major challenges: first, setting up digital traceability systems requires investments that do not seem justified by corresponding increases in income. And second, relying on farmer-supplied data creates the risk of inaccurate information due to insufficient capacity as well as incentives for providing distorted data. Our findings suggest that strong cooperation along the supply chain is needed to ensure adequate return on farmer-side costs and investments. Focusing on sustainability metrics at the community level, in addition to the farm level, may be promising, as these metrics can be reliably collected by external stakeholders and add value beyond existing third-party certification standards. Our case study provides recommendations for local policy makers and supply chain stakeholders to develop inclusive digital sustainability tracing systems with smallholder farmers.

7056 Can ChatGPT Educate Multicultural Patients About Metabolic Syndrome?

Abstract Disclosure: G. Wu: None. E. Cheng: None. V.V. Toram: None. K. Rosen: None. A. Wong: None. W. Zhao: None. M. Del Buono: None. Background: Metabolic Syndrome, which affects Asians, is a major risk factor for diabetes. According to the National Institute of Health (NIH), 1 in 3 Americans have Metabolic Syndrome. Diabetes affects 30 million Americans, and 8 million more are undiagnosed. ChatGPT and Bard are Artificial Intelligence (AI) mediated LLMs launched on 11/30/2022 and 3/21/2023, respectively, that generate real-time conversational responses. Purpose: Can ChatGPT educate our multicultural patients about metabolic syndrome? Methods: 1. User prompt into ChatGPT and Bard: What is metabolic syndrome? I am a South Asian male, 40 years old, with a cholesterol level of 250 and a fasting blood sugar level of 120. The exact prompt was used with an Asian male as a substitute. 2. The prompt was translated into Telugu, Hindi, Simplified Chinese, and Traditional Chinese via Google Translate. 3. Flesch-Kincade (FK) method of ascertaining reading level was used. FK is used by the US Department of Education. Results: Flesch-Kincaid reading ease: ChatGPT: English=29.2, Telugu=60.1, Hindi=33.4, Chinese (Trad.)=14.5, Chinese (Simp.)=22.6 Bard: English=35.3, Telugu=52, Hindi=51.7, Chinese (Trad.)=52, Chinese (Simp.)=36.8 Language Group Comparison to English: ChatGPT: Indian Languages p=0.004; Chinese Languages p=0.081. Bard: Indian Languages p=0.007; Chinese Languages p=0.136. Of note, the Telegu response has one incorrect response. Conclusions: In conclusion, ChatGPT and Bard can provide factual responses based on English prompts. Foreign prompts can yield inaccurate information. Physicians and their teams still need to supervise patient usage. Presentation: 6/2/2024

Iterative control decoupling tuning for precision MIMO motion systems: A matrix update method

Control decoupling is the basic control step for precision MIMO (Multi-Input-Multi-Output) motion systems. After decoupling, the MIMO logical controlled plant can be diagonal dominant so that the control design for each DOF (Degree of Freedom) can be separately treated. However, due to the manufacturing tolerances and the assembling errors, the actual CoG (Center of Gravity) and actuator positions are inconsistent with the designed values. The nominal static control decoupling matrix is inaccurate, which significantly deteriorates the decoupling performance. To address the problem, this paper develops a matrix update based iterative control decoupling tuning method. Tuning with feedback control signals to achieve accurate tuning is its first distinct feature. By employing rigid-body model information to construct more accurate basis functions, fast tuning can also be achieved, especially for relatively low control bandwidth occasions. Differing from the feedforward compensation based iterative control decoupling tuning method, the matrix update method improves the dynamics of the logical controlled plant, does not increase the control complexity and is more robust to the inaccuracy of the model information. Experimental results on the short-stroke module of a precision motion stage which is the key subsystem of the lithographic projection lens testing system present significant control decoupling performance improvement (for example the peak value of the Rx-DOF servo error caused by the Z-DOF movement is reduced from 1.29 ×10−5 m to 3.19 ×10−6 m) after just two trials.

Compiling molecular evidence from a tetraploid rose genome into a near-saturated map for the identification of pigment-related genes

With their high economic value and cultural significance, modern roses are one of the most important ornamental plants. Because of their complicated genetic background and tetraploid nature, the creation of high-density genetic maps of roses has been a challenge that has slowed the pace of molecular breeding for modern roses. The current construction of tetraploid genetic maps based on existing diploid rose genomes could lead to inaccurate marker information and genotyping results. Therefore, we generated the first high-quality tetraploid genome of Rosa chinensis ‘Yunzheng Xiawei.’ Utilizing Illumina, PacBio, and Hi-C sequencing technologies, we assembled a genome of 858.59 Mb with 14 pseudo-chromosomes. Mode of inheritance analysis using PolyOrigin indicated that modern roses show both quadrivalent and bivalent pairing. Based on this reference genome, high-density genetic maps were constructed using MSTmap with nearly saturated markers. Quantitative trait locus (QTL) analysis was conducted using WinQTLCart and R/qtl for flavonoids and carotenoids, and 11 QTL clusters were identified. By combining the genome annotation, phylogenetic analyses, and gene expression analyses, we were able to identify several key genes related to flavonoid and carotenoid biosynthesis. This study provides the basis for further genetic analyses of highly heterozygous tetraploid roses and could facilitate the progress of marker-assisted selection in modern roses.

Exploring willingness to use adverse drug reaction reporting systems: a multicentre qualitative study in China based on the technology acceptance model and task-technology fit integration approach

BackgroundAdverse drug reaction (ADR) reporting systems are critical for monitoring and managing drug safety. However, various factors influence the willingness to use these systems. This study aimed to investigate the...

The role of large language models in interdisciplinary research: Opportunities, challenges and ways forward

Abstract Large language models (LLMs) are gaining importance in research as they offer many benefits. One often overlooked benefit is their potential to facilitate and support interdisciplinary research, which is key to addressing current global challenges, such as the twin crises of biodiversity loss and climate change. LLMs can help reduce the costs associated with knowledge transfer and bridge gaps between different fields of study. They can also be especially useful in helping ecologists understand and adopt powerful techniques common in other fields. However, using LLMs in research, especially for complex tasks, carries important risks, including the possibility of generating inaccurate information, which can lead to false conclusions. We recommend that researchers adhere to best practices when using LLMs for research by providing appropriate prompts and dividing complex tasks into smaller, more manageable tasks that facilitate learning and testing. Moreover, journals should implement policies to ensure that information and code generated using LLMs are properly validated. Academic programs should incorporate formal training in LLMs, equipping students and researchers with the necessary skills to use these tools more effectively and responsibly, including for interdisciplinary research.

빅 히스토리를 활용한 AI 기반 융합질문 생성 교육용 서비스 ‘OASIS’ 개발

This study aims to design an AI-based educational service using Big History to enhance convergence competency in secondary school students and to evaluate the effectiveness and satisfaction of the designed service, OASIS(Online AI-based Service for Inquiry Studies). Through three stages of model improvement, the core model OASIS was developed. Convergence competency tests were conducted on 128 first-year high school students before and after using OASIS. Additionally, the effectiveness and user satisfaction were evaluated by a user satisfaction survey conducted with the same students and 15 educational experts. OASIS utilizes ChatGPT to provide multidisciplinary information on input keywords, thereby enhancing interdisciplinary understanding. The service is structured to foster convergence competency through the creation of convergence inquiries and interactive activities. The results of the convergence competency tendency test and user satisfaction survey indicated that the use of OASIS helped enhance students' convergence competency and showed high satisfaction regarding the usefulness of information. However, limitations such as the inaccuracy of information and slow loading speeds were noted. Addressing these limitations could improve the service’s applicability in secondary education for fostering convergence.

Data is the fuel of generative artificial intelligence

TThe aim of the article is to present the generative technology of artificial intelligence and a general analysis of its achievements and technological limitations. In turn, the hypothesis is as follows: data is the main factor ensuring the development of generative AI. The identified research niche includes stimulants of this development, the need to clarify the concept of generative AI and the indication of the most frequently used sources and methods of obtaining data. At the beginning, the concept and genesis of artificial intelligence were explained, which was necessary to move on to further considerations regarding the analyzed generative artificial intelligence. The self-learning mechanisms used by this type of artificial intelligence are discussed, consisting mainly in the analysis of specific data sets, thanks to which computers learn things that have not been known before. The advantages of generative artificial intelligence were also indicated, including increased productivity, greater efficiency and high creativity. Part of the attention was also paid to the limitations of this technology, including inaccurate and fuzzy output information, uncritical analyzes and often biased conclusions, copyright infringement and high requirements for memory and computing power of computers. Two factors have been identified that have recently stimulated the development of generative intelligence, i.e. the growing computing power of computers and easy access to large data sets. The main subject of considerations are large data sets, dynamically and uncontrollably self-replicating in Internet servers. Today, data resources are collected very efficiently, including: in Big Data, Cloud Computing and Internet of Things technologies, and their use is almost cost-free and publicly available. It was enough to improve the technology of artificial neural networks, expand multi-layer machine learning and create deep learning for generative intelligence to gain enormous momentum and become a symbol of the beginning of the 21st century. The whole investigation was summarized with a synthetic ending.

Технологии медиакоммуникаций в политической сфере в контексте современной геополитической ситуации

The article considers key characteristics of media communication technology in the political sphere in the context of the current geopolitical situation. The author explores the influence of modern media communication for political information. The article analyses the features of application of media communication technologies by various political actors, as well as their influence on public opinion formation and political preference. The article is of interest to specialists in the field of political science, sociology, journalism and other humanities, as well as to a wide range of readers interested in modern trends in the development of media communication technologies and their impact on the political sphere. The author of the article considers political communication as a process of transfer of politically relevant information between different elements of the political system with the aim of its subsequent assimilation. The digital factors of influence of media communications on political environment are analyzed. Modern media communication technologies provide new opportunities for political actors to influence public opinion and shape the political preferences of citizens. However, they can also be used to spread misinformation and manipulate the public consciousness, so the author points out the importance of professionalizing knowledge in this area to prevent the dissemination of inaccurate information. It seems that political actors in the digital environment need to intensify interaction with online platforms, digital services and social networks for effective interaction with the population.

Purchasing medicines and functional foods on the internet: a cross-sectional study investigating the knowledge, attitudes, and experience of Vietnamese people in 2023

ObjectiveTo investigate Vietnamese people’s knowledge, attitudes, and experience in purchasing medicines and functional foods online.MethodsVia an online survey, the data of 1,070 participants were collected, including their general characteristics, Internet use, previous experience, knowledge, and attitudes towards purchasing medicines/functional foods online. Factors associated with their knowledge and attitudes were identified via multivariate linear regression models.ResultsDuring 2022–2023, about 97.2% of participants used the Internet to seek health information (self-diagnosis: 65.0%, self-medication: 72.6%). Roughly 52.8% bought medicines and/or functional foods online. Among 565 buyers, 41.8% felt satisfied. Only 19.9% understood that selling medicines online was illegal in Vietnam. The main benefits of purchasing medicines/functional foods online that many people agreed on included convenience (87.1%), freedom from location (84.8%), and being able to order/buy products after opening hours (84.7%). Many people felt worried about the ability to buy counterfeit or substandard products (87.7%), inaccurate product information (85.0%), the lack of supervision of the authorities (83.7%), and increasing risks of drug abuse, self-medication, and treatment non-adherence (82.5%). Roughly 84.3% found distinguishing between legal and illegal online pharmacies difficult. Participants’ average knowledge and attitude scores were 6.514 ± 2.461 (range: 0–16) and 89.330 ± 13.720 (range: 23–115), respectively. The main factors associated with people’s knowledge and attitudes towards purchasing these products online included their frequency of Internet use, seeking health information online for self-medication, feeling satisfied with previous experience, and having at least one chronic disease.ConclusionsMany Vietnamese people’s knowledge about purchasing medicines/functional foods online was limited. With the increasing need for online shopping, enhancing their knowledge is paramount. In the forthcoming years, when the Ministry of Health and relevant authorities publish legal documents and enact laws involving online pharmacies and trading medicines on the Internet, ways to recognize licensed online pharmacies must be widely propagated and disseminated in the community.

Auditor Independence and Experience in Fraud Detection: the Crucial Role of Professional Skepticism

This study aims to examine the effect of auditor independence and experience on fraud detection, with professional skepticism as a moderating variable. In today's business world, many companies strive to achieve maximum profits. In pursuit of this goal, some companies engage in fraudulent practices, which have become common among businesspeople and are well-known to the general public. These fraudulent practices occur not only in the private sector but are also frequently found in the government sector, harming many parties due to inaccurate and irrelevant information. Investors are the most affected, as they often make incorrect investment decisions based on misleading information. Agency theory suggests that more independent auditors tend to be more effective in detecting fraud because they are more likely to act in the interest of the capital owners than less independent auditors. This study involves 108 auditors from 19 audit firms in Bali. The structural equation modeling analysis method was employed to measure the strength of the relationship between the dependent and independent variables using Smart PLS. The results show that auditor independence and experience have a positive impact on fraud detection, and professional skepticism strengthens the effect of independence and auditor experience on fraud detection.

Abstract B026: TikTok and #CancerPrevention: A content analysis

Abstract Introduction: TikTok is a widely used social media platform that allows users to post original short-form videos, typically under three minutes long. Of the 121 million TikTok users in the United States, the majority fall in the 18-34 age range. While most videos are classified as “entertainment” users can explore an array of hashtags, including health-related messages. Given its potential to disseminate information on cancer prevention, our project explored the content of #CancerPrevention videos on TikTok. Methods: Using a naïve TikTok account via a web browser, the team extracted the URLs of the top 157 TikTok videos tagged with “CancerPrevention”. We simultaneously collected analytics of the number of likes the videos received, comments, bookmarks, shares, length of video, and upload date. We developed a content codebook that was refined over several sessions to enhance agreement. The team double-coded the top 60 videos that were available and in English. The remaining videos were not double-coded before the URL linking to the video expired, thus limiting our sample to 60. Average coder agreement was 89%. New data: The 60 videos included in the analysis totaled 679,346 likes, 12,567 comments, 180,151 bookmarks, and 69,300 shares. The median length of a video was 53 seconds (range 5 seconds to 7 minutes 24 seconds). The oldest video was posted in March 2021 and the newest in October 2023. Nearly half of the videos appeared to be from health professionals (43.5%), while a quarter were from lay individuals (22.6%). However, most videos were not affiliated with medical organizations, non-profits, or other reputable organizations (93.5%). As the hashtag suggested, most videos targeted a general audience (86.4%) and focused on cancer prevention (68.3%). Half of the videos discussed diet and nutrition as cancer prevention strategies (51.7%), while very few emphasized exercise (13.3%), tobacco use (6.7%), or alcohol use (8.3%). Most videos addressed general cancer prevention (69.5%), with colon cancer being the most frequently specified type (13.6%), followed by breast cancer (5.1%). Very few discussed pharmacology or industry-related topics (6.7%). More than half (56.7%) promoted unconventional cancer prevention strategies, such as avoiding sugar consumption, which is claimed in some videos “to feed cancer cells” and eating specific foods to prevent cancer. Conclusions: Despite uncertainties about its future, TikTok remains a highly popular social media platform among youth and young adults in the U.S., with the ability to rapidly disseminate messages to a wide audience. However, our project revealed that TikTok content often lacks evidence-based information, which can potentially lead to the spread of misinformation. Public health practitioners can use this opportunity to evaluate which messages garner the most engagement and develop research-based content that is relevant and accurate, countering the spread of inaccurate or harmful information. Citation Format:Victoria Churchill, Anika Jaiswal, Robert T. Fairman, Osato Eke, Brian M. Rivers. TikTok and #CancerPrevention: A content analysis [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr B026.

Large language models in medical and healthcare fields: applications, advances, and challenges

Large language models (LLMs) are increasingly recognized for their advanced language capabilities, offering significant assistance in diverse areas like medical communication, patient data optimization, and surgical planning. Our survey meticulously searched for papers with keywords such as “medical,” “clinical,” “healthcare,” and “LLMs” across various databases, including ACM and Google Scholar. It sought to delve into the latest trends and applications of LLMs in healthcare, analyzing 175 relevant publications to support both practitioners and researchers in the field. We have compiled 56 experimental datasets, various evaluation methods and reviewed cutting-edge LLMs across tasks. Our comprehensive analysis of LLMs in healthcare applications, including medical question-answering, dialogue summarization, electronic health record generation, scientific research, medical education, medical product safety monitoring, clinical health reasoning, and clinical decision support. Furthermore, we have identified the challenges, including data security, inaccurate information, fairness and bias, plagiarism, copyrights, and accountability, and the potential solutions, namely de-identification framework, references,counterfactually fair prompting,opening and ending control codes, and establishing normative standards,to address these open issues,respectively. The findings of this survey exert a profound impact on spurring innovation in practical applications and addressing inherent challenges within the academic and medical communities.

Artificial Intelligence Promotes the Dunning Kruger Effect: Evaluating ChatGPT Answers to Frequently Asked Questions About Adolescent Idiopathic Scoliosis.

Patients have long turned to the Internet for answers to common medical questions. As the ability to access information evolves beyond standard search engines, patients with adolescent idiopathic scoliosis (AIS) and their parents may use artificial intelligence chatbots such as ChatGPT as a new source of information. Ten frequently asked questions regarding AIS were posed to ChatGPT. The accuracy and adequacy of the responses were graded as excellent not requiring clarification, satisfactory requiring minimal clarification, satisfactory requiring moderate clarification, and unsatisfactory requiring substantial clarification. ChatGPT gave one response that was excellent not requiring clarification, four responses that were satisfactory requiring minimal clarification, three responses that were satisfactory requiring moderate clarification, and two responses that were unsatisfactory requiring substantial clarification, with information about higher level, more complex areas of discussion such as surgical options being less accurate. ChatGPT provides answers to FAQs about AIS that were generally accurate, although correction was needed on specific surgical treatments. Patients may be at risk of developing a Dunning-Kruger effect by proxy from the superficial and sometimes inaccurate information provided by ChatGPT on more complex aspects of AIS.

Study on Assessing the Evolution of Nutritional Choices through Social Media Influence

Social media-related nutritional decisions influencers and commercial postings on social media have a significant impact on people's eating habits, purchasing decisions, and decisions about food in general. It also shapes people's dietary practices and overall nutrition. Investigating dietary habits through social media can be disadvantageous to the potential for biased or inaccurate information, as sensational content can lead to unreliable nutritional advice. The 160 participants' nutritional choices using social media influence data are collected, and random questionnaires are collected. There are some factors depicted in this study that are social media engagement, perceived credibility of nutrition information, influence of social media on food choices, and change in eating habits. The study utilized SPSS-29 for statistical analysis, descriptive statistics, multivariate regression, correlation analysis, and Mann-Whitney U test and Spearman's rank correlation coefficient were used to determine statistical significance. Social media use and food choices are found to be significantly correlated, with more credibility impacting consumption patterns. The most important effect of social media on eating decisions is revealed by multivariate regression. The study interaction with social media significantly influences dietary decisions, affecting credibility perceptions and highlighting the need for rigorous assessment of online nutritional information, as influence often leads to dietary modifications.