Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 20 de 14.693
Filter
1.
Rev. Odontol. Araçatuba (Impr.) ; 43(3): 12-16, set.-dez. 2022. graf, tab
Article in Portuguese | LILACS, BBO - Dentistry | ID: biblio-1381007

ABSTRACT

Verificar a rotina dos cirurgiões-dentistas (CD) e a utilização das mídias sociais, como meio de divulgação profissional e de atração de pacientes em clínicas odontológicas privadas, durante a pandemia de Covid-19. Este estudo transversal qualitativo inclui questionários respondidos por CD atuantes em clínicas privadas na região sudeste do Brasil. Um questionário virtual, elaborado através da plataforma Google Forms, abordou informações sobre o perfil dos profissionais e os aspectos dos métodos publicitários e mídias sociais utilizados para o alcance de pacientes durante o período de pandemia de Covid-19. Os dados obtidos foram tabulados e submetidos à análise estatística descritiva (%). No total, 102 CD participaram do estudo, sendo que 96 questionários seguiram os critérios de inclusão para a análise dos dados. A divulgação social como meio de exposição profissional foi uma ação realizada por 75 (78,13%) CD da amostra. Considerando esses profissionais, 74 (98,67%) utilizam redes sociais e domínios virtuais para tal finalidade, sendo que 71 (95,95%) CD usufruem do Instagram. Grande parte dos participantes (71,62%) relatou não possuir assessoria de marketing especializada para fazer publicações de conteúdo profissional nas redes sociais, embora a maioria publique este tipo de conteúdo mais de uma vez por semana (58,11%). Uma grande parcela dos participantes do estudo (67,71%) notou que a pandemia de Covid-19 procovou diminuição na quantidade de pacientes nas clínicas odontológicas. A inclusão de outros equipamentos de proteção individual foi a conduta mais seguida pelos CD (56,25%) para evitar a transmissão da doença neste período. Conclui-se que os CD participantes acreditam que a pandemia de Covid-19 promoveu um impacto negativo na atração de pacientes em clínicas odontológicas privadas na região sudeste brasileira, ainda que a maioria destes profissionais tenham incluído outros equipamentos de proteção individual como medida de segurança e utilizem frequentemente redes sociais para divulgação de conteúdo profissional, tendo o Instagram como a principal mídia social. No entanto, a assessoria de marketing especializada em publicações de conteúdo profissional nas redes sociais ainda é um recurso pouco utilizado no meio odontológico(AU)


To verify the routine of Dental Surgeons (DS) and the use of social media as a means of professional dissemination and patient attraction in private dental clinics during the Covid-19 pandemic. This cross-sectional qualitative study included questionnaires answered by Dental Surgeons working in private clinics in the southeastern region of Brazil. A virtual questionnaire, which was developed through the Google Forms platform, addressed information about the profile of professionals and aspects of advertising methods and social media used to reach patients during the Covid-19 pandemic period. The data were tabulated and submitted to descriptive statistical analysis (%). A total of 102 Dental Surgeons participated in the study, with 96 questionnaires meeting the inclusion criteria for data analysis. Social disclosure as a means of professional exposure was an action performed by 75 (78.13%) Dental Surgeons of the survey. Considering these professionals, 74 (98.67%) use social networks and virtual domains for this purpose and 71 (95.95%) Dental Surgeons use Instagram. A large portion of the participants (71.62%) reported not having a specialized marketing consultancy to make professional contente publications on social media, although most publish this type of content more than once a week (58.11%). A large portion of study participants (67.71%) noted that the Covid-19 pandemic caused a decrease in the amount of patients in the dental clinics. The inclusion of other personal protective equipment was the conduct most followed by the Dental Surgeons (56.25%) to avoid the transmission of the disease in this period. It can be concluded that the participating Dental Surgeons believe that the Covid-19 pandemic promoted a negative impact on attracting patients in private dental clinics in the southeastern region of Brazil, in spite of most of these professionals have included other personal protective equipment as safety measure and frequently use social networks for dissemination of professional content, with Instagram as main social media. However, a marketing consultancy specialized in publishing professional content on social networks is still a resource which is little used in the dental environment(AU)


Subject(s)
Humans , Male , Female , Dentists , Social Media , COVID-19 , Marketing , Social Networking
2.
PLoS One ; 17(9): e0274213, 2022.
Article in English | MEDLINE | ID: mdl-36129885

ABSTRACT

How do climate change deniers differ from believers? Is there any correlation between human sentiment and deviations from historic temperature? We answer nine such questions using 13 years of Twitter data and 15 million tweets. Seven aspects are explored, namely, user gender, climate change stance and sentiment, aggressiveness, deviations from historic temperature, topics discussed, and environmental disaster events. We found that: a) climate change deniers use the term global warming much often than believers and use aggressive language, while believers tweet more about taking actions to fight the phenomenon, b) deniers are more present in the American Region, South Africa, Japan, and Eastern China and less present in Europe, India, and Central Africa, c) people connect much more the warm temperatures with man-made climate change than cold temperatures, d) the same regions that had more climate change deniers also tweet with negative sentiment, e) a positive correlation is observed between human sentiment and deviations from historic temperature; when the deviation is between -1.143°C and +2.401°C, people tweet the most positive, f) there exist 90% correlation between sentiment and stance, and -94% correlation between sentiment and aggressiveness, g) no clear patterns are observed to correlate sentiment and stance with disaster events based on total deaths, number of affected, and damage costs, h) topics discussed on Twitter indicate that climate change is a politicized issue and people are expressing their concerns especially when witnessing extreme weather; the global stance could be considered optimistic, as there are many discussions that point out the importance of human intervention to fight climate change and actions are being taken through events to raise the awareness of this phenomenon.


Subject(s)
Disasters , Social Media , Attitude , Climate Change , Humans , Temperature
3.
J Med Internet Res ; 24(9): e36986, 2022 Sep 06.
Article in English | MEDLINE | ID: mdl-36066938

ABSTRACT

BACKGROUND: Schizophrenia is a disease associated with high burden, and improvement in care is necessary. Artificial intelligence (AI) has been used to diagnose several medical conditions as well as psychiatric disorders. However, this technology requires large amounts of data to be efficient. Social media data could be used to improve diagnostic capabilities. OBJECTIVE: The objective of our study is to analyze the current capabilities of AI to use social media data as a diagnostic tool for psychotic disorders. METHODS: A systematic review of the literature was conducted using several databases (PubMed, Embase, Cochrane, PsycInfo, and IEEE Xplore) using relevant keywords to search for articles published as of November 12, 2021. We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) criteria to identify, select, and critically assess the quality of the relevant studies while minimizing bias. We critically analyzed the methodology of the studies to detect any bias and presented the results. RESULTS: Among the 93 studies identified, 7 studies were included for analyses. The included studies presented encouraging results. Social media data could be used in several ways to care for patients with schizophrenia, including the monitoring of patients after the first episode of psychosis. We identified several limitations in the included studies, mainly lack of access to clinical diagnostic data, small sample size, and heterogeneity in study quality. We recommend using state-of-the-art natural language processing neural networks, called language models, to model social media activity. Combined with the synthetic minority oversampling technique, language models can tackle the imbalanced data set limitation, which is a necessary constraint to train unbiased classifiers. Furthermore, language models can be easily adapted to the classification task with a procedure called "fine-tuning." CONCLUSIONS: The use of social media data for the diagnosis of psychotic disorders is promising. However, most of the included studies had significant biases; we therefore could not draw conclusions about accuracy in clinical situations. Future studies need to use more accurate methodologies to obtain unbiased results.


Subject(s)
Psychotic Disorders , Schizophrenia , Social Media , Artificial Intelligence , Humans , Psychotic Disorders/diagnosis , Schizophrenia/diagnosis , Social Behavior
4.
J Med Internet Res ; 24(9): e37752, 2022 Sep 06.
Article in English | MEDLINE | ID: mdl-36066939

ABSTRACT

BACKGROUND: Physicians are increasingly using Twitter as a channel for communicating with colleagues and the public. Identifying physicians on Twitter is difficult due to the varied and imprecise ways that people self-identify themselves on the social media platform. This is the first study to describe a reliable, repeatable methodology for identifying physicians on Twitter. By using this approach, we characterized the longitudinal activity of US physicians on Twitter. OBJECTIVE: We aimed to develop a reliable and repeatable methodology for identifying US physicians on Twitter and to characterize their activity on Twitter over 5 years by activity, tweeted topic, and account type. METHODS: In this study, 5 years of Twitter data (2016-2020) were mined for physician accounts. US physicians on Twitter were identified by using a custom-built algorithm to screen for physician identifiers in the Twitter handles, user profiles, and tweeted content. The number of tweets by physician accounts from the 5-year period were counted and analyzed. The top 100 hashtags were identified, categorized into topics, and analyzed. RESULTS: Approximately 1 trillion tweets were mined to identify 6,399,146 (<0.001%) tweets originating from 39,084 US physician accounts. Over the 5-year period, the number of US physicians tweeting more than doubled (ie, increased by 112%). Across all 5 years, the most popular themes were general health, medical education, and mental health, and in specific years, the number of tweets related to elections (2016 and 2020), Black Lives Matter (2020), and COVID-19 (2020) increased. CONCLUSIONS: Twitter has become an increasingly popular social media platform for US physicians over the past 5 years, and their use of Twitter has evolved to cover a broad range of topics, including science, politics, social activism, and COVID-19. We have developed an accurate, repeatable methodology for identifying US physicians on Twitter and have characterized their activity.


Subject(s)
COVID-19 , Physicians , Social Media , Algorithms , Data Collection , Humans
5.
J Med Internet Res ; 24(9): e37337, 2022 Sep 08.
Article in English | MEDLINE | ID: mdl-36074544

ABSTRACT

BACKGROUND: Health-related misinformation can be propagated via social media and is a threat to public health. Several quality assessment tools and principles to evaluate health-related information in the public domain exist; however, these were not designed specifically for social media. OBJECTIVE: This study aims to develop Principles for Health-related Information on Social Media (PRHISM), which can be used to evaluate the quality of health-related social media content. METHODS: A modified Delphi approach was used to obtain expert consensus on the principles and functions of PRHISM. Health and social media experts were recruited via Twitter, email, and snowballing. A total of 3 surveys were administered between February 2021 and May 2021. The first survey was informed by a literature review and included open-ended questions and items from existing quality assessment tools. Subsequent surveys were informed by the results of the proceeding survey. Consensus was deemed if ≥80% agreement was reached, and items with consensus were considered relevant to include in PRHISM. After the third survey, principles were finalized, and an instruction manual and scoring tool for PRHISM were developed and circulated to expert participants for final feedback. RESULTS: A total of 34 experts consented to participate, of whom 18 (53%) responded to all 3 Delphi surveys. In total, 13 principles were considered relevant and were included in PRHISM. When the instructions and PRHISM scoring tool were circulated, no objections to the wording of the final principles were received. CONCLUSIONS: A total of 13 quality principles were included in the PRHISM tool, along with a scoring system and implementation tool. The principles promote accessibility, transparency, provision of authoritative and evidence-based information and support for consumers' relationships with health care providers. PRHISM can be used to evaluate the quality of health-related information provided on social media. These principles may also be useful to content creators for developing high-quality health-related social media content and assist consumers in discerning high- and low-quality information.


Subject(s)
Social Media , Consensus , Delphi Technique , Health Personnel , Humans , Surveys and Questionnaires
6.
J Med Internet Res ; 24(9): e39805, 2022 Sep 02.
Article in English | MEDLINE | ID: mdl-36053565

ABSTRACT

BACKGROUND: Dementia is a global public health priority due to rapid growth of the aging population. As China has the world's largest population with dementia, this debilitating disease has created tremendous challenges for older adults, family caregivers, and health care systems on the mainland nationwide. However, public awareness and knowledge of the disease remain limited in Chinese society. OBJECTIVE: This study examines online public discourse and sentiment toward dementia among the Chinese public on a leading Chinese social media platform Weibo. Specifically, this study aims to (1) assess and examine public discourse and sentiment toward dementia among the Chinese public, (2) determine the extent to which dementia-related discourse and sentiment vary among different user groups (ie, government, journalists/news media, scientists/experts, and the general public), and (3) characterize temporal trends in public discourse and sentiment toward dementia among different user groups in China over the past decade. METHODS: In total, 983,039 original dementia-related posts published by 347,599 unique users between 2010 and 2021, together with their user information, were analyzed. Machine learning analytical techniques, including topic modeling, sentiment analysis, and semantic network analyses, were used to identify salient themes/topics and their variations across different user groups (ie, government, journalists/news media, scientists/experts, and the general public). RESULTS: Topic modeling results revealed that symptoms, prevention, and social support are the most prevalent dementia-related themes on Weibo. Posts about dementia policy/advocacy have been increasing in volume since 2018. Raising awareness is the least discussed topic over time. Sentiment analysis indicated that Weibo users generally attach negative attitudes/emotions to dementia, with the general public holding a more negative attitude than other user groups. CONCLUSIONS: Overall, dementia has received greater public attention on social media since 2018. In particular, discussions related to dementia advocacy and policy are gaining momentum in China. However, disparaging language is still used to describe dementia in China; therefore, a nationwide initiative is needed to alter the public discourse on dementia. The results contribute to previous research by providing a macrolevel understanding of the Chinese public's discourse and attitudes toward dementia, which is essential for building national education and policy initiatives to create a dementia-friendly society. Our findings indicate that dementia is associated with negative sentiments, and symptoms and prevention dominate public discourse. The development of strategies to address unfavorable perceptions of dementia requires policy and public health attention. The results further reveal that an urgent need exists to increase public knowledge about dementia. Social media platforms potentially could be leveraged for future dementia education interventions to increase dementia awareness and promote positive attitudes.


Subject(s)
Dementia/psychology , Machine Learning , Social Media , Aged , Attitude , China/epidemiology , Dementia/epidemiology , Humans , Language
7.
PLoS One ; 17(9): e0272628, 2022.
Article in English | MEDLINE | ID: mdl-36074762

ABSTRACT

OBJECTIVE: Twitter as a social media platform has revolutionized the way we interact with others and receive information. The presence of dental schools in Twitter facilitates the engagement of students, educators, dental professionals, and the community. Given the explosive popularity of Twitter as a social media platform and its potential use in the areas of education and branding, the questions of why and how dental schools use these services warrant comprehensive research. Thus, the aim of this study was to analyze the pattern and use of Twitter as a social media platform for dental schools in Saudi Arabia. METHODS: The tweets were extracted within the timeframe from July 15, 2019, to July 15, 2020. The Twitter data collected included: full text content, the count of retweets, quotes, replies and likes. Extracted tweets were categorized into five main themes: news and announcement, dental professional communication, general communication, oral health education, and promoting participation. Tweets in each main theme were further categorized according to the dental schools' academic roles namely; education, research and community service. In addition, tweets were classified according to originality of the tweet, language used, nature of the tweet and the use of hashtags and mentions. Descriptive analysis presented in the form of frequency tables with percentages and mean (SD) as well as graphical presentation of the pattern and use of Twitter for Saudi dental schools in the form of bar, pie and line charts. Categorical data were analyzed using chi square test, while continuous data were analyzed using ANOVA. Statistical significance was set at p ≤ 0.05. RESULTS: A total of 15 Saudi dental schools with Twitter accounts were included in the analysis. King Saud University (KSU) had the largest number of followers with 17,200. Within the time frame of this study, a total of 1,889 original tweets from dental schools were found. Imam Abdulrahman Bin Faisal University (IAU) had the highest number of posted tweets (n = 647, 34.3%). The distribution of tweets was highest in September 2019 (n = 239) and lowest in July 2020 (n = 22). Majority of the tweets (81.9%) belonged to five out of the 15 dental schools. News and announcements were the most tweeted thematic subject with 1,034 tweets (55%). While community service was the most tweeted academic role with 803 tweets (42%). The top five active dental schools' performance for both thematic and academic role classifications were significantly different based on the chi square test (p < 0.001). CONCLUSION: This study highlights the importance of Twitter as a social media platform, in dental education especially when it comes to presence and branding for dental schools. Twitter is a helpful platform to expose dental schools to the community, this can be seen by their academic achievements as well as their active role with community service.


Subject(s)
Social Media , Communication , Humans , Saudi Arabia , Schools, Dental
8.
Lakartidningen ; 1192022 09 14.
Article in Swedish | MEDLINE | ID: mdl-36106743

ABSTRACT

Skewed information about medicines in social media influence the healthcare-patient contact. Healthcare staff need situation adapted evidence that can be linked to patient data. For 20 years Sweden has provided praised Pharmacological Knowledge Bases (PKB). They include ¼Janusmed drug-drug interactions«, ¼Janusmed drugs and birth defects« and ¼e-Ped (electronic pediatric) instructions and drug dosage control«. PKBs need to be better integrated into digital tools adhering to a national guide for optimal interface presentation of information. They should be produced by medical editors and delivered through a national digital highway. Experts need to adhere to a policy for handling conflicts of interest and evaluate that information is appreciated and used. PKBs should be accessible as a public good for healthcare staff, students and the public to support personalized medical care.


Subject(s)
Knowledge Bases , Social Media , Child , Delivery of Health Care , Humans , Sweden
9.
PLoS One ; 17(9): e0263449, 2022.
Article in English | MEDLINE | ID: mdl-36112639

ABSTRACT

Sentiment quantification is the task of training, by means of supervised learning, estimators of the relative frequency (also called "prevalence") of sentiment-related classes (such as Positive, Neutral, Negative) in a sample of unlabelled texts. This task is especially important when these texts are tweets, since the final goal of most sentiment classification efforts carried out on Twitter data is actually quantification (and not the classification of individual tweets). It is well-known that solving quantification by means of "classify and count" (i.e., by classifying all unlabelled items by means of a standard classifier and counting the items that have been assigned to a given class) is less than optimal in terms of accuracy, and that more accurate quantification methods exist. Gao and Sebastiani 2016 carried out a systematic comparison of quantification methods on the task of tweet sentiment quantification. In hindsight, we observe that the experimentation carried out in that work was weak, and that the reliability of the conclusions that were drawn from the results is thus questionable. We here re-evaluate those quantification methods (plus a few more modern ones) on exactly the same datasets, this time following a now consolidated and robust experimental protocol (which also involves simulating the presence, in the test data, of class prevalence values very different from those of the training set). This experimental protocol (even without counting the newly added methods) involves a number of experiments 5,775 times larger than that of the original study. Due to the above-mentioned presence, in the test data, of samples characterised by class prevalence values very different from those of the training set, the results of our experiments are dramatically different from those obtained by Gao and Sebastiani, and provide a different, much more solid understanding of the relative strengths and weaknesses of different sentiment quantification methods.


Subject(s)
Social Media , Attitude , Data Collection , Humans , Reproducibility of Results
10.
BMC Prim Care ; 23(1): 241, 2022 09 17.
Article in English | MEDLINE | ID: mdl-36115943

ABSTRACT

BACKGROUND: Patients with diabetes who have poor health literacy about the disease may exhibit poor compliance and thus subsequently experience more complications. However, the conceptual gap of diabetes between health providers and the general population is still not well understood. Decoding concerns about diabetes on social media may help to close this gap. METHODS: Social media data were collected from the OpView social media platform. After checking the quality of the data, we analyzed the trends in people's discussions on the internet using text mining. The natural language process includes word segmentation, word counting and counting the relationships between the words. A word cloud was developed, and clustering analyses were performed. RESULTS: There were 19,565 posts about diabetes collected from forums, community websites, and Q&A websites in the summer (June, July, and August) of 2017. The three most popular aspects of diabetes were diet (33.2%), life adjustment (21.2%), and avoiding complications (15.6%). Most discussions about diabetes were negative. The negative/positive ratios of the top three aspects were avoiding complications (7.60), problem solving (4.08), and exercise (3.97). In terms of diet, the most popular topics were Chinese medicine and special diet therapy. In terms of life adjustment, financial issues, weight reduction, and a less painful glucometer were discussed the most. Furthermore, sexual dysfunction, neuropathy, nephropathy, and retinopathy were the most worrisome issues in avoiding complications. Using text mining, we found that people care most about sexual dysfunction. Health providers care about the benefits of exercise in diabetes care, but people are mostly concerned about sexual functioning. CONCLUSION: A conceptual gap between health providers and the network population existed in this real-world social media investigation. To spread healthy diabetic education concepts in the media, health providers might wish to provide more information related to the network population's actual areas of concern, such as sexual function, Chinese medicine, and weight reduction.


Subject(s)
Diabetes Mellitus , Sexual Dysfunction, Physiological , Social Media , Data Mining , Diabetes Mellitus/epidemiology , Humans , Weight Loss
11.
PLoS One ; 17(9): e0273153, 2022.
Article in English | MEDLINE | ID: mdl-36054094

ABSTRACT

Governments can use social media platforms such as Twitter to disseminate health information to the public, as evidenced during the COVID-19 pandemic [Pershad (2018)]. The purpose of this study is to gain a better understanding of Canadian government and public health officials' use of Twitter as a dissemination platform during the pandemic and to explore the public's engagement with and sentiment towards these messages. We examined the account data of 93 Canadian public health and government officials during the first wave of the pandemic in Canada (December 31, 2019 August 31, 2020). Our objectives were to: 1) determine the engagement rates of the public with Canadian federal and provincial/territorial governments and public health officials' Twitter posts; 2) conduct a hashtag trend analysis to explore the Canadian public's discourse related to the pandemic during this period; 3) provide insights on the public's reaction to Canadian authorities' tweets through sentiment analysis. To address these objectives, we extracted Twitter posts, replies, and associated metadata available during the study period in both English and French. Our results show that the public demonstrated increased engagement with federal officials' Twitter accounts as compared to provincial/territorial accounts. For the hashtag trends analysis of the public discourse during the first wave of the pandemic, we observed a topic shift in the Canadian public discourse over time between the period prior to the first wave and the first wave of the pandemic. Additionally, we identified 11 sentiments expressed by the public when reacting to Canadian authorities' tweets. This study illustrates the potential to leverage social media to understand public discourse during a pandemic. We suggest that routine analyses of such data by governments can provide governments and public health officials with real-time data on public sentiments during a public health emergency. These data can be used to better disseminate key messages to the public.


Subject(s)
COVID-19 , Social Media , COVID-19/epidemiology , COVID-19/prevention & control , Canada/epidemiology , Government Employees , Humans , Pandemics/prevention & control
12.
PLoS One ; 17(9): e0272926, 2022.
Article in English | MEDLINE | ID: mdl-36067142

ABSTRACT

The maturity and growth of social media have empowered online customers to generate electronic word of mouth (eWOM), on various online websites and platforms, which may influence an individual's decision-making process. This paper explores eWOM information's impact on social media users' purchase intention by applying the information adoption model (IAM) and the technology acceptance model (TAM). PLS-SEM (SmartPLS V.3.3) has been utilized to test the hypotheses using data of 432 respondents. The research findings evinced that eWOM information quality, credibility, usefulness, and ease of use have been critical in determining online consumers' intention to adopt eWOM and form purchase behavior on social media. The study's outcomes offer the marketing managers a viewpoint to realize the significance of the effect of eWOM information on online purchase intention among social media users. Furthermore, the study findings will also enlighten marketing and business managers to utilize social media websites by gauging consumer behavior and focusing on characteristics of eWOM information on social media for better consumer insights.


Subject(s)
Consumer Behavior , Social Media , Electronics , Humans , Intention , Technology
13.
Front Public Health ; 10: 902576, 2022.
Article in English | MEDLINE | ID: mdl-36117599

ABSTRACT

Housing safety and health problems threaten owners' and occupiers' safety and health. Nevertheless, there is no systematic review on this topic to the best of our knowledge. This study compared the academic and public opinions on housing safety and health and reviewed 982 research articles and 3,173 author works on housing safety and health published in the Web of Science Core Collection. PRISMA was used to filter the data, and natural language processing (NLP) was used to analyze emotions of the abstracts. Only 16 housing safety and health articles existed worldwide before 1998 but increased afterward. U.S. scholars published most research articles (30.76%). All top 10 most productive countries were developed countries, except China, which ranked second (16.01%). Only 25.9% of institutions have inter-institutional cooperation, and collaborators from the same institution produce most work. This study found that most abstracts were positive (n = 521), but abstracts with negative emotions attracted more citations. Despite many industries moving toward AI, housing safety and health research are exceptions as per articles published and Tweets. On the other hand, this study reviewed 8,257 Tweets to compare the focus of the public to academia. There were substantially more housing/residential safety (n = 8198) Tweets than housing health Tweets (n = 59), which is the opposite of academic research. Most Tweets about housing/residential safety were from the United Kingdom or Canada, while housing health hazards were from India. The main concern about housing safety per Twitter includes finance, people, and threats to housing safety. By contrast, people mainly concerned about costs of housing health issues, COVID, and air quality. In addition, most housing safety Tweets were neutral but positive dominated residential safety and health Tweets.


Subject(s)
COVID-19 , Social Media , Cluster Analysis , Housing , Humans , Natural Language Processing , Sentiment Analysis
14.
Medicine (Baltimore) ; 101(37): e30473, 2022 Sep 16.
Article in English | MEDLINE | ID: mdl-36123912

ABSTRACT

Medical-related information rapidly spreads throughout the internet. However, these types of information often contain inaccurate information, which can lead to harmful misconceptions. In this study, we evaluated the reliability, quality, and accuracy of videos uploaded on YouTube that harbor claims on the effects of acupuncture on COVID-19 treatment. This is a cross-sectional study. Videos uploaded on YouTube up to February 17, 2022, were searched, and the keywords used were as follows: "acupuncture," "coronavirus," "COVID 19," "COVID-19," "Corona," "COVID," and "SARSCoV2." The top 50 videos in English were viewed and evaluated. The reliability of the videos was evaluated using the modified DISCERN scale, the content-quality was evaluated using the Global Quality Scale. The accuracy of the information in each video was evaluated as well. Of the 50 videos, only 8% were found to be reliable and 64% were of poor quality. Additionally, 98% of the videos were misleading. The mean modified DISCERN scores was 1.72 and the mean Global Quality Scale score was 2.06. Despite the videos being made by experts, their reliability, content-quality, and accuracy were found to be low. The spread of inaccurate information may result in the use of inappropriate and potentially harmful treatment methods for patients. Videos that contain medical information should be produced based on verified scientific evidence.


Subject(s)
Acupuncture Therapy , COVID-19 , Social Media , COVID-19/drug therapy , COVID-19/therapy , Cross-Sectional Studies , Humans , RNA, Viral , Reproducibility of Results , SARS-CoV-2 , Video Recording
15.
Medicine (Baltimore) ; 101(37): e30502, 2022 Sep 16.
Article in English | MEDLINE | ID: mdl-36123913

ABSTRACT

This study aimed to evaluate the usefulness, reliability, quality, and related characteristics of YouTube video clips on congenital muscular torticollis (CMT). This cross-sectional study analyzed 47 YouTube video clips on CMT. They were classified as either useful or misleading by 2 rehabilitation doctors. The modified DISCERN tool and the Global Quality Scale (GQS) were used to evaluate their reliability and quality. An analysis was conducted using the characteristics, such as presenters, ownership of YouTube channel accounts, countries, contents, and the video popularity. Of the 47 YouTube video clips, 8 (17%) were evaluated as misleading, which indicated that they included at least one scientifically unproven piece of information on CMT or more. They were less reliable and of lower quality than the useful video clips. The video clips presented by healthcare professionals were more useful compared to those presented by others (P = .015). However, the video popularity was not related to its usefulness. The reliability and quality (3.70 ± 0.82 vs 0.75 ± 0.50 and 2.95 ± 1.21 vs 1.50 ± 1.00) assessed by the modified DISCERN tool and GQS, respectively, were significantly higher in the video clips presented by healthcare professionals compared to those presented by others. There were misleading YouTube video clips on CMT. Video clips presented by healthcare professionals could be more useful, reliable, and of better quality. The popularity of the video clips does not indicate more usefulness, reliability, and better quality. YouTube viewers should be aware of these findings. We recommend that the viewers preferentially choose video clips on CMT presented by healthcare professionals, not by the video popularity.


Subject(s)
Social Media , Cross-Sectional Studies , Humans , Reproducibility of Results , Torticollis/congenital
16.
J Med Toxicol ; 18(4): 311-320, 2022 Oct.
Article in English | MEDLINE | ID: mdl-36097239

ABSTRACT

INTRODUCTION: Pharmacovigilance (PV) has proven to detect post-marketing adverse drug events (ADE). Previous research used the natural language processing (NLP) tool to extract unstructured texts relevant to ADEs. However, texts without context reduce the efficiency of such algorithms. Our objective was to develop and validate an innovative NLP tool, aTarantula, using a context-aware machine-learning algorithm to detect existing ADEs from social media using an aggregated lexicon. METHOD: aTarantula utilized FastText embeddings and an aggregated lexicon to extract contextual data from three patient forums (i.e., MedHelp, MedsChat, and PatientInfo) taking warfarin. The lexicon used warfarin package inserts and synonyms of warfarin ADEs from UMLS and FAERS databases. Data was stored on SQLite and then refined and manually checked by three clinical pharmacists for validation. RESULTS: Multiple organ systems where the most frequent ADE were reported at 1.50%, followed by CNS side effects at 1.19%. Lymphatic system ADEs were the least common side effect reported at 0.09%. The overall Spearman rank correlation coefficient between patient-reported data from the forums and FAERS was 0.19. As determined by pharmacist validation, aTarantula had a sensitivity of 84.2% and a specificity of 98%. Three clinical pharmacists manually validated our results. Finally, we created an aggregated lexicon for mining ADEs from social media. CONCLUSION: We successfully developed aTarantula, a machine-learning algorithmn based on artificial intelligence to extract warfarin-related ADEs from online social discussion forums automatically. Our study shows that it is feasible to use aTarantula to detect ADEs. Future researchers can validate aTarantula on the diverse dataset.


Subject(s)
Drug-Related Side Effects and Adverse Reactions , Social Media , Adverse Drug Reaction Reporting Systems , Artificial Intelligence , Drug-Related Side Effects and Adverse Reactions/diagnosis , Drug-Related Side Effects and Adverse Reactions/prevention & control , Humans , Machine Learning , Pharmacovigilance , Warfarin
17.
J Law Med ; 29(3): 895-903, 2022 Aug.
Article in English | MEDLINE | ID: mdl-36056672

ABSTRACT

Misinformation has challenged the rollout of COVID-19 vaccination around the world. In 2021, professional bodies for several regulated occupations (including doctors and lawyers) initiated investigations into the conduct of members who engaged in vaccine misinformation, including on social media. This commentary discusses key controversies surrounding this novel disciplinary issue, with the focus on the legal profession in New Zealand and Australia. We consider the difficulties of defining "vaccine misinformation", differentiating between public and private social media use, giving proper scope to rights of free speech, and challenges in identifying financial conflicts of interest and unethical client solicitation practices (eg, profiting from spreading vaccine misinformation). The chilling effect upon freedom of expression when lawyers are disciplined for their social media posts that are deemed unscientific is discussed.


Subject(s)
COVID-19 , Social Media , COVID-19 Vaccines , Communication , Humans , Occupations
18.
J Oral Maxillofac Surg ; 80(9): 1455-1457, 2022 Sep.
Article in English | MEDLINE | ID: mdl-36058567
19.
Comput Intell Neurosci ; 2022: 2067449, 2022.
Article in English | MEDLINE | ID: mdl-36059414

ABSTRACT

Primary research to detect duplicate question pairs within community-based question answering systems is based on datasets made of English questions only. This research put forward a solution to the problem of duplicate question detection by matching semantically identical questions in transliterated bilingual data. Deep learning has been implemented to analyze informal languages like Hinglish which is a bilingual mix of Hindi and English on Community Question Answering (CQA) platforms to identify duplicacy in questions. The proposed model works in two sequential modules. First module is a language transliteration module which converts input questions into a mono-language text. The next module takes the transliterated text where a hybrid deep learning model which is implemented using multiple layers is used to detect duplicate questions in the mono-lingual data. The similarity between the question pairs is done utilizing this hybrid model combining a Siamese neural network with identical capsule network as the subnetworks and a decision tree classifier. Manhattan distance function is used with the Siamese network for computing the similarity between questions. The proposed model has been validated on 150 pairs of questions which were scrapped from various social media platforms, such as Tripadvisor and Quora which achieves accuracy of 87.0885% and AUC-ROC value of 0.86.


Subject(s)
Neural Networks, Computer , Social Media , Humans , Language
SELECTION OF CITATIONS
SEARCH DETAIL
...