Health Misinformation in Search and Social Media

Ghenai, Amira

doi:10.1145/3077136.3084153

Cited by 9 publications

(17 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, online sources also contain misinformation that may negatively affect attitudes and behavior and, as such, may have extremely harmful effects on public health [ 5 ]. In addition, health misinformation, which is against established medical understanding [ 6 ], may be widely distributed in order to reach a large population in a short time in the digital age [ 7 ]. This is extremely important because previous studies have shown that many parents mostly receive vaccination information through online sources [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

The Impact of Online Media on Parents’ Attitudes toward Vaccination of Children—Social Marketing and Public Health

Melović

Stojanovic

Vulić

et al. 2020

IJERPH

View full text Add to dashboard Cite

The aim of this paper was to investigate the level of influence of online media on the parents’ attitudes toward vaccination of children in three countries of the Western Balkans—Montenegro, Serbia, and Bosnia and Herzegovina, in order to use the potentials of this form of communication effectively and efficiently. Online media are a critical factor of influence on the formation of attitudes in many areas of modern society, which is why their proper use plays an important role in strengthening vaccine confidence and which may further contribute to improvement of public health. On the other side, having in mind the fact that communication is an integral part of marketing, it is clear that social marketing has an extremely important role regarding the analyzed topic, especially because of the fact that social marketing activities tend to change or maintain people’s behavior for the benefit of individuals and society as a whole. For the purpose of this research, a conceptual model was developed. Quantitative research was conducted online in the first quarter of 2020 using the survey method. Statistical analysis was applied to data collected from 1593 parents in the analyzed countries. The relevance of the hypotheses was tested using standard statistical tests, ANOVA test, eta coefficient, and logistic regression. The research showed that all analyzed variables from the model have a significant impact on the parents’ attitudes toward the vaccination of children and that they correlate with the degree of trust in vaccines. The results also approved that online media have a significant influence on the formation of parents’ attitudes toward the vaccination of children (obtained values of eta coefficient η2 = 0.216, η2 = 0.18, η2 = 0.167, η2 = 0.090, reliability Cronbach’s Alpha 0.892), which confirms the importance of the use of social marketing in order to direct communication properly and to strengthen the level of trust in vaccines. Additionally, the results of logistic regression showed that the following groups of parents are particularly vulnerable to the influence of online media on attitudes toward vaccines: women, parents of younger age (“millennials”), and parents who are in common law marriage, as well as parents who have more children. In addition, the results showed that there is no statistically significant difference in the attitudes of parents in the observed countries (η2 = 0.000, F = 0.85). Based on the results of the research, the authors suggest that decision makers should pay more attention to modern forms of online communication and social marketing in order to use their potential for improvement of public health, as well as avoid the harmful impact that certain forms of communication may have on the formation of attitudes and loss of confidence in vaccines. The findings provide an important contribution for public health policy makers to identify and understand properly the impact of online media and social marketing and thus to better adapt their initiatives to changes in modern society.

show abstract

Section: Introductionmentioning

confidence: 99%

The Impact of Online Media on Parents’ Attitudes toward Vaccination of Children—Social Marketing and Public Health

Melović

Stojanovic

Vulić

et al. 2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…Ghenai and Mejova [10] collected 13,728,215 tweets concerning Zika from January to August 2016. Tweets were annotated as debunking a rumor, supporting a rumor, or neither.…”

Section: Introductionmentioning

confidence: 99%

Identifying Key Topics Bearing Negative Sentiment on Twitter: Insights Concerning the 2015-2016 Zika Epidemic

Mamidi¹,

Miller²,

Banerjee³

et al. 2019

JMIR Public Health Surveill

View full text Add to dashboard Cite

Background To understand the public sentiment regarding the Zika virus, social media can be leveraged to understand how positive, negative, and neutral sentiments are expressed in society. Specifically, understanding the characteristics of negative sentiment could help inform federal disease control agencies’ efforts to disseminate relevant information to the public about Zika-related issues. Objective The purpose of this study was to analyze the public sentiment concerning Zika using posts on Twitter and determine the qualitative characteristics of positive, negative, and neutral sentiments expressed. Methods Machine learning techniques and algorithms were used to analyze the sentiment of tweets concerning Zika. A supervised machine learning classifier was built to classify tweets into 3 sentiment categories: positive, neutral, and negative. Tweets in each category were then examined using a topic-modeling approach to determine the main topics for each category, with focus on the negative category. Results A total of 5303 tweets were manually annotated and used to train multiple classifiers. These performed moderately well (F1 score=0.48-0.68) with text-based feature extraction. All 48,734 tweets were then categorized into the sentiment categories. Overall, 10 topics for each sentiment category were identified using topic modeling, with a focus on the negative sentiment category. Conclusions Our study demonstrates how sentiment expressed within discussions of epidemics on Twitter can be discovered. This allows public health officials to understand public sentiment regarding an epidemic and enables them to address specific elements of negative sentiment in real time. Our negative sentiment classifier was able to identify tweets concerning Zika with 3 broad themes: neural defects , Zika abnormalities , and reports and findings . These broad themes were based on domain expertise and from topics discussed in journals such as Morbidity and Mortality Weekly Report and Vaccine . As the majority of topics in the negative sentiment category concerned symptoms, officials should focus on spreading information about prevention and treatment research.

show abstract

“…The third model suggests that examining a collection of trust indicators from data analysis is the ideal approach to predicting trustworthiness, in a model where personalized solutions for clusters of users can also be supported [4]. The final model examines rumour spread in social networks such as Twitter, using crowdsourcing to help to identify false information for applications such as health discussion boards [5,30,31].…”

Section: Results: Artificial Intelligence Trust Modeling To Detect Misinformationmentioning

confidence: 99%

“…The first social network we explored in more detail was Twitter. This was the network examined in the work of Ghenai [5,30,31] which employed crowdsourcing to assist in obtaining labelled data (used when training learning algorithms to detect misinformation). That study was restricted to the healthcare domain, where expert opinion was also available.…”

Section: Twittermentioning

confidence: 99%

Addressing Misinformation in Online Social Networks: Diverse Platforms and the Potential of Multiagent Trust Modeling

et al. 2020

Self Cite

View full text Add to dashboard Cite

In this paper, we explore how various social networking platforms currently support the spread of misinformation. We then examine the potential of a few specific multiagent trust modeling algorithms from artificial intelligence, towards detecting that misinformation. Our investigation reveals that specific requirements of each environment may require distinct solutions for the processing. This then leads to a higher-level proposal for the actions to be taken in order to judge trustworthiness. Our final reflection concerns what information should be provided to users, once there are suspected misleading posts. Our aim is to enlighten both the organizations that host social networking and the users of those platforms, and to promote steps forward for more pro-social behaviour in these environments. As a look to the future and the growing need to address this vital topic, we reflect as well on two related topics of possible interest: the case of older adult users and the potential to track misinformation through dedicated data science studies, of particular use for healthcare.

show abstract

Health Misinformation in Search and Social Media

Cited by 9 publications

References 84 publications

The Impact of Online Media on Parents’ Attitudes toward Vaccination of Children—Social Marketing and Public Health

The Impact of Online Media on Parents’ Attitudes toward Vaccination of Children—Social Marketing and Public Health

Identifying Key Topics Bearing Negative Sentiment on Twitter: Insights Concerning the 2015-2016 Zika Epidemic

Addressing Misinformation in Online Social Networks: Diverse Platforms and the Potential of Multiagent Trust Modeling

Contact Info

Product

Resources

About