Social media have brought undoubted benefits to our life, but when people use them to make health decisions, a threat for the whole society might arise. For instance, different studies showed a correlation between the increasing usage of social media to discuss about vaccination and the decreasing vaccination coverage, which leads to outbreaks of preventable diseases. The goal of this paper is to understand specific features of the language used to talk about vaccinations on social media platforms. First, we define four different linguistic and psychological categories of messages: (i) affective (e.g., anger and anxiety), (ii) social (e.g., family and entity), (iii) medical (e.g., disease and vaccine-preventable diseases), and (iv) biological (e.g., body and health-related language). Then, we develop a Python-based tool able to map more than 200.000 messages found on Italian Facebook groups that converse about vaccinations into the defined categories. The obtained results show that anti vaccination groups use a language that is difficult to refute (e.g., not anxious, not focused on specific health issues or on specific diseases), whereas the analysis of pro vaccination groups reveals much more anxiety and specificity (e.g., family cases, specific diseases or vaccines). These results might help health professionals to stop the negative vaccination coverage trend, as they allow them to produce social media contents with linguistic and psychological features suitable to contrast partial/misleading information.
Public health and social media: language analysis of vaccine conversations / Furini, Marco; Menegoni, Gabriele. - (2018), pp. 50-55. (Intervento presentato al convegno 3rd International Workshop on Social Sensing, SocialSens 2018 tenutosi a usa nel 2018) [10.1109/SocialSens.2018.00022].
Public health and social media: language analysis of vaccine conversations
Furini, Marco
;
2018
Abstract
Social media have brought undoubted benefits to our life, but when people use them to make health decisions, a threat for the whole society might arise. For instance, different studies showed a correlation between the increasing usage of social media to discuss about vaccination and the decreasing vaccination coverage, which leads to outbreaks of preventable diseases. The goal of this paper is to understand specific features of the language used to talk about vaccinations on social media platforms. First, we define four different linguistic and psychological categories of messages: (i) affective (e.g., anger and anxiety), (ii) social (e.g., family and entity), (iii) medical (e.g., disease and vaccine-preventable diseases), and (iv) biological (e.g., body and health-related language). Then, we develop a Python-based tool able to map more than 200.000 messages found on Italian Facebook groups that converse about vaccinations into the defined categories. The obtained results show that anti vaccination groups use a language that is difficult to refute (e.g., not anxious, not focused on specific health issues or on specific diseases), whereas the analysis of pro vaccination groups reveals much more anxiety and specificity (e.g., family cases, specific diseases or vaccines). These results might help health professionals to stop the negative vaccination coverage trend, as they allow them to produce social media contents with linguistic and psychological features suitable to contrast partial/misleading information.Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris