Dementia and anxiety take center stage in the science conversations of citizens on Twitter

A study conducted by the URJC analyzed health and healthcare related topics available on this social network for their impact and scope. The results show that there is an active conversation about various cognitive diseases and disorders.

Irene Vega

By analyzing citizen conversations about science and health on Twitter, a research team from URJC, in collaboration with RIAS institute, discovered that one of the main concerns of users (other than COVID-19) is the issue of mental illness. In addition, most of these messages revolve around the Sustainable Development Goals (SDGs), which are specifically linked to SDG 3 health and well-being.

results of this jobPublished in the scientific journal digital health, revealing that there is an active conversation about various diseases and disorders, especially dementia and anxiety, followed by COVID-19, diabetes and cancer. Fernando Martínez Martínez, a researcher at the Higher Technical School of Computer Engineering (ETSII) and co-author of the study, highlights, “Interestingly, the results found regarding the coronavirus are lower than expected after the pandemic.” In addition, it particularly highlights a very active conversation about Mosquito alerta Apps and a citizen science platform aimed at monitoring sightings of tiger mosquitoes and mummy mosquitoes that transmit dengue, Zika, and chikungunya, which demonstrated high engagement of the citizen science community on Twitter in content creation and when posting. Share this initiative, ” adds the researcher.

This research represents important value as information for the possibility of creating health policy recommendations through the use of trend data or influencer or thematic calculations. Within the study, we confirmed that the most influential accounts with the most followers and retweet They belonged to organizations and projects, “refers to Fernando Martínez.

In addition, thanks to the reproducibility of this analysis model, its application can be used to extend the study on these topics and monitor the evolution of trends, users, and other conversations. In this sense, according to the URJC researcher, “the different findings also point to new topics that may be interesting for study of their own, such as the use of Apps To monitor diseases and mental disorders or research rare diseases as they are Threads Too close.”

message parsing (Tweets) and labels (hashtags)

In order to get a sense of what the conversation about health and healthcare is like, the science team created a set of keywords used to filter all the Twitter data they collected. This data was collected from the tool lego, which is responsible for extracting science-related messages from Twitter. After getting those Tweets Regarding health, we used classic social network analysis techniques to obtain hashtags used, and the evolution of its use over time and more users retweetFernando Martinez explains.

Then they used state-of-the-art Natural Language Processing, or NLP, technologies. natural language processing) and NER (Identify the selected entityn) To identify the most frequently used terms in conversation. They also used graphic analysis techniques to create grids on the communications between users who spoke about a particular topic and, in this way, note who the main senders and recipients of the messages were. Finally, according to the URJC researcher, “We used techniques Subject modeling And machine learning To analyze the most discussed topics and how they have evolved over time, as well as the most popular languages ​​in the field.

This work is part of the CS-Track project, led by URJC which aims to analyze data found in various media related to citizen science.