Survey of firearm injury victims suggests a role for social media in violence prevention programs

Treviño, Jesús; Rizvanolli, Lum; Yarrow, Morriam O.; Christian, Errick; Chhabra, Neeraj; Kaminsky, Matthew

doi:10.1016/j.ajem.2022.05.006

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Passive actions, such as increasing the green space in firearm-injury-prone areas [ 40 ] and the demolition of abandoned buildings [ 41 ] are other possibilities. Online maps showing locations for voluntary, temporary firearm storage (especially useful for suicide victims) [ 42 ] and social media applications [ 43 ] are further possibilities. Community-based programs, such as gun buy-backs and other community-based prevention programs may be helpful, but they need to be deployed in culturally sensitive and trauma-informed manners, address social determinants of health, be appropriately funded, and include proper personnel training [ 44 ].…”

Section: Discussionmentioning

confidence: 99%

Firearm Injuries during Pregnancy in the USA

Luster

Loder

2023

Clinics and Practice

View full text Add to dashboard Cite

Trauma during pregnancy is the leading cause of non-pregnancy-related maternal deaths, with some due to injuries from firearms. It was the purpose of this study to characterize the patterns and presentations of firearm-associated injuries in pregnant women using a national emergency department visit database. Data from the Inter-University Consortium for Political and Social Research Firearm Injury Surveillance Study 1993–2020 were utilized. The data include age, sex, race, type of firearm, perpetrator of injury, intent of injury (unintentional, assault, suicide, or law enforcement), anatomic location of the injury, incident locale, disposition from the emergency department (ED), and whether the patient was shot or not with the firearm. Of the 3.36 million ED visits over this time span for firearm injuries, 4410 were pregnant women. The mean age of the pregnant cohort was 23.6 years, with more Hispanic and fewer White women in the pregnant group compared to the non-pregnant cohort. Pregnant women were more likely to experience an injury involving the lower trunk and had a higher percentage of fatalities and hospital admissions compared to the non-pregnant cohort. Fetal demise occurred in at least 70% of cases. Nearly one half of the assaults (44%) occurred on Saturdays and Sundays. As the cause of these injuries is complex, prevention will require input from multiple sources, including health care providers, social agencies, government agencies, elected officials, and law enforcement.

show abstract

Section: Discussionmentioning

confidence: 99%

Firearm Injuries during Pregnancy in the USA

Luster

Loder

2023

Clinics and Practice

View full text Add to dashboard Cite

show abstract

“…Social media data are a relatively new and potentially valuable source of information to support firearms research, an area long hindered by substantial data deficiencies [1][2][3]. Already, studies have used social media data in a variety of firearms-related research contexts, including (1) tracking sentiment, emotion or attitudes, and opinions around gun policy following mass shooting events [4][5][6][7][8][9][10][11][12]; (2) assessing the mental health-related effect of firearms violence and its sequelae [13,14]; (3) examining social media content related to firearm injury [15,16]; and (4) exploring the influence of firearms-related social media advertising [17,18]. Social media-based strategies to prevent gun violence represent a burgeoning area of additional research [19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Development and Assessment of a Social Media–Based Construct of Firearm Ownership: Computational Derivation and Benchmark Comparison

Gresenz¹,

Singh²,

Wang³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background Gun violence research is characterized by a dearth of data available for measuring key constructs. Social media data may offer a potential opportunity to significantly reduce that gap, but developing methods for deriving firearms-related constructs from social media data and understanding the measurement properties of such constructs are critical precursors to their broader use. Objective This study aimed to develop a machine learning model of individual-level firearm ownership from social media data and assess the criterion validity of a state-level construct of ownership. Methods We used survey responses to questions on firearm ownership linked with Twitter data to construct different machine learning models of firearm ownership. We externally validated these models using a set of firearm-related tweets hand-curated from the Twitter Streaming application programming interface and created state-level ownership estimates using a sample of users collected from the Twitter Decahose application programming interface. We assessed the criterion validity of state-level estimates by comparing their geographic variance to benchmark measures from the RAND State-Level Firearm Ownership Database. Results We found that the logistic regression classifier for gun ownership performs the best with an accuracy of 0.7 and an F1-score of 0.69. We also found a strong positive correlation between Twitter-based estimates of gun ownership and benchmark ownership estimates. For states meeting a threshold requirement of a minimum of 100 labeled Twitter users, the Pearson and Spearman correlation coefficients are 0.63 (P<.001) and 0.64 (P<.001), respectively. Conclusions Our success in developing a machine learning model of firearm ownership at the individual level with limited training data as well as a state-level construct that achieves a high level of criterion validity underscores the potential of social media data for advancing gun violence research. The ownership construct is an important precursor for understanding the representativeness of and variability in outcomes that have been the focus of social media analyses in gun violence research to date, such as attitudes, opinions, policy stances, sentiments, and perspectives on gun violence and gun policy. The high criterion validity we achieved for state-level gun ownership suggests that social media data may be a useful complement to traditional sources of information on gun ownership such as survey and administrative data, especially for identifying early signals of changes in geographic patterns of gun ownership, given the immediacy of the availability of social media data, their continuous generation, and their responsiveness. These results also lend support to the possibility that other computationally derived, social media–based constructs may be derivable, which could lend additional insight into firearm behaviors that are currently not well understood. More work is needed to develop other firearms-related constructs and to assess their measurement properties.

show abstract

Survey of firearm injury victims suggests a role for social media in violence prevention programs

Cited by 2 publications

References 6 publications

Firearm Injuries during Pregnancy in the USA

Firearm Injuries during Pregnancy in the USA

Development and Assessment of a Social Media–Based Construct of Firearm Ownership: Computational Derivation and Benchmark Comparison

Contact Info

Product

Resources

About