Paper Type
ERF
Abstract
This study examines social media's spatial distribution of cognition and drug-related language by employing the linear directional mean (LDM) and circular variance to analyze directional data. The results reveal differences in spatial distributions, with drug-referenced social media exhibiting a slightly stronger non-uniform pattern than cognition. Researchers should interpret findings cautiously due to several limitations, including temporal constraints, social media origin uncertainties, and feature extraction methods. The study introduces a novel artifact, demonstrating the effectiveness of enhanced grammar-based feature engineering. Additionally, natural language processing (NLP) extracts valuable insights from sparse text social media. Finally, this work extends current research with a deeper understanding of social media data utilization for various applications and underscores the potential of structured frameworks and advanced NLP approaches in this evolving domain.
Paper Number
1187
Recommended Citation
Corso, Anthony; Lee, Esther; Corso, Nathan A.; and Sanders, Benjamin, "Operationalized Social Media and Linear Directional Mean Address Drug Overdose Crisis in America" (2024). AMCIS 2024 Proceedings. 14.
https://aisel.aisnet.org/amcis2024/elevlife/elevlife/14
Operationalized Social Media and Linear Directional Mean Address Drug Overdose Crisis in America
This study examines social media's spatial distribution of cognition and drug-related language by employing the linear directional mean (LDM) and circular variance to analyze directional data. The results reveal differences in spatial distributions, with drug-referenced social media exhibiting a slightly stronger non-uniform pattern than cognition. Researchers should interpret findings cautiously due to several limitations, including temporal constraints, social media origin uncertainties, and feature extraction methods. The study introduces a novel artifact, demonstrating the effectiveness of enhanced grammar-based feature engineering. Additionally, natural language processing (NLP) extracts valuable insights from sparse text social media. Finally, this work extends current research with a deeper understanding of social media data utilization for various applications and underscores the potential of structured frameworks and advanced NLP approaches in this evolving domain.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.