Machine Learning Techniques for Predicting Usage of Crack Cocaine Drug

This research investigates the socioeconomic factors that influence initial experimentation with crack cocaine and contribute to continued use and addiction. By analyzing data from the 2006 National Household Survey on Drug Use and Health, the study employs robust statistical methods like Ordinary L...

Full description

Saved in:
Bibliographic Details
Main Authors: Seluguri, Nagarjuna, Sree, S. Gowri, Saturi, Rajesh, Venkateswara Rao, M., Sridhar Reddy, V., Arjun, N.
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Addiction
Analytical models
Biological system modeling
Crack Cocaine
Drug
Drugs
Least Square Regression
Logistic Models
Logistics
Predictive models
Social Media
Socioeconomics
Surveys
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This research investigates the socioeconomic factors that influence initial experimentation with crack cocaine and contribute to continued use and addiction. By analyzing data from the 2006 National Household Survey on Drug Use and Health, the study employs robust statistical methods like Ordinary Least Squares regressions and logistic models to uncover patterns and correlations. This research study explores how demographic, economic, and social variables influence crack cocaine use over time, considering both historical trends and contemporary patterns. By leveraging advanced machine learning and deep learning algorithms, the study delves into social media data to gain further insights into the factors driving substance use. This research contributes to the broader understanding of substance use disorders, shedding light on the complex interplay between socioeconomic factors, individual choices, and addiction pathways associated with crack cocaine. The implications of these findings extend beyond academic inquiry, informing evidence-based policy interventions and public health strategies.
ISSN:2768-0673
DOI:10.1109/I-SMAC61858.2024.10714783