Related Experiment Video
Updated: Feb 12, 2026

Modeling Alcohol Consumption in Rodents Using Two-Bottle Choice Home Cage Drinking and Microstructural Analysis
Published on: November 8, 2024
Can Twitter be used to predict county excessive alcohol consumption rates?
Brenda Curtis1, Salvatore Giorgi2, Anneke E K Buffone2
1Center on Continuum of Care in Addictions, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America.
Researchers analyzed Twitter data to predict excessive alcohol consumption rates. Social media language effectively forecasts public health concerns, offering insights beyond traditional demographic factors.
Area of Science:
- Public Health
- Computational Social Science
- Digital Epidemiology
Background:
- Excessive alcohol consumption is a significant public health issue.
- Sociodemographic factors are traditionally used to understand alcohol consumption patterns.
- The potential of social media data for public health surveillance remains underexplored.
Purpose of the Study:
- To determine if excessive alcohol consumption rates can be predicted using Twitter data.
- To investigate if language patterns on Twitter correlate with county-level alcohol consumption.
- To explore the relationship between social media language, socioeconomic status, and excessive drinking.
Main Methods:
- Analysis of over 138 million county-level tweets from 1,384 US counties.
- Application of predictive modeling techniques to identify correlations.
- Utilizing differential and mediating language analysis to understand linguistic patterns.
Main Results:
- Twitter language data accurately predicts excessive alcohol consumption rates.
- Social media language captures consumption patterns beyond sociodemographic factors.
- Mediation analysis revealed that specific Twitter topics explain variance between socioeconomic status and excessive drinking.
Conclusions:
- Twitter data serves as a valuable tool for predicting public health concerns like excessive drinking.
- Integrating predictive modeling with mediation analysis enhances understanding of socioeconomic influences on health behaviors.
- Digital communication platforms offer novel avenues for public health research and intervention.
Related Concept Videos
Excess Pressure Inside a Drop and a Bubble
Predicting Molecular Geometry
Rate-Determining Steps
In a multistep reaction mechanism, one of the elementary steps progresses significantly slower than the others. This slowest step is called the rate-limiting step (or rate-determining step). A reaction cannot proceed faster than its slowest step, and hence, the rate-determining step limits the overall reaction rate.
The concept of rate-determining step can be understood from the analogy of a 4-lane freeway with a short-stretch of traffic-bottleneck caused due to...
Oxidation of Alcohols
The process of oxidation in a chemical reaction is observed in any of the three forms:
Reaction Rate
The mathematical representation of the change in the concentration of reactants and products, over time, is the rate...
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.

