Related Experiment Video
Updated: Feb 20, 2026
10:35
Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus
Published on: May 31, 2020
3.6K
Discovering explanatory models to identify relevant tweets on Zika
Summary
Researchers developed a system to detect Zika virus tweets on Twitter with 92% accuracy using text analysis. This tool helps understand public concerns and the spread of Zika virus information online.
Area of Science:
- Public Health
- Computational Linguistics
- Social Media Analysis
Background:
- Zika virus gained global attention, prompting public discussion on social media platforms like Twitter.
- Understanding public discourse is crucial for monitoring disease outbreaks and public health concerns.
Purpose of the Study:
- To develop an automated system for identifying Zika virus-related tweets.
- To extract key features from tweets for deeper insights into Zika discussions.
- To provide a tool for sentiment analysis and tracking the spread of Zika information.
Main Methods:
- Utilized text-based features extracted using Parts of Speech (POS) taggers and N-gram analysis.
- Developed a classification model, specifically a simple logistic classifier.
- Trained and evaluated the classifier on Twitter data to detect Zika-related content.
Main Results:
- Achieved 92% accuracy in detecting Zika-related tweets.
- Identified significant text features that characterize Zika discussions.
- Demonstrated the effectiveness of the developed classification system.
Conclusions:
- The developed system accurately identifies Zika virus tweets, offering valuable insights.
- This approach can assist public health experts in sentiment analysis and monitoring disease spread.
- Social media analysis provides a scalable method for understanding public health issues.
