Simplistic Collection and Labeling Practices Limit the Utility of Benchmark Datasets for Twitter Bot Detection.
Chris HaysZachary SchutzmanManish RaghavanErin WalkPhilipp ZimmerPublished in: WWW (2023)
Keyphrases
- benchmark datasets
- uci repository
- automatic detection
- ensemble methods
- detection method
- detection algorithm
- false positives
- social media
- detection rate
- object detection
- document collections
- uci machine learning repository
- utility function
- image segmentation
- social networks
- event detection
- anomaly detection
- learning algorithm
- machine learning