UCE-FID: Using Large Unlabeled, Medium Crowdsourced-Labeled, and Small Expert-Labeled Tweets for Foodborne Illness Detection.
Ruofan HuDongyu ZhangDandan TaoHuayi ZhangHao FengElke A. RundensteinerPublished in: BigData (2023)
Keyphrases
- training data
- supervised learning
- semi supervised learning
- labeled examples
- training set
- unlabeled training data
- manual labeling
- false positives
- labeled training set
- small number
- unlabeled documents
- text classification
- manually labeled
- labeled data
- unlabeled data
- high quality
- learning algorithm
- false alarms
- automatic detection
- detection rate
- named entities
- health care
- unsupervised learning
- anomaly detection
- information systems
- feature selection
- semi supervised
- video sequences
- information retrieval