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: CoRR (2023)
Keyphrases
- supervised learning
- training data
- labeled training set
- automatic detection
- unsupervised learning
- object detection
- training set
- domain knowledge
- detection algorithm
- false alarms
- social media
- semi supervised
- prior knowledge
- domain experts
- false positives
- health care
- detection rate
- feature space
- low quality
- manual labeling
- high quality