# Data

We provide the following data sets: 
- trainset_students.csv contains training IDs, labels, and labels confidence. It contains more than 9,000 images and acts as the training data.
- ID: the unique image identifier. The actual corresponding image can be found here [link] 
Label: the image sentiment polarity score. The labels are highly positive, positive, neutral, negative, and highly negative.
- Label_confidence: The confidence of the image Label between 0 to 1 where 1 indicates 100% confidence over the Label. Please note that each image is manually labeled by several human annotators and this column indicates their agreement with the image sentiment polarity.
- testset_students.csv: only testing ids are available. It contains 3146 images. The actual corresponding image can be found here [link]