Model Card for Model ID
This model predicts the type of a place (e.g. restaurant, hotel, park) based on the text of a user review.
E.g.
'I enjoyed the food, it was very delicious' -> 'Restaurants'
'I liked the exhibition, very inspiring' -> 'Museums and Galleries'
Model Details
Model Description
The Bert-User-Review-Rating model is trained on a dataset of 1,300,000 reviews of public places and points of interest. It is capable of classifying the type of a place based on a user review into one of the following categories:
0: 'Specialty Food Stores', 1: 'Hotels and Inns', 2: 'Schools and Universities', 3: 'Shopping mall', 4: 'Museums and Galleries', 5: 'Restaurants', 6: 'Parks', 7: 'Shops', 8: 'Cafes and Coffee Shops', 9: 'Cultural Institutions', 10: 'Places of Worship', 11: 'Leisure and Amusement', 12: 'Tourist Attractions', 13: 'Medical Services', 14: 'Social Services', 15: 'Food Courts', 16: 'Sports and Fitness', 17: 'Outdoor Activities', 18: 'Training and Development', 19: 'Bars and Pubs', 20: 'Industrial and Commercial', 21: 'Wellness Services', 22: 'Pets Services', 23: 'Public Transit', 24: 'Performing Arts', 25: 'Vehicle Services', 26: 'Other Lodging', 27: 'Professional Services', 28: 'Government Services', 29: 'Religious Services', 30: 'Travel Services'
Model type: BERT-based model
Language(s) (NLP): English
Direct Use
The model can be used directly to classify the type of a place based on a user review.
Bias, Risks and Limitations
The model may reflect biases present in the training data, such as cultural or regional biases, as training data reflects public places in Singapore.
How to Get Started with the Model
Use the code below to get started with the model.
Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="mekes/Bert-Place-Type")
result = pipe("The food was super tasty, I enjoyed every bite.")
print(result)
Metrics
Eval Accuracy: 0.753
Eval F1 Score: 0.741
Eval Recall: 0.753
Environmental Impact
Carbon emissions were estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019)
Calculations were done with Nvidia RTX 3090 instead of the used Nvidia RTX 4090.
For one training run it emmited approximately 1,5 kg CO2
- Downloads last month
- 20