|
--- |
|
language: |
|
- en |
|
library_name: transformers |
|
tags: |
|
- map |
|
- reviews |
|
- public places |
|
--- |
|
|
|
|
|
# Model Card for Model ID |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
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 |
|
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> |
|
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 |
|
<!-- These are the evaluation metrics being used, ideally with a description of why. --> |
|
|
|
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 |
|
|
|
|
