j-hartmann commited on
Commit
e26a7d1
1 Parent(s): b6ed3f8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -22,6 +22,20 @@ The model was fine-tuned on 2,000 manually annotated social media posts.
22
  The hold-out accuracy is 95% (vs. a balanced 50% random-chance baseline).
23
  For details on the training approach see Web Appendix F in Hartmann et al. (2021).
24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  # Reference
26
  Please cite [this paper](https://journals.sagepub.com/doi/full/10.1177/00222437211037258) when you use our model. Feel free to reach out to [j.p.hartmann@rug.nl](mailto:j.p.hartmann@rug.nl) with any questions or feedback you may have.
27
  ```
22
  The hold-out accuracy is 95% (vs. a balanced 50% random-chance baseline).
23
  For details on the training approach see Web Appendix F in Hartmann et al. (2021).
24
 
25
+ # Application
26
+
27
+ ```python
28
+ from transformers import pipeline
29
+ classifier = pipeline("text-classification", model="j-hartmann/purchase-intention-english-roberta-large", return_all_scores=True)
30
+ classifier("I want this!")
31
+ ```
32
+
33
+ ```python
34
+ Output:
35
+ [[{'label': 'no', 'score': 0.0014553926885128021},
36
+ {'label': 'yes', 'score': 0.9985445737838745}]]
37
+ ```
38
+
39
  # Reference
40
  Please cite [this paper](https://journals.sagepub.com/doi/full/10.1177/00222437211037258) when you use our model. Feel free to reach out to [j.p.hartmann@rug.nl](mailto:j.p.hartmann@rug.nl) with any questions or feedback you may have.
41
  ```