Add "Bias, Risks, and Limitations" section to model card

Hi, this is an automatic PR generated by the [Giskard Bot](https://huggingface.co/giskard-bot).

Based on an automated scan of the model ([check the discussion here](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest/discussions/14)), we have generated a [Bias, Risks, and Limitations](https://huggingface.co/docs/hub/model-card-annotated#bias-risks-and-limitations) section for your model card.

While we do our best to generate the most reliable reporting, it is possible that our automated analysis produced false positives. If this is the case, please let us know in a comment and feel free to close this PR.

README.md

@@ -130,3 +130,13 @@ Output:
 }
 
 ```
+
+
+## Bias, Risks, and Limitations
+
+The model was analyzed with [Giskard](github.com/giskard-AI/giskard) and the following limitations were identified:
+
+- Typos and misspellings can have a negative impact on the model performances, potentially affecting non-native speakers or people with limited educational background.
+- The model is sensitive to letter case and could classify the same text differently if transformed to lowercase or uppercase. Please make sure that your usage takes this into account.
+
+A full report is available [here](https://htmlpreview.github.io/?https://github.com/Giskard-AI/ml-scan-reports/blob/main/scan_reports/huggingface/cardiffnlp/twitter-roberta-base-sentiment-latest/ea9d76e8-a9f2-429a-b053-ed6da8ef6df/report.html).