Update README.md

README.md

@@ -7,6 +7,13 @@ license: apache-2.0
 
   Compared with the existing similar models (e.g, climatebert/distilroberta-base-climate-sentiment, XerOpred/twitter-climate-sentiment-model ) with the accuracy ranging from  10% to 30% and F1 score about 15%, our model shows wonderful results: accuracy 89%, and F1 score 89% if we use the test dataset from climatebert/climate_sentiment.
 
+  Note that you should paste or type a text concerning the climate change in the API input bar. Otherwise, the model does not work. e,.g, the example input, "The Deputy Mayor also said that while RRF regulations are clear at EU level, bureaucracy at national level in Italy has led to confusion for cities. “At national level, the implementation of RRF funds is not straightforward, there are ministries that have their own rules and cities get different information from different people,” she explained.
+
+Adding to the discussion on whether a simpler, faster model, led by national governments, is best for dispersing EU funds, Boni stressed the importance of finding the right balance.
+
+“I think that if we keep on saying let’s simplify, like the RRF is simpler than the Cohesion policy, we need to make sure this is true,” she stated. “Is simplification the priority, ahead of democracy or effectiveness even. If local authorities are involved, we have seen studies that show investments are better delivered.“
+
+   
   The following code shows how to test in the model.
   python
   ```