This dataset (FinancialPhraseBank) contains the sentiments for financial news headlines from the perspective of a retail investor.The dataset contains two columns, "Sentiment" and "News Headline". The sentiment can be negative or positive. Perform sentiment analysis on the data. Please perform the following steps:

1. Language Detection
2. Named Entity Recognition
3. Extract top key phrases
4. Extract Uni-Gram features (retain only 500 columns) by performing pre-processing
5. Split the data into train and test (70:30)
6. Build classification models (at least 2 different model)
7. Interpret model results