Download the file and set it as a Dataframe. $(1$ Marks$)$

Remove punctuations, special characters and stopwords from the text column. Convert the text to lower case. $(2$ Marks$)$

Create two objects Xand y$.$ X will be the $\text{'}$ Text $\text{'}$ column dataframe and y will be the $$Sentiment$$ column. $(1$ Mark$).$

Generate embeddings using CBOW and Skip$-$gram on the text using three different window sizes and display the embeddings using a visualization method $(2$ Marks$).$

Display the embeddings and interpret the results for predicting similar words to the most frequent word using the results of embeddings on different window sizes used in above task. $(2$ Marks$)$

Assume your application involves processing text data with evolving semantics over time $($e$.$g$.,$ news articles$).$ How could dynamic word embeddings be advantageous in capturing the changing meaning of words? What challenges might you face, and how would you address them? $(2$ Marks$)$