Questions 4 Topics Classification from the text

Given a dataset named “topics_dataset.tab” which includes sentences and corresponding labels indicating the topic of each sentence, complete the following tasks:

1. Format the text dataset into the Bag of Words using Python’s Orange library. Then, use the data to train Logistic Regression classifiers capable of classifying the four topics: 1-World, 2-Sports, 3-Business, and 4-Sci/Tech. The classifiers should have an F1 score of at least 0.8 and an AUC score of at least 0.8 based on the test data.(2 marks)
2. Explain the importance of text preprocessing in machine learning. Provide three specific preprocessing techniques commonly used in natural language processing (NLP). (4 marks)