Use Python 3 for this question. Do the sentiment analysis based on a text file which contains numerous tweets in its raw text format. All tweets collected in this file contains a key word specified by the instructor. The key word being used is “Trump”. You can use the raw tweets file provided by the following link: tinyurl.com/46ntt3a5. You will need to convert this to a .txt file for this assignment. Your raw tweets file size at least needs to be 350K. After you have the raw tweets file ready, you need to per
Use Python 3 for this question.
Do the sentiment analysis based on a text file which contains numerous tweets in its raw text format. All tweets collected in this file contains a key word specified by the instructor. The key word being used is “Trump”.
You can use the raw tweets file provided by the following link: tinyurl.com/46ntt3a5. You will need to convert this to a .txt file for this assignment.
Your raw tweets file size at least needs to be 350K.
After you have the raw tweets file ready, you need to perform the following tasks in a Jupyter notebook file. First you need to clean up the tweet file content to the best you can. For each word that is not a “stop word” (and, the, a, is, as, …), assign a value +1 for positive sentiment or a value -1 for negative sentiment. A list of “positive” words will be provided to you. You can easily find a list of “stop words”, and a list of “negative” words online. For the words that is not in positive/negative/stop words, count as ‘others’.
Explain code using comments and mark down cells.
You need to answer the following questions:
• What’s the word count for positive/negative/stop word/others?
• What’s the ratio of positive/negative/stop word/others compare to the total word count?
• What’s the ratio for positive vs negative word count?
• Do you think that the general sentiment is negative or positive? Weakly or strongly?
Trending now
This is a popular solution!
Step by step
Solved in 2 steps
