Task:   Find word(s) (theme or topic) that occurs frequently in Taylor Swift and Katie Perry corpus.  You will use Keyword analysis, Collocate, Concordance and N‐grams functions to explain how the  word(s) (theme) develops differently across the lyrics of the songwriters. Eventually, you may  also want to split the corpus by period and repeat your analysis to find out if there a given  theme/topic is particularly linked to a specific period years (years are indicated in the name of  each file).   Deliverables:  Please note that only submissions through Canvas will be accepted. Email submission will not  count for this assignment. 

1. Output Files (Zip): Save your output when applicable to create four text files for the work 

done in Section 2, 3, 4 and 5. Submit the 4 output text files in 1 Zip file  with your first and  last name clearly indicated in the zip file. 

2. Report: your first and last name clearly indicated in the file name. Points will be deducted 

for spelling errors. 

Write a minimum of four pages report to describe the following: 

Section 1: (5 points): Introduction.  

Lay out The Research Question and present the Corpus. 

Section 2: (20 points): Report Keyword Analysis  Do a keywords analysis to find word(s) (theme or topic) that occurs frequently in:  1. Taylor Swift corpus 

2. Katie Perry corpus  3. Taylor Swift and Katie Perry Corpus (both directories)  You will use the Full Brown Corpus as a reference corpus for the above 3 keyword analysis.   4. You will also do a keywords analysis of Taylor Swift using Katie Perry as a reference corpus.  5. You will also do a keywords analysis of Katie Perry using Taylor Swift as a reference corpus 

Section 3: (15 points):  Report Collocate Analysis (one report for each singer)  Define collocate analysis and explain the results of finding collocates around your key words.  Experiment with collocates of different windows and see which window size (words on the left  and on the right) seems of most use in identifying themes. 

Section 4 (15 points):  Report Concordance Analysis (one report for each singer)  Define concordance analysis and use concordance to extract larger contexts, including full  sentences, where your keywords and collocates reside in the corpus of each singer. Analyze  in a paragraph or two how the finding of these contexts can help you find themes for each  singer. 

Section 5 ( 15 points):  Report N‐Gram Analysis (one report for each singer)  Define N‐Gram analysis and use N‐Gram function to extract the most frequent N‐Grams for  each singer using different cluster size. Analyze in a paragraph or two how the finding of  these N‐Grams can possibly help you find themes for each singer. 

Section 6 (20 points).  Reporting Taylor Swift and Katie Perry Themes 

Enumerate and briefly describe a list of 5‐10 themes that Taylor Swift and Katy Perry sing about  based on your work with AntConc. 

You may also want to check the listing of themes in Taylor Swift songs at  https://literarydevices.net/10‐different‐themes‐in‐taylor‐swift‐songs/ and the themes of Katy  Perry songs at https://en.wikipedia.org/wiki/Portal:Katy_Perry/Topics 

Section 7: (10 points):  Conclusion 

Summarize your findings and own insights in this task.