CS8803-Homework 1 Solved

In this basic assignment, you’ll begin the process of discovering how data from a user’s social media profile is used by various organizations. You’ll accomplish this task by examining your own data profile on social media. We will focus on Facebook for this assignment (see the note below if you’d like to choose another social media platform).

 

•        Step 1: Information on how to download a coy of your data can be found at:

        https://www.facebook.com/help/1701730696756992                                      

 

•        Step 2: Download your data associated with the “Select Ads” category (two formats are available:

html and json).

 

•        Step 3: Based on the data file advertisers_who_uploaded_a_contact_list_with_your_information.html, categorize advertisers into (no less than) 5 categories and (no more than) 10 categories.  

 

•        Step 4: Create a data flow graph (using http://sankeymatic.com/build/) that associates your advertiser categories with three types of data buckets: Relevant, Not Relevant, Way Off. Feel free to be creative in the naming of your buckets.  

 

•        Step 5: Compute basic statistical measures on the data (per category): count, mean, accuracy (= %Relevant), and rubbish (%Way Off). Identify which category was the most accurate and which was the least.    

 

•        Step 6: Identify which advertisers are associated with a regulated domain in law (i.e. Credit,

Education, Employment, Housing and ‘Public Accommodation’). For each regulated domain, list how many fall within and the associated advertiser.  

 

•        Step 7: Turn in a report documenting your findings, including number of advertisers, categories identified, script (if using sankeymatic) and data flow graphic, statistical measures, regulated domain/advertiser list. As an example, here’s the report associated with my data:

 

Prof. Ayanna Howard

 

Number of Advertisers: 1700

 

Categories Identified (5):                                    

Car Companies (e.g. International Autos Mercedes Benz)                                                 
 

 

 

 

Table: Summary Statistics Count (Partial Example for One Category)

Variable
Ordinal Categories  
Count
Mean
Accuracy
Rubbish Meter
Shopping
-1. U Got to be Kidding
85
 
 
 
 
0. No
85
 
 
 
 
1. Yes
0
 
 
 
 
Total
170
-0.5
0%
50%
             

My most accurate category: Social Impact

My least accurate category (i.e. rubbish): Shopping

 

Advertisers and Associated Regulated Domains in Law:

Credit (2):  

Alliant Credit Union

Anchor Capital  

 

Education (3):

Baylor College of Medicine  

Daniels College of Business

Georgia State University

 

Employment (0)

 

Housing (2):

Ashton Woods Homes

Echo Fine Properties

 In this basic assignment, you’ll begin the process of discovering how data from a user’s social media profile is used by various organizations. You’ll accomplish this task by examining your own data profile on social media. We will focus on Facebook for this assignment (see the note below if you’d like to choose another social media platform).

 

•        Step 1: Information on how to download a coy of your data can be found at:

        https://www.facebook.com/help/1701730696756992                                      

 

•        Step 2: Download your data associated with the “Select Ads” category (two formats are available:

html and json).

 

•        Step 3: Based on the data file advertisers_who_uploaded_a_contact_list_with_your_information.html, categorize advertisers into (no less than) 5 categories and (no more than) 10 categories.  

 

•        Step 4: Create a data flow graph (using http://sankeymatic.com/build/) that associates your advertiser categories with three types of data buckets: Relevant, Not Relevant, Way Off. Feel free to be creative in the naming of your buckets.  

 

•        Step 5: Compute basic statistical measures on the data (per category): count, mean, accuracy (= %Relevant), and rubbish (%Way Off). Identify which category was the most accurate and which was the least.    

 

•        Step 6: Identify which advertisers are associated with a regulated domain in law (i.e. Credit,

Education, Employment, Housing and ‘Public Accommodation’). For each regulated domain, list how many fall within and the associated advertiser.  

 

•        Step 7: Turn in a report documenting your findings, including number of advertisers, categories identified, script (if using sankeymatic) and data flow graphic, statistical measures, regulated domain/advertiser list. As an example, here’s the report associated with my data:

 

Prof. Ayanna Howard

 

Number of Advertisers: 1700

 

Categories Identified (5):                                    

Car Companies (e.g. International Autos Mercedes Benz)                                                 
 

 

 

 

Table: Summary Statistics Count (Partial Example for One Category)

Variable
Ordinal Categories  
Count
Mean
Accuracy
Rubbish Meter
Shopping
-1. U Got to be Kidding
85
 
 
 
 
0. No
85
 
 
 
 
1. Yes
0
 
 
 
 
Total
170
-0.5
0%
50%
             

My most accurate category: Social Impact

My least accurate category (i.e. rubbish): Shopping

 

Advertisers and Associated Regulated Domains in Law:

Credit (2):  

Alliant Credit Union

Anchor Capital  

 

Education (3):

Baylor College of Medicine  

Daniels College of Business

Georgia State University

 

Employment (0)

 

Housing (2):

Ashton Woods Homes

Echo Fine Properties