Data Visualization / Data cleaning - Jupyter Notebook. (Python) -- 2
Budget: €30 – €250 EUR
Using 2 different datasets provided by me you will have to visualize data given to you from these datasets .
The goal of the project is to be able to compare individual authors (twitter users) & their following/followers/likes/common key words & phrases within tweets.
The second part of the job is to see if there are matching authors across these datasets. If so, the goal is to then see if common key words & key phrases are utilized. Which hashtags are used and at what point in time.
The goal is to visualize all of this data in one project.
To summarize: These datasets all need to be used, the individual datasets have to be visualized in an understandable manner. Individual authors within each dataset have to be compared with each other. At the end of that we want to see if there are authors that are in multiple datasets (the ones provided) & if so, try to map their tweets/hashtags etc.
I want the code to be, FULLY COMMENTED.
Datasets:
1) https://www.kaggle.com/code/gr0ceries/modeling-of-russian-troll-tweets/data
2) https://www.kaggle.com/datasets/vikasg/russian-troll-tweets
(not a dataset but may be useful, of what is needed: https://www.kaggle.com/code/chadalee/text-analytics-on-russian-troll-tweets-part-1/notebook)
The goal of the project is to be able to compare individual authors (twitter users) & their following/followers/likes/common key words & phrases within tweets.
The second part of the job is to see if there are matching authors across these datasets. If so, the goal is to then see if common key words & key phrases are utilized. Which hashtags are used and at what point in time.
The goal is to visualize all of this data in one project.
To summarize: These datasets all need to be used, the individual datasets have to be visualized in an understandable manner. Individual authors within each dataset have to be compared with each other. At the end of that we want to see if there are authors that are in multiple datasets (the ones provided) & if so, try to map their tweets/hashtags etc.
I want the code to be, FULLY COMMENTED.
Datasets:
1) https://www.kaggle.com/code/gr0ceries/modeling-of-russian-troll-tweets/data
2) https://www.kaggle.com/datasets/vikasg/russian-troll-tweets
(not a dataset but may be useful, of what is needed: https://www.kaggle.com/code/chadalee/text-analytics-on-russian-troll-tweets-part-1/notebook)