This project was part of the seminar "Web & Society: A Computational Social Science Perspective", part of my masters in Social and Economics Data Science.
Here I scraped a website of my own interest (www.outdoorgearlab.com), apply NLP preprocessing and an analysis method, I chose to apply cosine similarity to compare the different backpacks and contrast the result with the overall score that the website gives them.
The scraped articles reviews of best laptop-backpacks in 2022 can be found in https://www.outdoorgearlab.com/topics/travel/best-laptop-backpack
In this repository you will find:
- Code and analysis in Python
- Final dataset stored as excel file (backpack.xlsx)
- Wordclouds done for each backpack
Have fun,
Trinidad