We continued to work on our presentation for our findings for Lenovo, rechecking and finalizing our presentation and data. It was quite interesting to be on the other side and receiving feedback to analyze.
Author: yunlong_yu
Lenovo, Kaeshev and Leo, Day 5
We finally overcame our problem! With patience, creativity, and perseverance, we got our code to work, which helped us massively simplify our task of going through 20000 reviews. Using this, we were able to categorize them, and filter meaningful comments out, and a report was generated.
Here is our report so far
Lenovo, Kaeshev and Leo, Day 4
It turns out 20,000 review is a lot, and it’s not all smooth sailing. We began running into difficulty in separating data into meaningful categories (especially since 1/3 of people didn’t write more than half a sentence), and our code began to have some issues. Besides looking for solutions, we did some more detailed analysis on the smaller sample sizes, and gave our report.
Hashmap diagram (what we are trying to get to work):
Lenovo, Kaeshev and Leo, Day 2
Today we finished our code from yesterday, which helped us sort, categorize, and find various trends throughout consumer feedback Lenovo received. We were able to find keywords in the reviews with our program and determine the frequency of the keywords, which were then used to analyze the review score and satisfaction regarding instances of those words to find possible correlations between the words and customer satisfaction (or dissatisfaction). Using these methods, we were able to iterate through the 1000 reviews that were given to us and find the similarities and trends between them. We presented our findings to the WEP host.
Here is a small snippet of the report of our findings of a 299 sample size:
