Motivation Behind This Project:
My motivation behind this project stems from my passion for consumer insights and understanding human behavior through data analysis. Analyzing the reviews of Disneyland branches in Paris, California, and Hong Kong provides a unique opportunity to delve into the minds of visitors and uncover valuable patterns and insights.
Technical Analysis:
While browsing through thousands of datasets on the internet, I finally came across a dataset of my interest. I sourced my dataset from Kaggle. This dataset contains 42,000 rows of data of reviews on 3 Disneyland branches - Paris, California, and Hong Kong from 2010-2019, posted by visitors on Trip Advisor.
Conducted word frequency analysis on review text data for each Disneyland branch using the NLP toolkit, identifying the most frequently used words by visitors.
Utilized TextBlob and sentiment analyzer in the NLP toolkit to perform sentiment analysis on the review text, determining the distribution of sentiment (positive, negative, and neutral) for each Disneyland branch.
Employed matplotlib to visualize the seasonal variation in average ratings across different seasons of the year for each Disneyland branch, examining potential patterns and trends.
Applied scipy.stats for ANOVA analysis to investigate if there were statistically significant differences in ratings or sentiments expressed in reviews based on the reviewer's country of origin, providing insights into the impact of reviewer location on Disneyland branch experiences.
The whole analysis was done using Jupyter Notebook.
Link to the code: DisneyLand Reviews Analysis