Skip to content

An NLP analysis (topic modeling and sentiment analysis) of Disneyland reviews for 3 of its branches (California, Hong Kong, and Paris).

Notifications You must be signed in to change notification settings

GabeOw/NLP-Analysis-for-Disneyland-Reviews

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

Project Overview:

  • An analysis (topic modeling and sentiment analysis) of Disneyland reviews for 3 of its branches (California, Hong Kong, and Paris). Results were based on joint findings.

General Purpose:

  • Topic modeling can be used by Disney to automatically organize and categorize large collections of text data (in this case customer reviews). This makes it easier to analyze and understand the topics that are prevalent in customers’ feedback. Topic modeling can also be used to improve document search and retrieval efficiency within their internal review databases by identifying the main topics in a document and using those topics as keywords for search queries.

  • Sentiment analysis can be used to automatically classify and analyze the sentiment (positive, negative, or neutral) of large volumes of text data, such as customer reviews, social media posts, and survey responses (independent of the “star” rating of the review).

  • Topic modeling can be used in conjunction with other natural language processing techniques, such as sentiment analysis, to gain deeper insights into customer opinions and preferences. For example, Disney could use topic modeling to identify the main topics of discussion in customer reviews, and then use sentiment analysis to determine the overall sentiment (positive, negative, or neutral) associated with those topics.

  • Disney can use all of this information to prioritize areas for improvement in their products or services for each specific park location.

Data Source:

https://www.kaggle.com/datasets/arushchillar/disneyland-reviews

Results:

Hong Kong:

  • Park entrance is not well-designed (long waits)
  • Overpriced food and bad quality
  • Small park and very few rides (compared to other Disney parks)

California:

  • Overpriced food
  • Extremely expensive overall
  • A lot of rides are closed (for unknown reasons)
  • Huge crowds with long wait times

Paris:

  • Long wait times, rides closed, extremely expensive
  • Slow and inefficient service
  • Run-down, not well-maintained, dirty
  • A lot of people smoking
  • Food is expensive, low quality, and there is not much variety
  • Staff provides slow service and lacks energy (comes across as not caring)
  • Few Disney characters walk around the park

About

An NLP analysis (topic modeling and sentiment analysis) of Disneyland reviews for 3 of its branches (California, Hong Kong, and Paris).

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published