Implemented sentiment analysis solution for Kenya Airways - #9
Open
Matthew-kabiu wants to merge 1 commit into
Open
Implemented sentiment analysis solution for Kenya Airways#9Matthew-kabiu wants to merge 1 commit into
Matthew-kabiu wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces the complete implementation of the Sentiment Analysis Solution for Kenya Airways. The solution is designed to scrape customer reviews from travel review sites, process the data, analyze the sentiment expressed in the reviews, and present the findings through a user-friendly web dashboard.
Key Features:
Data Scraping:
Implemented a web scraper (scraper.py) that collects customer reviews from the airlinequality.com website. The scraper is capable of fetching reviews asynchronously, optimizing the data collection process.
Data Processing & Sentiment Analysis:
Developed preprocessing functions (processor.py) to clean and prepare the scraped review text.
Integrated the VADER sentiment analysis tool to categorize reviews into positive, negative, or neutral sentiments.
Data Storage:
Created functionality (storage.py) to save the processed review data into a CSV file and load it when necessary, ensuring data persistence.
Visualization:
Generated var
README.md
ious visualizations (visualization.py) including word clouds, sentiment distribution, and word count distribution to visually represent the sentiment analysis results.
Dashboard Implementation:
Built a web dashboard using Dash (dashboard.py) that displays the generated visualizations, providing an interactive way to explore customer sentiment data.
Assumptions:
The solution currently scrapes data from a single travel review site (airlinequality.com). Future enhancements could include additional sources such as social media platforms.
Sentiment analysis is based on the VADER tool, which works well for general sentiment analysis but may not capture industry-specific nuances.
Limitations:
The scraping module is designed to handle up to 48 pages of reviews. This limit can be adjusted based on the desired data scope.
Real-time data processing is not implemented; the solution processes data in batch mode when the pipeline is executed.
The confusion matrix generation is set up but not fully integrated into the current visualization workflow, as the machine learning model is not a part of this implementation.