https://github.com/cano1998/sentiment-analysis-report-for-amazon-product-reviews

Sentiment analysis of Amazon product reviews. The analysis provides insights into customer sentiment and opinions regarding specific products sold on Amazon.
https://github.com/cano1998/sentiment-analysis-report-for-amazon-product-reviews

pdf pdf-generation sentiment-analysis spacy text-blob

Last synced: 6 days ago
JSON representation

Sentiment analysis of Amazon product reviews. The analysis provides insights into customer sentiment and opinions regarding specific products sold on Amazon.

• Host: GitHub
• URL: https://github.com/cano1998/sentiment-analysis-report-for-amazon-product-reviews
• Owner: Cano1998
• Created: 2024-06-25T16:38:25.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-06-25T16:45:44.000Z (4 months ago)
• Last Synced: 2024-10-31T04:06:04.765Z (6 days ago)
• Topics: pdf, pdf-generation, sentiment-analysis, spacy, text-blob
• Language: Python
• Homepage:
• Size: 6.84 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Sentiment-analysis-report-for-Amazon-product-reviews

The goal of this project is to analyze sentiment from Amazon product reviews using natural language processing (NLP) techniques. The analysis includes preprocessing the text data, extracting sentiment using Spacy and TextBlob, and generating a comprehensive report summarizing the findings.

The tools and libraries that I used:

Spacy: Used for tokenization, part-of-speech tagging, and named entity recognition (NER).

TextBlob: Utilized for sentiment analysis to determine sentiment polarity and subjectivity.

Python libraries: Pandas for data manipulation, and ReportLab for creating PDF reports.

## Analysis steps

-Data preprocessing: Cleaned and prepared the Amazon product review data for analysis.

-Sentiment Analysis:

·Spacy: Extracted linguistic features such as tokens, part-of-speech tags, and named entities.

·TextBlob: Analyzed sentiment polarity and subjectivity of the reviews.

-Report Generation: Compiled the findings into a comprehensive report summarizing:

·Overview of sentiment distribution across reviews.

·Insights into positive, negative, and neutral sentiments.

·Visualizations illustrating sentiment trends and distributions.

## Summary findings

The sentiment analysis revealed insightful patterns in Amazon product reviews, providing a nuanced understanding of customer sentiments towards the products. The report includes detailed visualizations and statistical analyses to support these findings.