Skip to main content

An optimized stopwords list for sentiment analysis that retains key negations like 'not', 'won't', and 'wouldn't', along with intensity modifiers like 'very' and 'most' to preserve sentiment accuracy.

Project description

Revised Stopwords for NLP

Overview

This package provides an optimized stopwords list for sentiment analysis by preserving sentiment-related words that NLTK’s default list would typically remove. By retaining key negations and intensity modifiers, this package ensures that sentiment expressions remain intact, leading to more accurate sentiment classification.

Features

  • Retains crucial negations (not, won't, wouldn't, shouldn't, etc.)
  • Keeps intensity modifiers (very, most, more, etc.) for better sentiment retention
  • Removes only words that do not impact sentiment analysis

Installation

Install via pip

pip install revised-stopwords

Import and Use in Your NLP Pipeline

from revised_stopwords import get_revised_stopwords

# Get the optimized stopwords list
stopwords_list = get_revised_stopwords()

print(stopwords_list)  # Output: A set of refined stopwords

Example: Removing Stopwords from Text

from revised_stopwords import get_revised_stopwords

text = "I don't think this is a very good idea"
tokens = text.lower().split()  # Basic word split

filtered_tokens = [word for word in tokens if word not in get_revised_stopwords()]

print(filtered_tokens)
# Output: ["don't", 'think', 'very', 'good', 'idea']

Troubleshooting

LookupError: Resource stopwords not found?

Please use the NLTK Downloader to obtain the resource. Run this command once to manually download stopwords

import nltk
nltk.download('stopwords')

ModuleNotFoundError: No module named 'nltk'?

This error means that the nltk library is not installed in your environment.
Ensure NLTK is installed:

pip install nltk

Contributing

Want to improve this package? Feel free to fork the repo, submit PRs, or suggest enhancements!

How to Contribute:

  1. Fork this repository to your GitHub account.

  2. Clone your forked repo:

    git clone https://github.com/priyaa279/revised_stopwords.git
    
  3. Create a new branch for your changes:

    git checkout -b feature-branch-name
    
  4. Make your changes and commit them:

    git commit -m "Describe your change"
    
  5. Push your branch to GitHub:

    git push origin feature-branch-name
    

Submit a Pull Request (PR) for review. For major changes, please open an issue first to discuss what you'd like to modify.

License

This project is open-source and licensed under the MIT License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

revised-stopwords-0.1.3.tar.gz (3.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

revised_stopwords-0.1.3-py3-none-any.whl (4.2 kB view details)

Uploaded Python 3

File details

Details for the file revised-stopwords-0.1.3.tar.gz.

File metadata

  • Download URL: revised-stopwords-0.1.3.tar.gz
  • Upload date:
  • Size: 3.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.6

File hashes

Hashes for revised-stopwords-0.1.3.tar.gz
Algorithm Hash digest
SHA256 9fbac67a84cb4a2c1d249d5304d6dc488b118aaba17e697a05d26e2f2a5cc19f
MD5 e88ce1fb1f8cb8fd35340efd983c25f7
BLAKE2b-256 e08599c9aba143acaa646733d28ba3e9b652af11914aeda5a103f7127cb791b9

See more details on using hashes here.

File details

Details for the file revised_stopwords-0.1.3-py3-none-any.whl.

File metadata

File hashes

Hashes for revised_stopwords-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 6868f787d3fa82fa8b64eefed2a90b653a98c2b9ae1b5df9a6494150de7b3c5d
MD5 83f6ef6c3fbbc938ec64977dce2f6b33
BLAKE2b-256 4a890ddd0aa5dbb5822874261e912a0adc0c2d57a2a97a58e714e33dd8a2979a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page