FranxYao/pivot_analysis

Implementation of INLG 19 paper: Rethinking Text Attribute Transfer: A Lexical Analysis

29
/ 100
Experimental

This project helps you understand which specific words drive the sentiment or style of text in large datasets like product reviews, social media posts, or news articles. It takes a collection of text labeled with different attributes (like 'positive' or 'negative') and identifies the key 'pivot' words that are most indicative of each attribute. The output includes lists of these pivot words, their precision and recall, and examples of how they appear in sentences, enabling analysts to quickly pinpoint influential vocabulary.

No commits in the last 6 months.

Use this if you need to quantitatively identify, measure, and visualize the impact of individual words on text attributes like sentiment or style within your datasets.

Not ideal if you are looking for a tool to perform actual text style transfer or generate new text content.

text-analysis sentiment-analysis natural-language-understanding data-science content-moderation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

16

Forks

5

Language

Python

License

Last pushed

Sep 30, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/FranxYao/pivot_analysis"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.