dykang/cgraph

dataset for Detecting and Explaining Causes From Text For a Time Series Event, EMNLP'17

28
/ 100
Experimental

This project provides a dataset for understanding how text-based information influences real-world time-series events. It takes various text data like sentiment, topics, and n-gram frequencies, alongside stock prices and tweet IDs, to help you explore causal relationships. A data scientist or researcher in social science or finance would use this to analyze event causation.

No commits in the last 6 months.

Use this if you are a researcher or data scientist looking for a comprehensive dataset to study how textual content, such as news or social media, impacts time-series events like stock price fluctuations.

Not ideal if you are looking for a tool or an algorithm to perform causal inference directly, as this provides only the raw data.

causal-inference social-media-analysis financial-sentiment topic-modeling event-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

15

Forks

3

Language

Shell

License

Last pushed

Aug 31, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/dykang/cgraph"

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