📚
Quanda
  • Content Model Catalog
  • KR STOCK
    • Market
      • Price Volume
      • Price Volume v2
      • Investor Activity
      • Credit
    • Financial
      • Financial Statements
      • Analyst Consensus
    • Quantitative
      • Descriptor
      • Factor
        • Factor (1)
        • Factor (2)
      • Regime
    • Event
      • Company Status
      • Corporate Actions
    • Economic
      • Indicators
    • Unstructured
      • Theme
        • Theme Analytics Metrics
        • Company Keyword
      • EWS (Early Warning Signal)
        • Korea Sentiment Index
        • Korea EWS Index
        • Keyterm Sentiment Analytics Metrics
    • [Free] Open dataset
  • US ETF
    • Market
      • Price Volume
  • US STOCK
    • Market
      • Price Volume
      • Classification
      • Universe
    • Financial
      • Financial Statement
      • PIT Financial Statement
    • Quantitative
      • Factor
    • Unstructured
      • EWS (Early Warning Signal)
        • US sentiment index
        • US EWS Index
        • Keyterm Sentiment Analytics Metrics
  • VN STOCK
    • Market
      • Price Volume
      • Classification
    • Financial
      • Ratio TTM
  • VN Stock (deprecated)
    • Market
      • Price Volume
      • Classification
    • Event
      • Corporate Actions
  • ID STOCK
    • Market
      • Price Volume
      • Classification
  • CRYPTO SPOT
    • Market
      • Price Volume
  • CRYPTO FUTURE
    • Market
      • Price Volume
Powered by GitBook
On this page
  • Example code
  • Metadata
  • Item List
  • All Sentiment
  • Negative Sentiment
  • Neutral Sentiment
  • Positive Sentiment

Was this helpful?

Edit on GitHub
  1. US STOCK
  2. Unstructured
  3. EWS (Early Warning Signal)

Keyterm Sentiment Analytics Metrics

This dataset provides metrics on news articles, segmented by sentiment (positive, negative, neutral) and category, including rates and counts of materials.

Example code

from finter.data import ContentFactory
cf = ContentFactory("us_stock", 20240101, 20240201)

# sentiment_us category
df = cf.get_df("all-mat_cat_rate", cagegory='sentiment_us')

# sentiment_exp_us category
df = cf.get_df("all-mat_cat_rate", cagegory='sentiment_exp_us')

Metadata

Valid From
Delivery Schedule
Time Zone
Data Frequency

2005-01-01

UTC 00 21 * * *

Asia/Seoul

1d

Item List

  • Use sentiment_us category for US

  • Use sentiment_exp_us category for US Expanded

All Sentiment

  • all-mat_cat_rate: Category rate for overall sentiment on the given day in the U.S.

  • all-N_of_mat_cat_each: Number of news articles for overall sentiment in each category on the given day in the U.S.

  • all-N_of_news: Number of total news articles for overall sentiment on the given day in the U.S.

Negative Sentiment

  • neg-mat_cat_rate: Category rate for negative sentiment on the given day in the U.S.

  • neg-N_of_mat_cat_each: Number of news articles for negative sentiment in each category on the given day in the U.S.

  • neg-N_of_news: Number of total news articles for negative sentiment on the given day in the U.S.

Neutral Sentiment

  • neu-mat_cat_rate: Category rate for neutral sentiment on the given day in the U.S.

  • neu-N_of_mat_cat_each: Number of news articles for neutral sentiment in each category on the given day in the U.S.

  • neu-N_of_news: Number of total news articles for neutral sentiment on the given day in the U.S.

Positive Sentiment

  • pos-mat_cat_rate: Category rate for positive sentiment on the given day in the U.S.

  • pos-N_of_mat_cat_each: Number of news articles for positive sentiment in each category on the given day in the U.S.

  • pos-N_of_news: Number of total news articles for positive sentiment on the given day in the U.S.

PreviousUS EWS IndexNextMarket

Last updated 9 months ago

Was this helpful?