Skip to content
  • datasets
  • sentiment

News Sentiment Dataset

Access AI-powered sentiment analysis derived from financial news. FinBrain’s NLP models process thousands of articles daily and distill each ticker’s news flow into a single daily sentiment score, helping you gauge market mood and momentum.

What’s Included

Section titled “What’s Included”

The News Sentiment dataset provides:

  • Sentiment Score: Normalized numeric score from -1 (bearish) to +1 (bullish) — one score per ticker per trading day
  • Array-Based Data: Historical sentiment returned as an array of date/score objects
  • Pre-Open Delivery: Each day’s score is finalized before the US market opens and does not change intraday
  • Consistent History: The live pipeline and the historical backfill share identical scoring logic, so history matches what the live feed delivered — values are not restated
  • Historical Data: 5+ years of sentiment history (since 2021) for backtesting
  • Flexible Filtering: Filter by date range or limit the number of results

Coverage

Section titled “Coverage”
Coverage Detail
Universe 12,000+ US-listed stocks and ETFs (NYSE and NASDAQ), including every S&P 500 and Dow 30 constituent
Granularity One score per ticker per trading day
Update Frequency Daily, finalized before US market open

Score density follows news flow: thinly covered names carry sparser meaningful observations than large caps. Selected international markets have partial sentiment coverage; check ticker availability via the tickers endpoint.

Sentiment scores have 5+ years of historical data available for backtesting and trend analysis.

Understanding Sentiment Scores

Section titled “Understanding Sentiment Scores”
Range Interpretation
0.5 to 1.0 Strong bullish sentiment
0.2 to 0.5 Moderate bullish sentiment
-0.2 to 0.2 Neutral sentiment
-0.5 to -0.2 Moderate bearish sentiment
-1.0 to -0.5 Strong bearish sentiment

Sentiment scores are returned as numbers in the v2 API.

Quick Start

Section titled “Quick Start”
from finbrain import FinBrainClient


fb = FinBrainClient(api_key="YOUR_API_KEY")


df = fb.sentiments.ticker("AAPL", as_dataframe=True)
print(df)

You can also filter by date range or limit results:

from finbrain import FinBrainClient


fb = FinBrainClient(api_key="YOUR_API_KEY")


# Get sentiment with date range
df = fb.sentiments.ticker("AAPL", date_from="2025-01-01", date_to="2025-06-30",
                          as_dataframe=True)
print(df.head(30))

For complete code examples in Python, JavaScript, C++, Rust, and cURL, see the API Reference.

Visualization

Section titled “Visualization”

Plot sentiment scores with the built-in SDK chart:

from finbrain import FinBrainClient


fb = FinBrainClient(api_key="YOUR_API_KEY")


# One-line interactive sentiment chart
fb.plot.sentiments("TSLA")
Sentiments Chart
TSLA news sentiment over time

Use Cases

Section titled “Use Cases”

Sentiment-Based Trading Signals

Section titled “Sentiment-Based Trading Signals”

Generate trading signals based on sentiment thresholds:

from finbrain import FinBrainClient


fb = FinBrainClient(api_key="YOUR_API_KEY")


def get_sentiment_signal(symbol):
    """Generate trading signal from sentiment score"""
    df = fb.sentiments.ticker(symbol, as_dataframe=True)


    if df.empty:
        return "no_data"


    latest_score = df["score"].iloc[0]


    if latest_score > 0.5:
        return "strong_buy"
    elif latest_score > 0.2:
        return "buy"
    elif latest_score < -0.5:
        return "strong_sell"
    elif latest_score < -0.2:
        return "sell"
    else:
        return "hold"


signal = get_sentiment_signal("TSLA")
print(f"Signal: {signal}")

Sentiment Screening

Section titled “Sentiment Screening”

Screen a watchlist for tickers with extreme sentiment:

from finbrain import FinBrainClient


fb = FinBrainClient(api_key="YOUR_API_KEY")


watchlist = ["AAPL", "GOOGL", "MSFT", "AMZN", "NVDA", "TSLA"]


bullish = []
bearish = []


for symbol in watchlist:
    df = fb.sentiments.ticker(symbol, as_dataframe=True)
    if not df.empty:
        score = df["score"].iloc[0]
        if score > 0.5:
            bullish.append((symbol, score))
        elif score < -0.5:
            bearish.append((symbol, score))


print("Bullish tickers:", bullish)
print("Bearish tickers:", bearish)

Combine with Price Predictions

Section titled “Combine with Price Predictions”

Enhance prediction confidence when sentiment aligns with expected price movement:

from finbrain import FinBrainClient


fb = FinBrainClient(api_key="YOUR_API_KEY")


def analyze_ticker(symbol):
    """High conviction signals when predictions and sentiment align"""
    # Get predictions
    pred_result = fb.predictions.ticker(symbol, prediction_type="daily")
    expected_short = pred_result["metadata"]["expectedShortTerm"]


    # Get sentiment
    sent_df = fb.sentiments.ticker(symbol, as_dataframe=True)
    sent_score = sent_df["score"].iloc[0]


    # Stronger signal when expected move and sentiment align
    if expected_short > 0.5 and sent_score > 0.3:
        return "high_conviction_buy"
    elif expected_short < -0.5 and sent_score < -0.3:
        return "high_conviction_sell"
    else:
        return "mixed_signals"


result = analyze_ticker("AAPL")
print(result)
Section titled “Related Resources”