In partnership with
Invest right from your couch
Have you always been kind of interested in investing but found it too intimidating (or just plain boring)? Yeah, we get it. Luckily, today’s brokers are a little less Wall Street and much more accessible. Online stockbrokers provide a much more user-friendly experience to buy and sell stocks—right from your couch. Money.com put together a list of the Best Online Stock Brokers to help you open your first account. Check it out!
Elite Quant Plan – 14-Day Free Trial (This Week Only)
No card needed. Cancel anytime. Zero risk.
You get immediate access to:
Full code from every article (including today’s HMM notebook)
Private GitHub repos & templates
All premium deep dives (3–5 per month)
2 × 1-on-1 calls with me
One custom bot built/fixed for you
Try the entire Elite experience for 14 days — completely free.
→ Start your free trial now 👇
(Doors close in 7 days or when the post goes out of the spotlight — whichever comes first.)
See you on the inside.
👉 Upgrade Now →
🔔 Limited-Time Holiday Deal: 20% Off Our Complete 2026 Playbook! 🔔
Level up before the year ends!
AlgoEdge Insights: 30+ Python-Powered Trading Strategies – The Complete 2026 Playbook
30+ battle-tested algorithmic trading strategies from the AlgoEdge Insights newsletter – fully coded in Python, backtested, and ready to deploy. Your full arsenal for dominating 2026 markets.
Special Promo: Use code DECEMBER2025 for 20% off
Valid only until December 20, 2025 — act fast!
👇 Buy Now & Save 👇
Instant access to every strategy we've shared, plus exclusive extras.
— AlgoEdge Insights Team
Premium Members – Your Full Notebook Is Ready
The complete Google Colab notebook from today’s article (with live data, full Hidden Markov Model, interactive charts, statistics, and one-click CSV export) is waiting for you.
Preview of what you’ll get:
Inside:
Automatic META news fetch from Yahoo Finance (latest 8–10 articles)
Robust sentiment analysis using FinBERT (financial-domain model)
Handles long texts with safe truncation & messy data cleanup
Confidence scores for each news item
Sorted results table with titles, dates, and sentiments
Beautiful bar chart of positive / negative / neutral distribution
Average confidence breakdown per sentiment
Ready-to-use CSV export with one-click download in Colab
Bonus: change one ticker line to run on any stock (e.g., AAPL, TSLA, NVDA)
Free readers – you already got the full breakdown and visuals in the article. Paid members – you get the actual tool.
Not upgraded yet? Fix that in 10 seconds here👇
Google Collab Notebook With Full Code Is Available In the End Of The Article Behind The Paywall 👇 (For Paid Subs Only)
META Stock News Sentiment Analysis Chart
News plays a major role in how people and markets react to stocks. A single article or press release can cause a sharp change in stock price.
Understanding the sentiment behind financial news can help investors make better decisions.
In this article, I will show you how to build a simple sentiment analysis pipeline for stock-related news using FinBERT, a language model designed specifically for financial text.
We’ll use Python, the Hugging Face transformers library, and yfinance to collect news headlines and summaries. Then we'll classify each news summary as:
positive
negative or
neutral
Finally, we'll save and visualize the sentiment distribution.
Retirement Planning Made Easy
Building a retirement plan can be tricky— with so many considerations it’s hard to know where to start. That’s why we’ve put together The 15-Minute Retirement Plan to help investors with $1 million+ create a path forward and navigate important financial decisions in retirement.
What is FinBERT?
FinBERT is a version of the BERT model that has been fine-tuned on financial news articles. It was created by Prosus AI using the original BERT base model from Google.
Unlike general-purpose sentiment models, FinBERT is trained on financial language, which helps it understand domain-specific words and phrasing.
For example, a sentence like “profits decreased less than expected” may be seen as positive in financial contexts, even though it contains the word “decreased”.
FinBERT is designed to handle this kind of nuance.
Installing the Required Libraries
First, we need to install the necessary libraries. These include:
yfinancefor retrieving stock newstransformersandtorchfor working with FinBERTpandasfor handling datamatplotlibplotting results.
%pip install yfinance transformers torch pandas matplotlibThis cell ensures all dependencies are installed in your Python environment.
Importing Python Libraries
Once the libraries are installed, we import them into our workspace.
import pandas as pd
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
import matplotlib.pyplot as plt
import yfinance as yf
plt.style.use("dark_background")We import pandas to handle dataframes, matplotlib.pyplot for plotting, and several modules from transformers to load FinBERT.
yfinance is used to pull news related to a stock ticker.
Loading the FinBERT Model
Now we load the pre-trained FinBERT model and tokenizer.
# Load FinBERT for sentiment analysis
model_name = "ProsusAI/finbert"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)We specify the model name ProsusAI/finbert, which is available on Hugging Face. We create a sentiment classification pipeline using this model and tokenizer.
The pipeline will handle tokenization and prediction for each input string.
Fetching News from Yahoo Finance
We now fetch the latest news articles for a stock of interest.
ticker = "META" # Example ticker symbol
dat = yf.Ticker(ticker)
news = dat.newsWe create a Ticker object for Meta Platforms Inc. (formerly Facebook) and use the .news attribute to access recent news headlines and summaries.
Preparing the News Data
We convert the news into a structured format using a dataframe.
# Extract 'content' part into a DataFrame
df = pd.DataFrame([item["content"] for item in news])
# Keep only desired columns
columns_to_keep = ['title', 'summary', 'pubDate']
df = df[columns_to_keep]
# Display result
df.head(100)Each news item is stored as a dictionary. We extract the "content" part of each item and create a dataframe.
Then we keep only the columns we need:
the title,
summary,
and publication date.
Performing Sentiment Analysis
Now we apply FinBERT to each news summary.
df["sentiment"] = df["summary"].apply(lambda x: classifier(x)[0]['label'])
df["confidence"] = df["summary"].apply(lambda x: classifier(x)[0]['score'])
# Optional: Clean up label casing
df["sentiment"] = df["sentiment"].str.lower()
df.head()We use the sentiment classifier to predict the sentiment of each summary. The .apply function runs the classifier on each row and extracts both the label and confidence score.
We also convert the sentiment labels to lowercase for consistency.
Saving the Results
We can now save the results to a CSV file for future analysis.
# Save to CSV
filename = f"{ticker}_news_sentiment.csv"
df.to_csv(filename, index=False)
print(f"Saved sentiment results to {filename}")This cell creates a filename based on the stock ticker and writes the dataframe to a CSV file. The index=False argument ensures that row indices are not saved.
Visualizing the Sentiment Distribution
Finally, we visualize how many news items were classified as positive, neutral, or negative.
# Visualize sentiment
sentiment_counts = df["sentiment"].value_counts()
sentiment_counts.plot(kind="bar", title=f"{ticker} News Sentiment", color=["blue", "green", "red"])
plt.ylabel("Count")
plt.xticks(rotation=0) # Set x-axis labels to horizontal
plt.tight_layout() # Adjust layout to prevent clipping
plt.savefig(f"{ticker}_sentiment_counts.png")
plt.show()
META Stock News Sentiment Analysis Chart
We count how many times each sentiment label appears and use a bar chart to show the distribution. Green represents positive news, red represents negative, and gray is for neutral sentiment.
Subscribe to our premium content to read the rest.
Become a paying subscriber to get access to this post and other subscriber-only content.
Upgrade