How to beginner · 3 min read

How to classify news articles by topic

Q: How to classify news articles by topic

Use a large language model like gpt-4o via the OpenAI Python SDK to classify news articles by topic. Send the article text as a prompt with a clear instruction to the model to return the topic label.

Quick answer

Use a large language model like gpt-4o via the OpenAI Python SDK to classify news articles by topic. Send the article text as a prompt with a clear instruction to the model to return the topic label.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the openai Python package and set your API key as an environment variable.

Run pip install openai to install the SDK.
Set your API key in your shell: export OPENAI_API_KEY='your_api_key' (Linux/macOS) or setx OPENAI_API_KEY "your_api_key" (Windows).

bash

pip install openai

output

Collecting openai
  Downloading openai-1.x.x-py3-none-any.whl (xx kB)
Installing collected packages: openai
Successfully installed openai-1.x.x

Step by step

This example shows how to classify a news article by topic using the gpt-4o model. The prompt instructs the model to return a concise topic label.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

article_text = "The stock market rallied today as tech shares surged amid strong earnings reports."

messages = [
    {"role": "user", "content": f"Classify the following news article into a topic category in one word:\n\n{article_text}"}
]

response = client.chat.completions.create(
    model="gpt-4o",
    messages=messages
)

topic = response.choices[0].message.content.strip()
print(f"Topic: {topic}")

output

Topic: Finance

Common variations

You can use other models like gpt-4o-mini for faster, cheaper classification or claude-3-5-sonnet-20241022 via the Anthropic SDK. Async calls and streaming are also supported for large-scale or real-time classification.

python

import asyncio
import os
from openai import OpenAI

async def classify_article_async(article: str) -> str:
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    messages = [{"role": "user", "content": f"Classify the news article into a topic in one word:\n\n{article}"}]
    response = await client.chat.completions.create(
        model="gpt-4o-mini",
        messages=messages
    )
    return response.choices[0].message.content.strip()

async def main():
    article = "NASA announced a new mission to explore Jupiter's moons."
    topic = await classify_article_async(article)
    print(f"Async topic: {topic}")

asyncio.run(main())

output

Async topic: Space

Troubleshooting

If you get an authentication error, verify your OPENAI_API_KEY environment variable is set correctly.
If the model returns unexpected output, refine your prompt to be more explicit about returning a single topic word.
For rate limits, consider using smaller models like gpt-4o-mini or batching requests.

✅

Key Takeaways

Use the OpenAI Python SDK with gpt-4o for accurate news topic classification.
Craft clear prompts instructing the model to return concise topic labels.
Async and smaller models like gpt-4o-mini enable scalable classification.
Always set your API key via environment variables to avoid authentication errors.

Verified 2026-04 · gpt-4o, gpt-4o-mini, claude-3-5-sonnet-20241022

Verify ↗