Prompt Engineering Tutorial and Prompt PracticePrompt Library

Sentiment Classification

Zero-shot sentiment classification prompt

CHAPTER PROMPT DECISION

01Prompt problem

Zero-shot sentiment classification prompt

02Reviewable output

A reusable prompt, example set, evaluation record or safety rule with its task boundary preserved.

03Definition of done

Run at least one representative case, inspect the result and record what still requires human review.

Background

This prompt tests an LLM's classification ability: categorize a piece of text as neutral / negative / positive.

Prompt

Classify the text into neutral, negative, or positive
Text: I think the food was okay.
Sentiment:

Template

Classify the text into neutral, negative, or positive
Text: {input}
Sentiment:

API (example)

GPT-4 (OpenAI)

from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {
            "role": "user",
            "content": "Classify the text into neutral, negative, or positive\nText: I think the food was okay.\nSentiment:\n"
        }
    ],
    temperature=1,
    max_tokens=256,
    top_p=1,
    frequency_penalty=0,
    presence_penalty=0
)