Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Kopieren Sie diesen Prompt in unsere Developer Console, um ihn selbst auszuprobieren!
| Inhalt | |
|---|---|
| System | Ihre Aufgabe ist es, den bereitgestellten Tweet zu analysieren und den primären Ton und die Stimmung zu identifizieren, die der Autor ausdrückt. Der Ton sollte als einer der folgenden klassifiziert werden: Positiv, Negativ, Neutral, Humorvoll, Sarkastisch, Enthusiastisch, Wütend oder Informativ. Die Stimmung sollte als Positiv, Negativ oder Neutral klassifiziert werden. Geben Sie eine kurze Erklärung für Ihre Klassifizierungen, heben Sie die Schlüsselwörter, Phrasen, Emoticons oder andere Elemente hervor, die Ihre Entscheidung beeinflusst haben. |
| User | Wow, ich bin so beeindruckt von der Handhabung dieser Krise durch das Unternehmen. 🙄 Sie haben ihre Prioritäten wirklich richtig gesetzt. #sarcasm #fail |
Ton: Sarkastisch Stimmung: Negativ
import anthropic
client = anthropic.Anthropic(
# defaults to os.environ.get("ANTHROPIC_API_KEY")
api_key="my_api_key",
)
message = client.messages.create(
model="claude-opus-4-6",
max_tokens=1000,
temperature=0,
system="Your task is to analyze the provided tweet and identify the primary tone and sentiment expressed by the author. The tone should be classified as one of the following: Positive, Negative, Neutral, Humorous, Sarcastic, Enthusiastic, Angry, or Informative. The sentiment should be classified as Positive, Negative, or Neutral. Provide a brief explanation for your classifications, highlighting the key words, phrases, emoticons, or other elements that influenced your decision.",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Wow, I'm so impressed by the company's handling of this crisis. 🙄 They really have their priorities straight. #sarcasm #fail"
}
]
}
]
)
print(message.content)
Was this page helpful?