Go to example tasks
Ai Classify Review Sentiment And Topics
Run customer reviews through Claude Haiku 4.5 and get back a sentiment label, the main topic and the product aspects mentioned, as three new columns you can filter and count. Uses four built-in example reviews; point it at your own reviews dataset or file.
Dataset AI Enrich (LLM Classify, Extract, Summarise Rows)nerolabs/dataset-ai-enrich
Id
Product
Review
Sentiment
+4 fieldsTextNumberBooleanListObject
Input
Data (inline)
id:1+3
product:Wireless earbuds+3
review:Battery life is fantastic and the sound is crisp, but the charging case feels cheap and creaks.+3
Instruction (applied to every row)(required):Classify the sentiment of this customer review as positive, neutral or negative. Then name the main topic in one to three words, and list up to three product aspects the customer mentions.
Product: {{product}}
Review: {{review}}
Output columns
name:sentiment+2
type:string+2
description:exactly one of: positive, neutral, negative+2
Model:anthropic/claude-haiku-4.5
Export file formats:csv
Output fields
Id
Product
Review
Sentiment
Topic
Aspects
Model
Error
Sign up on Apify01
Create your Apify account to access the Dataset AI Enrich (LLM Classify, Extract, Summarise Rows).
Start the run02
The Actor will start running based on the input automatically.
Receive the output03
Monitor the progress in real-time. You will be notified as soon as your dataset is complete and ready for review.
Integrate into your workflow04
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow.
