Product Reviews with Sentiment Analysis avatar

Product Reviews with Sentiment Analysis

Pricing

from $1.34 / 1,000 review sentiments

Go to Apify Store
Product Reviews with Sentiment Analysis

Product Reviews with Sentiment Analysis

Collect product reviews, enrich each with sentiment, and generate a per-product sentiment report.

Pricing

from $1.34 / 1,000 review sentiments

Rating

0.0

(0)

Developer

E Commerce

E Commerce

Maintained by Apify

Actor stats

0

Bookmarked

3

Total users

0

Monthly active users

2 days ago

Last modified

Categories

Share

Collects product reviews, enriches every review with sentiment, and generates a full sentiment report per product.

What it does

  1. Collects reviews by calling the deployed e-commerce standby Actors directly (e-commerce--<marketplace>-standby.apify.actor, POST /reviews) for each product or review URL, following pagination until every review is collected. 35 marketplaces are supported (Amazon, Walmart, eBay, IKEA, Target, Best Buy, and more).
  2. Enriches each review with sentiment (positive / neutral / negative), a confidence score, and per-aspect sentiment, using OpenAI. One enriched row per review is written to the dataset.
  3. Generates a per-product report across all of that product's reviews: an aspect-based sentiment analysis with themes, pain points, representative quotes, and recommendations. Each report is stored in the key-value store and summarized in the run log.

Input

Provide at least one product URL or review listing URL on a supported marketplace. Options: sortReview, additionalReviewProperties, maxReviewsPerProduct, maxProducts (report-spend safety cap), generateReport, and reportFormat (markdown / html / pdf). The OpenAI models and sentiment is handled internally - the customer pays per review scored and per report.

Configuration (operator only, via env)

  • OPENAI_API_KEY - required. The Actor uses the operator's OpenAI account; the customer does not supply a key.
  • PLATFORM_ACCOUNT_TOKEN - required. Full Apify account token used to authenticate calls to the standby Actors (falls back to APIFY_TOKEN).
  • SENTIMENT_MODEL / REPORT_MODEL - optional overrides (default gpt-4o-mini / gpt-4o).

Output

  • Dataset: one enriched review per row (sentimentLabel, sentimentScore, aspects, plus the original review fields).
  • Key-value store: per product, report-<id>.json (machine-readable), report-<id>.md or .html (human-readable), and reports-index.json mapping every product URL to its report records.

Pricing (pay-per-event)

EventWhen it is charged
review-sentimentOnce per review scored and written to the dataset.
sentiment-reportOnce per product, after its report is stored.