Product reviews in five languages

What this example returns

The dataset’s “Sentiment” view shows 17 columns: Text, Sentiment, Score (-1 to 1), Positive, Neutral, Negative, Confidence, Emotion, Topics, Keywords, Categories, Aspect sentiment, Summary, Language, Source, Row, and Error. See every output field.

What each setting does

The input this example runs Text Analytics: Sentiment, Topics & Keywords with. “Try this input” opens it in the console, where you can run it as-is or change any field first.

Texts texts

Fantastic headphones, the sound is crystal clear and they arrived a day early!, Worst purchase ever. It stopped working after three days and the refund took a month., Do you ship to Canada?, Die Lieferung war schnell und die Verarbeitung ist hervorragend., El producto llegó roto y el servicio al cl…

Texts to analyse, one per line: reviews, comments, posts, survey answers, support tickets, headlines. Any language. Leave empty when you analyse a dataset or files below.

Your categories (aspect sentiment) categories

price, quality, delivery, customer service

Optional. Your own categories, for example price, quality, delivery, customer service. Each text is tagged with the categories it talks about, plus the sentiment about each one (a review can love the quality and hate the delivery). Up to 40.

One-sentence summary summary

Yes

A short summary of each text. Useful for long reviews, tickets and articles; adds a little AI model usage per text.

Default: No → this example uses Yes

Language for topics and summaries outputLanguage

English

Topics and summaries are written in this language, whatever the language of the text, so results from many languages can be compared. Keywords stay as written in the text.

{
  "texts": [
    "Fantastic headphones, the sound is crystal clear and they arrived a day early!",
    "Worst purchase ever. It stopped working after three days and the refund took a month.",
    "Do you ship to Canada?",
    "Die Lieferung war schnell und die Verarbeitung ist hervorragend.",
    "El producto llegó roto y el servicio al cliente nunca respondió.",
    "Le prix est correct, la qualité est moyenne.",
    "とても使いやすくて、毎日使っています。",
    "Shipping took three weeks, but the jacket itself is beautiful and warm.",
    "🔥🔥🔥",
    "Oh great, the app crashed again right before checkout. Just what I needed."
  ],
  "categories": [
    "price",
    "quality",
    "delivery",
    "customer service"
  ],
  "summary": true,
  "outputLanguage": "English"
}

What it costs

You pay for the events the actor reports, such as each result or page it produces, plus the platform usage of your runs: compute, proxies and storage. Platform usage is typically about $0.02 per 1,000 results.

• Analysed textfrom $0.00174One text analysed and saved: sentiment with scores, language, and the emotion, topics, keywords, categories and summary you chose. Empty texts and texts that could not be analysed are free.

Full pricing

When to use this example

From the Text Analytics: Sentiment, Topics & Keywords readme:

Other ways to run Text Analytics: Sentiment, Topics & Keywords

• A web page and a CSV columnAnalyse the text of a web page as one document and the product titles of a CSV file (the text column is found automatically), with topics written in Spanish.

All examples of Text Analytics: Sentiment, Topics & Keywords

About Text Analytics: Sentiment, Topics & Keywords

Score the sentiment of reviews, comments, posts or any text column, and get emotion, topics, keywords, your own categories with aspect sentiment, and a run summary. Texts, datasets of other runs, CSV/JSON files or web pages, in any language.

Price:

from $1.74 / 1,000 results

Developer:

Querystone

Categories:

AI, Developer tools, Social media

Text Analytics: Sentiment, Topics & Keywords pageOutput fieldsPricing