Skip to content

ai-analyze-sentiment-transact-sql.md

Latest commit

 

History

History
87 lines (65 loc) · 2.53 KB

ai-analyze-sentiment-transact-sql.md

File metadata and controls

87 lines (65 loc) · 2.53 KB
Raw
title AI_ANALYZE_SENTIMENT (Transact-SQL)
description The AI_ANALYZE_SENTIMENT function detects sentiment in input text.
author WilliamDAssafMSFT
ms.author wiassaf
ms.reviewer jovanpop
ms.date 06/10/2026
ms.service sql
ms.subservice t-sql
ms.topic reference
ms.custom
sql-ai
f1_keywords
ai_analyze_sentiment_TSQL
ai_analyze_sentiment
helpviewer_keywords
ai_analyze_sentiment
dev_langs
TSQL
monikerRange =fabric

AI_ANALYZE_SENTIMENT (Transact-SQL)

[!INCLUDE fabricsedw]

The AI_ANALYZE_SENTIMENT function analyzes input text and returns one of these sentiment labels: positive, negative, mixed, or neutral.

Note

  • AI_ANALYZE_SENTIMENT is in preview.
  • AI_ANALYZE_SENTIMENT is available only in [!INCLUDE fabric-se-short] and [!INCLUDE fabric-dw].

Syntax

:::image type="icon" source="../../includes/media/topic-link-icon.svg" border="false"::: Transact-SQL syntax conventions

AI_ANALYZE_SENTIMENT ( text )

Arguments

text

An expression of a character type, for example nvarchar, varchar, nchar, or char.

Return types

Returns nvarchar with one of the following values:

  • positive
  • negative
  • mixed
  • neutral

Remarks

AI functions return NULL if the AI model can't process the text. Common reasons include:

  • Responsible AI rules block inappropriate content in the input text.
  • Input text exceeds token limits. The current model supports up to 15 KB of text.

Examples

A. Analyze sentiment in a string

SELECT ai_analyze_sentiment('This hotel was great!') AS sentiment;

Expected result: positive

B. Analyze sentiment from a table column

SELECT review_id,
       ai_analyze_sentiment(review_text) AS sentiment
FROM dbo.hotel_reviews;

Related content