<a id="flink-sql-sentiment"></a>

# Analyze Sentiment in Text with Confluent Cloud for Apache Flink

You can use Aspect-Based Sentiment Analysis (ABSA) to determine sentiment
toward specific aspects or topics within text. Instead of analyzing overall
sentiment, you can identify how users feel about particular features, attributes,
or elements mentioned in reviews, feedback, or social media posts.

For example, in the customer feedback “Battery life is amazing, but the screen
is too dim outdoors,” you can identify positive sentiment toward “battery” and
negative sentiment toward “screen,” capturing nuanced insights that overall
sentiment analysis would miss.

Confluent Cloud for Apache Flink® integrates sentiment analysis capabilities on your streams by using
this function:

- [AI_SENTIMENT](#flink-sql-sentiment-ai-sentiment) (Early Access Program):
  Analyze sentiment toward specific aspects in text using aspect-based sentiment
  analysis with transformer models like
  [DeBERTa](https://huggingface.co/yangheng/deberta-v3-base-absa-v1.1).

<a id="flink-sql-sentiment-ai-sentiment"></a>

## AI_SENTIMENT

You can use the AI_SENTIMENT function to analyze text and determine sentiment
toward specific aspects. The function uses a transformer model that is managed
by Confluent and hosted in Confluent Cloud to classify sentiment for each aspect you
specify as positive, negative, or neutral with a confidence score.

AI_SENTIMENT uses [DeBERTa](https://huggingface.co/yangheng/deberta-v3-base-absa-v1.1)
by default, a transformer model designed for aspect-based sentiment analysis.

During the Early Access Program, you can request additional sentiment analysis
models to be made available. To request additional models, contact your
Confluent representative.

#### IMPORTANT
The AI_SENTIMENT function is an Early Access Program feature
in Confluent Cloud.

<!-- Admonition for product maturity stage: EAP -->
<!-- Use this file for standard legalese in docs for new Early access Program features. -->
<!-- Suggested usage: -->
<!-- .. note: (add a second colon here) -->
<!-- Feature X is an Early Access Program feature in |product|. -->
<!-- .. include:: ../.hidden/docs-common/home/includes/product-maturity-stage-admonition-eap.rst -->
<!-- (optional) If you would like to participate in the Early Access Program, email address@confluent.io. -->
<!-- Reference: Product maturity stages and docs -->
<!-- https://confluentinc.atlassian.net/wiki/spaces/DOC/pages/2695004342/Product+maturity+stages+and+docs -->

An Early Access feature is a component of Confluent Cloud introduced to gain
feedback. This feature should be used only for evaluation and non-production
testing purposes or to provide feedback to Confluent, particularly as it
becomes more widely available in follow-on preview editions.

Early Access Program features are intended for evaluation use in development
and testing environments only, and not for production use. Early Access Program
features are provided: (a) without support; (b) “AS IS”; and (c) without
indemnification, warranty, or condition of any kind. No service level commitment
will apply to Early Access Program features. Early Access Program features are
considered to be a Proof of Concept as defined in the Confluent Cloud Terms of Service.
Confluent may discontinue providing preview releases of the Early Access
Program features at any time in Confluent’s sole discretion.

To participate in the Early Access Program, see the
[sign-up form](https://events.confluent.io/early-access-flink-features).

#### NOTE
AI_SENTIMENT uses models that are managed by Confluent and hosted in
Confluent Cloud. You cannot use your own managed models or remote models from cloud
providers with this function.

### Parameters

The AI_SENTIMENT function accepts the following parameters.

#### aspects

- **Type:** ARRAY<STRING>
- **Required:** Yes

The aspects to evaluate sentiment for. For example, if you specify the array
value `ARRAY['battery', 'screen']`, the function analyzes sentiment toward
battery and screen. The array must not be null or empty.

#### config

- **Type:** STRING
- **Required:** No

A JSON object with configuration parameters. The configuration must be constant
within a query.

#### text

- **Type:** STRING
- **Required:** Yes

The text to analyze for sentiment. The text must not be null or blank.

#### Configuration parameters

You can pass the following configuration parameters in the JSON object for the
`config` parameter.

##### batchSize

- **Type:** INTEGER
- **Default:** 32
- **Validation:** Must be > 0

The number of aspect-text pairs to process per batch.

##### model

- **Type:** STRING
- **Default:** `deberta`
- **Required:** No

The model to use for sentiment analysis.

### Output

The AI_SENTIMENT function returns a ROW data type with the following fields.

#### sentiment

- **Type:** ARRAY<ROW<aspect STRING, label STRING, score DOUBLE>>

An array of sentiment results, one per aspect. Each entry contains the following
fields:

- `aspect`: The aspect name
- `label`: The sentiment label. Possible string values are `'positive'`, `'negative'`, or `'neutral'`.
- `score`: Confidence score as a double value from 0.0 to 1.0

#### metadata

- **Type:** STRING

A JSON string containing model metadata.

### Examples

The following examples demonstrate how to use the AI_SENTIMENT function for
various sentiment analysis scenarios.

#### Analyzing product reviews

The following example analyzes sentiment for multiple aspects in product reviews.

```sql
CREATE TABLE reviews (
    review_id BIGINT,
    review_text STRING
);

INSERT INTO reviews VALUES
    (1, 'Battery life is amazing, but the screen is too dim outdoors'),
    (2, 'The performance is excellent and screen quality is superb'),
    (3, 'Battery drains too quickly, though the performance is decent');

SELECT
    review_id,
    review_text,
    AI_SENTIMENT(
        review_text,
        ARRAY['battery', 'screen', 'performance']
    ) AS sentiment_result
FROM reviews;
```

#### Extracting individual aspect sentiments

The following example shows how you can extract specific sentiment results for
individual aspects from the returned row.

```sql
SELECT
    review_id,
    review_text,
    sentiment_result.sentiment[0].aspect AS first_aspect,
    sentiment_result.sentiment[0].label AS first_label,
    sentiment_result.sentiment[0].score AS first_score,
    sentiment_result.metadata AS model_metadata
FROM (
    SELECT
        review_id,
        review_text,
        AI_SENTIMENT(
            review_text,
            ARRAY['battery', 'screen'],
            JSON_OBJECT('model' VALUE 'deberta')
        ) AS sentiment_result
    FROM reviews
);
```

#### Filtering for negative sentiment

The following example shows how you can filter reviews to find those with
negative sentiment toward specific aspects.

```sql
SELECT
    review_id,
    review_text,
    s.sentiment
FROM (
    SELECT
        review_id,
        review_text,
        AI_SENTIMENT(
            review_text,
            ARRAY['battery', 'screen']
        ) AS s
    FROM reviews
)
WHERE s.sentiment[0].label = 'negative'
   OR s.sentiment[1].label = 'negative';
```

#### Using custom batch size

The following example shows how you can process sentiment analysis with a
custom batch size for performance optimization.

```sql
SELECT
    review_id,
    review_text,
    AI_SENTIMENT(
        review_text,
        ARRAY['product', 'shipping', 'support'],
        JSON_OBJECT(
            'model' VALUE 'deberta',
            'batchSize' VALUE 64
        )
    ) AS sentiment_result
FROM reviews;
```

## Related content

- [AI Model Inference and Machine Learning Functions](../../flink/reference/functions/model-inference-functions.md#flink-sql-model-inference-functions)
- [Run a Remote AI Model](../ai-model-inference.md#flink-sql-ai-model)
- [CREATE MODEL statement](../../flink/reference/statements/create-model.md#flink-sql-create-model)

#### NOTE
This website includes content developed at the [Apache Software Foundation](https://www.apache.org/)
under the terms of the [Apache License v2](https://www.apache.org/licenses/LICENSE-2.0.html).