> ## Documentation Index
> Fetch the complete documentation index at: https://docs.supercontrast.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Sentiment Analysis

> Score text on a scale of positive, negative, or neutral

Sentiment Analysis is the process of determining the emotional tone behind a series of words, used to gain an understanding of the attitudes, opinions and emotions expressed within an online mention.

Running Sentiment Analysis with `supercontrast` is easy, all you have to do is provide the text and the provider you want to use.
In this example, we'll specify that for `Task.SENTIMENT_ANALYSIS`, we want to use `Provider.AWS`, which uses Amazon's Comprehend API.

```python theme={null}
from supercontrast import SuperContrastClient, Task, Provider, SentimentAnalysisRequest

client = SuperContrastClient(task=Task.SENTIMENT_ANALYSIS, providers=[Provider.AWS])
request = SentimentAnalysisRequest(text="I love programming in Python!")
response, metadata = client.request(request)
```

Each task has its own request and response schema. For `Task.SENTIMENT_ANALYSIS`, the request schema is defined by `SentimentAnalysisRequest` and the response schema is defined by `SentimentAnalysisResponse`.

[SentimentAnalysisRequest](https://github.com/supercontrast-ai/supercontrast/blob/main/src/supercontrast/task/types/sentiment_analysis_types.py#L6)

* `text`: a string of the text to analyze for sentiment.

[SentimentAnalysisResponse](https://github.com/supercontrast-ai/supercontrast/blob/main/src/supercontrast/task/types/sentiment_analysis_types.py#L13)

* `score`: a float between 0 and 1, representing the sentiment of the text.