# Sentiment Analysis

Determine the sentiment expressed in a text

The Sentiment Analysis block is a stellar addition to GraphLinq IDE’s machine learning suite, facilitating the analysis of textual content to discern the underlying sentiment. Through the adept application of machine learning algorithms, it categorizes sentiments as positive, negative, or neutral, providing a deep insight into the emotional undertone of the text.

**Block Description**

Part of the machine learning category in the GraphLinq IDE, the Sentiment Analysis block operates as a keen analyzer of emotions expressed in text. By tapping into powerful machine learning algorithms, it gauges the sentiment prevailing in the text, a feature pivotal in understanding user feedback, reviews, or social media posts. This executable block is a central component in graphs focusing on data analytics and sentiment analysis.

**Input Parameters**

The Sentiment Analysis block demands the following input:

* **Text**: This input parameter is where you feed the text whose sentiment is to be analyzed. The text should be input as a string variable.

**Output**

After performing the sentiment analysis, the block outputs:

* **Sentiment**: This parameter bears the analyzed sentiment, categorizing it as ‘positive’, ‘negative’, or ‘neutral’.
* **Confidence Score**: This output highlights a score representing the confidence level of the sentiment analysis outcome, helping in ascertaining the analysis's reliability.

**Example Use Case**

To illustrate the utility of the Sentiment Analysis block, consider a scenario involving customer reviews analysis:

1. An e-commerce platform leverages GraphLinq IDE to analyze customer reviews for products.
2. Customer reviews are channeled through the Sentiment Analysis block to undergo a meticulous analysis of the underlying sentiments.
3. Inside the block, the "Text" parameter is populated with individual reviews, setting off the sentiment analysis.
4. Upon analysis, the "Sentiment" output parameter yields the sentiment category of each review, which is then employed to understand the customer sentiment landscape.
5. The "Confidence Score" output offers a measure of the reliability of the sentiment analysis, facilitating a nuanced understanding of customer feedback.

By utilizing the Sentiment Analysis block, developers can delve deep into the sentiments echoed in textual content, fostering a responsive and emotion-aware application environment. It thereby stands as a key tool in crafting applications that are finely tuned to the emotional nuances reflected in texts.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.graphlinq.io/dev-tooling/blocks-machine-learning/sentiment-analysis.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.