# Using EmotionsAI

**EmotionsAI classifies visitors into 10 needs depending on the way they interact with a website**. Based on their predictive patterns, the algorithm classifies visitors as it detects their **Intuitive Needs** (attention, comfort, community, competition, and safety) and **Rational Needs** (change, immediacy, notoriety, quality, and understanding).

Our algorithm has been developed by experts: a Doctor (PhD) specialized in Purchase Behavior Modeling, who conducted his PhD guided by a Nobel Prize winner. 

EmotionsAI is the result of 8 years of R\&D and in-depth research on millions of users' journeys, thousands of online surveys and hundreds of A/B tests analyzed. Which makes it unique on the market.

## The AI in EmotionsAI <a href="#h_01j8pxxrydjbxk4mw5m3dmvyep" id="h_01j8pxxrydjbxk4mw5m3dmvyep"></a>

EmotionsAI provides an audience segmentation that was built by training an algorithm to identify the links between user behaviors and the type of online experience they prefer. The AI has identified 10 groups of visitors with very different UX preferences and can predict these preferences based on observed visitor behaviors.&#x20;

As a result, website online experiences can be tailored to visitor preferences, enabling the websites to demonstrate emotional intelligence.

## Visitor categorization <a href="#h_01j8pxyr5cephjf0ah3z2ysm4m" id="h_01j8pxyr5cephjf0ah3z2ysm4m"></a>

It takes only 30 seconds for EmotionsAI to categorize a visitor into one of the 10 available segments!&#x20;

We calculated 30 seconds as the optimal amount of time between qualifying and business. The average time spent on a page is 52 sec (source Contentsquare), within 30 seconds we are able to qualify users on the first page they visit and to enable a tailored experience as soon as the second viewed page. If EmotionsAI took a longer time to predict, we would increase the accuracy but may react too late to keep the visitor engaged.&#x20;


---

# 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.abtasty.com/emotions-ai/using-emotionsai.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.