Motivation tracking

Learn about motivation tracking.

Motivation tracking helps to determine user motivation.

It ensures human-centricity of experiences within the scope of the project by preserving and favoring user motivations over the project's.

• In cases of imposed motivation, motivation tracking assesses historical data of users in similar situations and state variables.

• In cases of free motivation, motivation tracking analyzes user responses and factors such as:

  • The time of the day

  • The user's speaking style

  • State variables to discern each user's intrinsic motivation

Advantage

Motivation tracking allows you to design and build human-centric solutions with nuanced insights into user motivation. It enables you to create deeply personalized experiences by accurately assessing and responding to user needs and states.

Most AI-based software solutions available in the market today do not understand what drives user actions. They focus more on grasping behavioral data and clustering people based on common factors instead of each individual user's uniqueness. This lack of individualization prevents them from generating affective interactions.

Moreover, these AI systems are largely trained on big data to predict patterns. They often imbibe the biases inherent in these data sets and provide biased responses. Therefore, they find it difficult to activate hyper-personalization in real-time.

On the other hand, EDAA™ (the underlying technology that powers Affective Computing by Virtue) can align itself with its users' motivations in real-time and preserve them over the project's motivation. By doing this, it can personalize actions according to the users' current states of mind and creates the desired impact.

How it works

The project's motivation is configured in the database and linked to the project's functions. Each project function has either imposed (preset) or free (user-determined) motivation.

To learn more about the two types of motivation, see How EDAA™ determines user motivation.

Imposed motivation, which ensures that user motivations are aligned with a predefined purpose, is achieved as a result of model training.

The model training, which occurs when Affective Computing by Virtue operates in product calibration mode, is driven by the data you provide, and requires approximately 150 interactions.

This data can includes the inputs of perception (such as physiological, user motion, and environmental data) and two psychological profiles for reference.

The engine model is also re-trained occasionally during regular action mode.

In cases of Free motivation, in which EDAA™ understands the user’s motivation and predicts the best action that can be delivered, the system learns continuously during each session until the visible states reach their optimal values.

Unlike the imposed motivation model, the free motivation model learns from scratch for each user and in every session.

In cases of free motivation, based on users' depth profiles, EDAA™ identifies when users are not efficient and considers those situations as anomalies.

How EDAA™ determines user motivation

EDAA™ distinguishes between two types of motivation: Imposed and Free.

By doing this, it enables your solution to tailor its responses to user needs.

Type of motivation	Description
Imposed motivation	In scenarios of imposed motivation, the solution already has a specific purpose or objective defined. All users must achieve the preset objectives (that you defined) by performing ideal actions and gaining the psychological skills required to perform the assignment. The solution aligns user actions to achieve the predetermined goals and ensures that they remain in the optimal state for success. This approach is beneficial in contexts such as reducing human errors in critical tasks or customizing training for high-performance athletes.
Free motivation	In scenarios of free motivation, users can have any motivation; user goals are not predefined or are unknown. EDAA™ identifies and understands the intrinsic motivations of users to predict and deliver the most suitable content or interactions. Unlike in cases of imposed motivation, where the situations are analyzed to identify anomalies, for free motivation, an anomaly is identified when a user is less efficient, based on their depth profile. This model is adept in personalizing experiences like music playlists, emotional workout routines, or real-time psychological assessments.

How EDAA™'s metacognition engines process motivation

Both free and imposed motivations are processed by EDAA™'s metacognition engines (Motivation, Sensation, and Strategy), which evaluate user motivation as a dynamic vector, adapting the solution's responses to suit either imposed or free motivation scenarios.

The metacognition engines also detect anomalies.

An anomaly is identified as a situation when a user deviates from their expected motivation and is indicated by signs such as an unusually high word frequency or elevated heart rate.

The solution targets minimalizing these anomalies and achieving a state of lower deviation. It aims to reduce anomalies by suggesting personalized actions tailored to the user's current state.

Favorable states, in which anomalies are minimal, are the desired outcome as they indicate that the user is closely aligned with their expected motivational profile.

For detailed information about anomaly detections, see Anomaly detection.