Emotional Response Predictor Using Eye Tracking and Voting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Collecting training data for affective computing models that accurately translate affective responses into emotional responses is challenging due to the difficulty in obtaining spontaneous, genuine emotional expressions in day-to-day scenarios, which requires manual curation and can be impractical on a large scale.

Innovation Solution

An automated system that utilizes users' explicit actions on content, such as voting mechanisms on social networks, to generate samples of affective responses paired with emotional labels, using eye tracking data to ensure the user's attention and genuine emotional response, thereby creating a more accurate training dataset for emotional response prediction models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual curation is used to collect spontaneous emotional expressions in day-to-day scenarios, then the authenticity and genuineness of emotional data is improved, but the productivity and scalability of data collection deteriorates

Engineering Contradiction:

Improveauthenticity of emotional dataVSAvoiddata collection efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system automatically collects and labels emotional data without requiring manual curation. Sensors detect affective responses and the system autonomously pairs them with content context and explicit user actions, eliminating the need for manual data annotation while maintaining authenticity through automated detection of genuine emotional expressions in natural settings

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent introduces an automated affective computing system as an intermediary between users and researchers. This system uses sensors, machine learning models, and content analysis to automatically capture and label emotional responses, bridging the gap between spontaneous user behavior and structured training data without requiring direct manual intervention

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If automated methods are used to collect affective response data, then the productivity and scalability of data collection is improved, but the measurement precision of genuine emotional responses deteriorates

Engineering Contradiction:

Improvedata collection efficiencyVSAvoidaccuracy of emotional labeling

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system uses explicit user actions (likes, shares, comments) as feedback signals to validate and refine automated emotional labels. By comparing sensor-detected affective responses with these explicit user behaviors, the system continuously improves the precision of its emotional measurements while maintaining automated collection at scale

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent combines multiple data sources including sensor measurements of affective responses, eye tracking data for attention verification, content context analysis, and explicit user actions. This multi-modal fusion approach enhances measurement precision by cross-validating signals from different sources while maintaining automated collection efficiency

Inventive Principle:

Principle #5Merging (Combining)

3Measurement precision

If large amounts of training data are collected to improve model accuracy, then the prediction accuracy of emotional response models is improved, but the complexity and resources required for data management increases

Engineering Contradiction:

Improvemodel prediction accuracyVSAvoiddata management complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary filtering and organization of training data during collection by automatically pairing affective responses with content context, time stamps, and user action labels. This pre-structuring of data reduces future management complexity while enabling the accumulation of large-scale training datasets for improved model accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The automated data collection system serves multiple functions simultaneously: it collects affective response data, validates attention through eye tracking, contextualizes data with content information, and labels data with explicit user actions. This multi-functional approach consolidates what would otherwise require separate systems into a unified platform, reducing overall complexity while enabling comprehensive data collection

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9477993B2Training a predictor of emotional response based on explicit voting on content and eye tracking to verify attention

Publication Date: 2016.10.25 ALDERIAN TECHNOLOGIES LLC

AI summary

Utilizing eye tracking to collect naturally expressed affective responses for training an emotional response predictor, comprising: receiving a vote of a user on a segment of content consumed by the user; receiving eye tracking data of the user taken while the user consumed the segment of content; determining, based on the eye tracking data, that a gaze-based attention level to the segment reaches a predetermined threshold; utilizing the vote to generate a label related to an emotional response to the segment; receiving an affective response measurement of the user taken substantially while the user consumed the segment of content; and training a measurement emotional response predictor with the label and the affective response measurement.