Emotional Event Detection in Text Using Statistical Deviation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing approaches to sentiment and emotion detection in text are inadequate as they fail to capture the full range of emotions and often classify text as expressing only positive, neutral, or negative sentiment, without providing a granular emotional analysis.
Innovation Solution
A computer-implemented method that segments text into sentences, identifies entities using pre-defined domain entities, classifies entities with sentiment, determines the strongest sentiment for each entity, derives emotions, and calculates mean and standard deviation to map entities to strongest emotions, thereby providing a comprehensive emotional analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing sentiment detection approaches are used, then text can be classified as positive, neutral, or negative, but the full range of emotions cannot be captured and granular emotional analysis is not provided
Solution Approach 1:
The patent segments the emotional analysis process into distinct components: sentence segmentation, entity identification, sentiment classification, emotion derivation, and statistical analysis. This segmentation allows the system to handle complex emotional analysis through manageable stages, improving measurement precision while controlling system complexity through modular design
Solution Approach 2:
The patent transitions from traditional single-dimension sentiment classification (positive/neutral/negative) to multi-dimensional emotional analysis by deriving multiple emotions (joy, sadness, anger, fear, disgust) with polarity and strength scores. This dimensional expansion captures the full range of emotions while using systematic methods to manage the increased complexity
2Loss of information
If traditional sentiment classification is used, then text can be categorized broadly, but key emotional content and extraordinary moments cannot be identified
Solution Approach 1:
The patent extracts key emotional content by identifying the strongest sentiment and corresponding emotion for each entity in each sentence, rather than analyzing the entire text uniformly. This extraction approach preserves important emotional information while improving processing efficiency by focusing computational resources on significant emotional moments
Solution Approach 2:
The patent uses statistical feedback mechanisms by calculating mean and standard deviation of emotion strengths across the text, then using these statistics to identify extraordinary moments that deviate from the norm. This feedback loop enables the system to adaptively identify key emotional content while maintaining processing efficiency through statistical thresholds
Data Source
AI summary
Computer implemented methods, systems, and computer program products include program code executing on a processor(s) that obtains text from a computing resources in a domain and segments it into sentences. The processor(s) identifies entities in each sentence. The processor(s) classifies each entity with a sentiment (a polarity). The processor(s) identifies, for each sentence, a given entity with a strongest sentiment. The processor(s) derives for each sentence, for each entity, emotions and classifies each emotion by assigning a polarity to each and scoring each. The processor(s) calculates, based on the (emotion) scores, a mean and a standard deviation from the mean. The processor(s) maps the given entity for each sentence to a strongest emotion for the given entity where the polarity of the strongest emotion is the same as the polarity of the strongest sentiment. The processor(s) determines if each strongest emotion is within the standard deviation from the mean.