Narrative Point of View Classification via Feature Vector Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack the ability to automatically identify and classify the point of view and diegesis in narrative text, which are crucial for understanding the interpretation and reception of news and narratives, as they involve complex stylistic characteristics such as narrator involvement and perspective.
Innovation Solution
A machine learning-based approach using natural language processing pipelines to classify text by extracting features such as pronoun usage and semantic role labeling, with a support vector machine model to predict point of view and diegesis, enabling computers to understand narrators' relationships to the story and interpret stories effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning techniques are used to automatically classify point of view and diegesis, then classification accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the text analysis task into distinct feature extraction components (pronoun usage, semantic role labeling, narrator identification) that can be processed independently and then combined for final classification. This modular approach improves accuracy through comprehensive feature analysis while managing computational complexity through organized processing stages.
Solution Approach 2:
The patent performs preliminary text processing and feature extraction before the main classification task. By pre-identifying pronouns, semantic roles, and potential narrators, the system prepares structured data that accelerates the subsequent machine learning classification process, reducing the computational burden during inference.
2Measurement precision
If comprehensive feature extraction is performed to improve classification accuracy, then processing time increases
Solution Approach 1:
The patent applies different levels of feature extraction to different parts of the text based on local characteristics. For example, it focuses intensive feature extraction on sentences containing pronouns or potential narrator references, while applying lighter processing to other portions, thereby balancing accuracy with processing efficiency.
Solution Approach 2:
The patent implements a two-stage approach where a quick preliminary classification is performed first, and only texts requiring higher accuracy undergo comprehensive feature extraction. This partial application of full processing to only necessary cases reduces overall processing time while maintaining high accuracy for critical classifications.
Data Source
AI summary
Methods for classifying a point of view and diegesis are provided. A method can include providing a processor in operable communication with a computer-readable medium, receiving a narrative text, extracting a set of features from the narrative text, transmitting the features into a feature vector, transmitting a plurality of feature vectors to a support vector machine, predicting a point of view and diegesis for the narrative text associate with a particular feature vector, and annotating the narrative text.