Automated Lexical Concreteness Scoring for Narrative Text
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods lack an efficient and automated way to characterize lexical concreteness in narrative text, which is crucial for assessing the quality of written stories, particularly in educational settings, as they rely on manual scoring and do not effectively differentiate between various story types.
Innovation Solution
A computer-implemented technique that removes function words from narrative text, assigns concreteness scores to content words using a database, and aggregates scores to provide a quantitative measure of lexical concreteness, allowing for automated scoring and analysis by parts-of-speech, thereby enabling the characterization of narrative text quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual scoring methods are used to assess narrative text quality, then scoring accuracy can be maintained through human judgment, but productivity is reduced and resource consumption increases
Solution Approach 1:
The patent replaces the manual mechanical scoring process with an automated computational system that uses natural language processing algorithms to analyze narrative text and generate quality assessments, thereby eliminating the need for human scorers while maintaining consistent evaluation criteria
Solution Approach 2:
The system enables narrative text to be automatically evaluated through self-service processing, where the computational model independently analyzes the text features and generates scoring without requiring external human intervention, thus improving productivity while maintaining measurement precision
2Adaptability or versatility
If general narrative text analysis is performed, then broad applicability is achieved, but the ability to differentiate between various story types is reduced
Solution Approach 1:
The patent applies different analysis parameters and weighting schemes to different story types (e.g., fictional vs. non-fictional narratives), allowing the system to maintain broad applicability across multiple genres while achieving precise differentiation through localized evaluation criteria for each story type
Solution Approach 2:
The system dynamically adjusts analysis parameters based on the detected story type, changing the weights and thresholds of various text features to optimize both general applicability and specific differentiation capability across different narrative genres
3Loss of information
If all words in narrative text are analyzed, then comprehensive coverage is achieved, but computational complexity and resource usage increase
Solution Approach 1:
The patent extracts and analyzes only the most informative words and phrases from narrative text (such as content words, adjectives, and adverbs that contribute to narrative quality), removing function words and stop words that add computational complexity without providing meaningful information for quality assessment
Solution Approach 2:
The system segments the narrative text into meaningful units (words, phrases, sentences) and applies targeted analysis to each segment, processing only the relevant linguistic features that contribute to quality assessment while ignoring redundant elements, thus reducing computational complexity while maintaining comprehensive coverage
Data Source
AI summary
A computer-implemented technique for characterizing lexical concreteness in narrative includes receiving data encapsulating narrative text having a plurality of words. Thereafter, the function words can be removed from the narrative text to result in only content words. A concreteness score can then be assigned to each content word by polling a database to identify matching words and to use concreteness scores associated with such matching words as specified by the database. Data can then be provided which characterizes the assigned concreteness scores. Related apparatus, systems, techniques and articles are also described.