Keystroke Burst Boundary Clustering for Writing Fluency Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing burst measures for assessing writing fluency are influenced by both translation and transcription processes, often correlating with typing speed, and lack individualization, leading to unreliable scoring and feedback.
Innovation Solution
The method involves gathering keystroke log data to determine an optimal burst boundary threshold through clustering analyses, allowing for the separation of translation and transcription processes, and providing individualized burst-related measures and statistics to assess writing proficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing burst measures are used to assess writing fluency, then writing fluency can be assessed, but the measures are influenced by both translation and transcription processes and correlate with typing speed, leading to unreliable scoring
Solution Approach 1:
The patent segments the writing process into distinct bursts separated by pause intervals. By identifying burst boundaries through clustering analysis of inter-key intervals, the system separates continuous writing into discrete productive bursts, allowing independent measurement of fluency characteristics without confounding transcription speed effects.
Solution Approach 2:
The patent applies individualized burst boundary thresholds to each writer based on their personal typing characteristics. Instead of using a universal threshold, the system determines optimal burst boundaries specific to each writer's keyboarding patterns, thereby accounting for individual differences in transcription speed while maintaining reliable fluency measurement.
2Productivity
If fixed burst boundary thresholds are used, then burst measures can be calculated, but the measures lack individualization and do not account for personal typing characteristics
Solution Approach 1:
The patent performs preliminary clustering analysis on a writer's inter-key interval data before assessing their writing fluency. This preliminary action establishes personalized burst boundary thresholds that reflect the writer's unique typing patterns, enabling subsequent fluency measurements to be both efficient and individually adapted.
Solution Approach 2:
The patent transforms fixed, static burst boundary thresholds into dynamic, adaptive thresholds that adjust to each writer's characteristics. The system determines optimal burst boundaries based on individual typing patterns, making the measurement system flexible and responsive to personal differences in keyboarding behavior.
Data Source
AI summary
Systems and methods for defining and using an optimal burst boundary threshold to assess the reliability of a manual/automatic writing score are presented. Keystroke data, including inter-key interval data, such as inter-word interval data, may be gathered from writings. Clustering analyses may be performed on the inter-key interval data to determine an optimal number of bursts for the writings. An optimal burst boundary may be determined from the optimal number of bursts. Other burst-related measures and statistics, including the average and maximum burst lengths, may be determined from the writings based on the optimal burst boundary threshold. A score may be received for each of the writings. A validation indication metric may be generated for each of the writings based on the received score and the optimal burst boundary threshold. The resulting measures and statistics may be used or applied in different ways and provide personalized feedback as learning analytics.