System and method for assessing reading skills

• US 10,692,393 B2
• Filed: 09/30/2016
• Issued: 06/23/2020
• Est. Priority Date: 09/30/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kochura, Nadiya, Lu, Fang
• Primary Examiner(s): Egloff, Peter R
• Application Number:
  US15/282,458
• Publication Number:
  US 20180096625A1
• Time in Patent Office: 1,362 Days
• CPC Class Codes: G09B 17/003 electrically operated apparatus or devices
• CPC Class Codes: G09B 5/02 with visual presentation of the material to be studied, e.g. using film strip
• CPC Class Codes: G09B 5/12 different stations being capable of presenting different information simultaneously G09B5/14 takes precedence

Abstract

Embodiments can provide a computer implemented method in a data processing system comprising a processor and a memory comprising instructions which are executed by the processor to cause the processor to implement a reading skill assessment system, the method comprising creating one or more sets of parameterized text mutators for one or more different reading skill levels; applying a reading skill score function to calculate baseline scores for one or more tested reading skill levels; adjusting the reading skill score function to best match with the one or more tested reading skill levels; optimizing the parameters of the one or more sets of text mutators; creating one or more baseline reading skill score levels for each of the one or more tested reading skill levels; and associating one or more sets of text mutators with the one or more tested reading skill levels.

Claims

1. A computer implemented method, in a data processing system comprising a processor and a memory comprising instructions which are executed by the processor to cause the processor to implement a reading skill assessment system, the method comprising:

creating one or more sets of parameterized text mutators for one or more different reading skill levels;

applying a reading skill score function to calculate baseline scores for one or more tested reading skill levels;

adjusting the reading skill score function to best match with the one or more tested reading skill levels;

optimizing the parameters of the one or more sets of text mutators by applying one or more machine learning classification algorithms to the parameters;

creating one or more baseline reading skill score levels for each of the one or more tested reading skill levels;

associating one or more sets of text mutators with the one or more tested reading skill levels;

processing a body of text;

applying one or more selected text mutators to the body of text to produce a mutated text output, wherein applying the one or more selected text mutators modifies the body of text such that the mutated text output includes one or more non-words or non-letter characters;

presenting the mutated text output to a reader;

prompting the reader to provide one or more answers to one or more questions regarding the mutated text output;

processing the one or more answers provided by the reader;

processing one or more reader metrics collected from the reader;

calculating a reader skill score for the reader based on the collected reader metrics; and

mapping the calculated reader skill score against the one or more baseline reading skill score levels;

wherein the reading skill assessment system is implemented on a cognitive system,

wherein the reader metrics include biometrics and one or more of mean reading duration per word, reading speed, total reading time, correctness of responses regarding text understanding, time needed to provide responses, word reading level with applied text mutators, or sentence reading level with applied text mutators, and

wherein the biometrics includes heart rate, hormonal status, stress levels, transpiration, and galvanic skin response.

2. The method as recited in claim 1, further comprising:

associating one or more sets of text mutators with one or more sets of reading skill tests, wherein the text mutators comprise at least one of;

pseudoword injections, letter transposition injections, randomized text, word rotation, mirroring, letter spacing, word extraction, and text stretching.

3. The method as recited in claim 1, further comprising:

storing the one or more baseline reading skill scores and one or more skill score associations in a reading skill knowledge repository.

4. The method as recited in claim 1, further comprising:

adjusting the reading skill score function to best match with the one or more tested reading skill levels by adjusting one or more weightings of the parameters of the one or more sets of text mutators by the reading skill score function.

5. A computer program product for reading skill assessment, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

create one or more sets of parameterized text mutators for one or more different reading skill levels;

apply a reading skill score function to calculate baseline scores for one or more tested reading skill levels;

adjust the reading skill score function to best match with the one or more tested reading skill levels;

optimize the parameters of the one or more sets of text mutators by applying one or more machine learning classification algorithms to the parameters;

create one or more baseline reading skill score levels for each of the one or more tested reading skill levels;

associate one or more sets of text mutators with the one or more tested reading skill levels;

process a body of text;

apply one or more select text mutators to the body of text to produce a mutated text output, wherein applying the one or more selected text mutators modifies the body of text such that the mutated text output includes one or more non-words or non-letter characters;

present the mutated text output to a reader;

prompt the reader to provide one or more answers to one or more questions regarding the mutated text output;

process the one or more answers provided by the reader;

process one or more reader metrics collected from the reader;

calculate a reader skill score for the reader based on the collected reader metrics; and

map the calculated reader skill score against the one or more baseline reading skill score levels,

wherein the reader metrics include biometrics and one or more of mean reading duration per word, reading speed, total reading time, correctness of responses regarding text understanding, time needed to provide responses, word reading level with applied text mutators, or sentence reading level with applied text mutators, and

wherein the biometrics includes heart rate, hormonal status, stress levels, transpiration, and galvanic skin response.

6. The computer program product as recited in claim 5, wherein the processor is further caused to:

associate one or more sets of text mutators with one or more sets of reading skill tests, wherein the text mutators comprise at least one of;

pseudoword injections, letter transposition injections, randomized text, word rotation, mirroring, letter spacing, word extraction, and text stretching.

7. The computer program product as recited in claim 5, wherein the processor is further caused to:

store the one or more baseline reading skill scores and one or more skill score associations in a reading skill knowledge repository.

8. The computer program product as recited in claim 5, wherein the processor is further caused to:

adjust the reading skill score function to best match with the one or more tested reading skill levels by adjusting one or more weightings of the parameters of the one or more sets of text mutators by the reading skill score function.

9. A reading skill assessment system, comprising:

a reading skill assessment processor configured to;

create one or more sets of parameterized text mutators for one or more different reading skill levels;

apply a reading skill score function to calculate baseline scores for one or more tested reading skill levels;

adjust the reading skill score function to best match with the one or more tested reading skill levels;

optimize the parameters of the one or more sets of text mutators by applying one or more machine learning classification algorithms to the parameters;

create one or more baseline reading skill score levels for each of the one or more tested reading skill levels;

associate one or more sets of text mutators with the one or more tested reading skill levels;

process a body of text;

apply one or more select text mutators to the body of text to produce a mutated text output, wherein applying the one or more selected text mutators modifies the body of text such that the mutated text output includes one or more non-words or non-letter characters;

present the mutated text output to a reader;

prompt the reader to provide one or more answers to one or more questions regarding the mutated text output;

process the one or more answers provided by the reader;

process one or more reader metrics collected from the reader;

calculate a reader skill score for the reader based on the collected reader metrics; and

map the calculated reader skill score against the one or more baseline reading skill score levels,

wherein the reader metrics include biometrics and one or more of mean reading duration per word, reading speed, total reading time, correctness of responses regarding text understanding, time needed to provide responses, word reading level with applied text mutators, or sentence reading level with applied text mutators, and

wherein the biometrics includes heart rate, hormonal status, stress levels, transpiration, and galvanic skin response.

10. The system as recited in claim 9, wherein the reading skill assessment processor is further configured to:

associate one or more sets of text mutators with one or more sets of reading skill tests, wherein the text mutators comprise at least one of;

pseudoword injections, letter transposition injections, randomized text, word rotation, mirroring, letter spacing, word extraction, and text stretching.

11. The system as recited in claim 9, wherein the reading skill assessment processor is further configured to:

adjust the reading skill score function to best match with the one or more tested reading skill levels by adjusting one or more weightings of the parameters of the one or more sets of text mutators by the reading skill score function.