Abstract: Systems and methods of the present invention may be used to determine metrics and health scores for content that may correspond to an educational course or textbook, which may be in a digital format. The metrics and health scores may be determined at various hierarchical content levels, and may be used to quantitatively assess how well the corresponding content is performing based on responses submitted to assessment item parts of the content by responders. The metrics may include difficulty and discrimination metrics, which may be determined using maximum likelihood estimation methods based on a modified two parameter item response model. A content analytics interface corresponding to a given content element may be generated and displayed via a user device, and may include content health scores of subcontent within that content element. The subcontent may be ordered according to content health score.

Abstract: Systems and methods of the present invention provide for estimating latent ability of responders to a digital assessment in the form of ability scores and estimating item parameters an assessment item of the digital assessment including difficulty scores and discrimination scores. Maximum likelihood estimation may be performed based on an item response theory model to estimate the item parameters. Supervisory, extraction, and worker modules of a workflow manager module may initiate general purpose graphics processing unit instances and cause these instances to perform the maximum likelihood estimation calculations. The item response theory model may be a two parameter model that is modified to account for changes in difficulty caused by the use of hints.

Abstract: Systems and methods of the present invention may be used to determine metrics and health scores for content that may correspond to an educational course or textbook, which may be in a digital format. The metrics and health scores may be determined at various hierarchical content levels, and may be used to quantitatively assess how well the corresponding content is performing based on responses submitted to assessment item parts of the content by responders. The metrics may include difficulty and discrimination metrics, which may be determined using maximum likelihood estimation methods based on a modified two parameter item response model. A content analytics interface corresponding to a given content element may be generated and displayed via a user device, and may include content health scores of subcontent within that content element. The subcontent may be ordered according to content health score.

Abstract: Systems and methods of the present invention may be used to determine metrics and health scores for content that may correspond to an educational course or textbook, which may be in a digital format. The metrics and health scores may be determined at the assessment-item-part-level, assessment-item-level, section-level, chapter-level, and title-level, and may be used to quantitatively assess how well the corresponding content is performing based on responses submitted to assessment item parts of the content by one or more responders. The assessment-item-part-level metrics may include difficulty and discrimination values, scores, weights, and reliability values, which may be determined in whole or in part using maximum likelihood estimation methods based on a modified two parameter item response model.

Abstract: Systems and methods of the present invention may be used to determine metrics and health scores for content that may correspond to an educational course or textbook, which may be in a digital format. The metrics and health scores may be determined at various hierarchical content levels, and may be used to quantitatively assess how well the corresponding content is performing based on responses submitted to assessment item parts of the content by responders. The metrics may include difficulty and discrimination metrics, which may be determined using maximum likelihood estimation methods based on a modified two parameter item response model. A content analytics interface corresponding to a given content element may be generated and displayed via a user device, and may include content health scores of subcontent within that content element. The subcontent may be ordered according to content health score.

Abstract: Systems and methods of the present invention may be used to determine metrics and health scores for content that may correspond to an educational course or textbook, which may be in a digital format. The metrics and health scores may be determined at various hierarchical content levels, and may be used to quantitatively assess how well the corresponding content is performing based on responses submitted to assessment item parts of the content by responders. The metrics may include difficulty and discrimination metrics, which may be determined using maximum likelihood estimation methods based on a modified two parameter item response model. A content analytics interface corresponding to a given content element may be generated and displayed via a user device, and may include content health scores of subcontent within that content element. The subcontent may be ordered according to content health score.

Abstract: Systems and methods of the present invention provide for estimating latent ability of responders to a digital assessment in the form of ability scores and estimating item parameters an assessment item of the digital assessment including difficulty scores and discrimination scores. Maximum likelihood estimation may be performed based on an item response theory model to estimate the item parameters. Supervisory, extraction, and worker modules of a workflow manager module may initiate general purpose graphics processing unit instances and cause these instances to perform the maximum likelihood estimation calculations. The item response theory model may be a two parameter model that is modified to account for changes in difficulty caused by the use of hints.

Abstract: Systems and methods of the present invention may be used to determine metrics and health scores for content that may correspond to an educational course or textbook, which may be in a digital format. The metrics and health scores may be determined at the assessment-item-part-level, assessment-item-level, section-level, chapter-level, and title-level, and may be used to quantitatively assess how well the corresponding content is performing based on responses submitted to assessment item parts of the content by one or more responders. The assessment-item-part-level metrics may include difficulty and discrimination values, scores, weights, and reliability values, which may be determined in whole or in part using maximum likelihood estimation methods based on a modified two parameter item response model.