Glossary

Search results

SARI(also: System output Against References and against the Input sentence)

An automatic evaluation metric for text simplification systems that compares a system’s output against both the original input sentence and a set of human-written simplification references, rewarding the system for adding appropriate words, keeping important words, and deleting…

SHAP(also: SHapley Additive exPlanations)

A unified framework for feature-importance explanations of machine-learning models, introduced by Lundberg and Lee in 2017, grounded in Shapley values from cooperative game theory. For any model and input, SHAP assigns each feature a value representing its contribution to that…

SUMI(also: Software Usability Measurement Inventory)

A standardised questionnaire-based method for measuring software usability from the end user perspective. SUMI assesses five dimensions: efficiency, affect (user satisfaction), helpfulness, control, and learnability. In accessibility contexts, SUMI can be adapted alongside…

Scenario-Based Evaluation(also: Path-Based Testing, User Journey Testing)

An accessibility evaluation approach that assesses the complete user experience across a sequence of steps needed to accomplish a task, rather than testing individual pages in isolation. For example, evaluating an e-commerce checkout means testing every step from product search…

Score Prediction(also: Predicted grade, Comprehension self-prediction)

A subjective-response evaluation item in which a research participant, immediately after reading a passage and before learning their actual comprehension-question score, estimates the percentage of questions they will have answered correctly. Score prediction is used in…

Self-Assessment Manikin(also: SAM)

A nonverbal pictorial instrument developed by Bradley and Lang (1994) for measuring the affective dimensions of valence, arousal, and dominance. Respondents select from a row of stylised manikin figures whose expressions and body states vary along each dimension, typically on a…

Semi-Automatic Evaluation(also: Semi-Automated Testing, Guided Manual Evaluation)

An approach to accessibility evaluation that combines automated checks with human expert judgment. Semi-automatic tools run algorithmic tests to detect issues that can be identified programmatically — such as missing alt text or invalid ARIA attributes — and then guide the…

Semiotic Inspection Method(also: SIM, MIS)

An evaluation method from Semiotic Engineering theory that systematically assesses the communicability of an interactive system by examining how well the designer's intended message is conveyed through the interface. The evaluator analyzes three types of interface signs…

Sensitivity(also: Recall, Thoroughness, Completeness)

In the context of accessibility evaluation, sensitivity (also called recall or thoroughness) is the proportion of true accessibility problems that are successfully identified and reported by an evaluator. High sensitivity means that most real barriers are found, while low…

Signal Detection Theory(also: SDT)

A statistical framework used to measure the accuracy of a system or person in distinguishing between the presence and absence of a target signal amid noise. In accessibility and assistive technology research, Signal Detection Theory is used to evaluate how well detection systems…

Single Case Experimental Design(also: SCED, Single Subject Design, N-of-1 Design)

A research methodology in which individual participants serve as their own control, with repeated measurements taken during baseline and intervention phases to evaluate the effect of a treatment or intervention. This approach is particularly valuable in accessibility and…

Structured Walkthrough(also: Guided Walkthrough, Accessibility Walkthrough)

An accessibility evaluation method in which an evaluator is guided through a systematic series of checks using predefined steps, instructions, and heuristics. Unlike a full WCAG conformance review which requires expert knowledge to interpret success criteria, a structured…

12 results.