Web Screen Reading Automation Assistance Using Semantic Abstraction

Abstract

A screen reader's sequential press-and-listen interface makes for an unsatisfactory and often times painful web-browsing experience for blind people. To help alleviate this situation, we introduce Web Screen Reading Automation Assistant (SRAA) for automating users' screen-reading actions (e.g., finding price of an item) on demand, thereby letting them focus on what they want to do rather than on how to get it done. The key idea is to elevate the interaction from operating on (syntactic) HTML elements, as is done now, to operating on web entities (which are semantically meaningful collections of related HTML elements, e.g., search results, menus, widgets, etc.). SRAA realizes this idea of semantic abstraction by constructing a Web Entity Model (WEM), which is a collection of web entities of the underlying webpage, using an extensive generic library of custom-designed descriptions of commonly occurring web entities across websites. The WEM brings blind users closer to how sighted people perceive and operate on web entities, and together with a natural-language user interface, SRAA relieves users from having to press numerous shortcuts to operate on low-level HTML elements - the principal source of tedium and frustration. This paper describes the design and implementation of SRAA. Evaluation with 18 blind subjects demonstrates its usability and effectiveness.