An interface agent for non-visual, accessible web automation

Abstract

The Web is far less usable and accessible for the users with visual impairments than it is for the sighted people. Web automation has the potential to bridge the divide between the ways visually impaired people and sighted people access the Web, and enable visually impaired users to breeze through Web browsing tasks that beforehand were slow, hard, or even impossible to achieve. Typical automation interfaces require that the user record a macro, a useful sequence of browsing steps, so that these steps can be re-played in the future. In this paper, I present a high-level overview of an approach that enables users to find quickly relevant information on the webpage, and automate browsing without recording macros. This approach is potentially useful both for visually impaired, and sighted users.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.