Information overload in non-visual web transaction

Abstract

Visually disabled individuals use screen readers to browse the Web. Sequential processing of screen readers makes Web browsing time-consuming and strenuous. The problem is further exacerbated when conducting Web transactions (e.g. buying books, paying utility bills, etc.), which typically involve a number of steps spanning several pages. Thus browsing becomes fatigue inducing and causes significant information overload. But usually one needs only small segments of Web pages for completing a Web transaction. Identifying and presenting such segments from Web pages can reduce information overload. An interesting idea is to use context surrounding a link to identify relevant information on the next Web page. I describe how context analysis coupled with Web content analysis can identify relevant content segments. Preliminary results based on my system incorporating this idea, show a lot of promise in combating the information overload problem encountered by visually disabled individuals when they do transactions over the Web.

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 — 4 citations exist upstream.

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