When headers are not there
Authors:
Open Access
- 25 April 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Abstract
Using headers to grasp a document's structure has been one of the main strategies employed by blind users on web documents when using screen readers. However, when headers are not available or not appropriately marked up, they can cause serious difficulties. This paper presents the design and evaluation of a tool for automatically generating headers for screen readers with topicalisation and labelling algorithms. The proposed tool uses Natural Language Processing techniques to divide a web document into topic segments and label each segment based on its content. We conducted an initial user study with eight blind and partially-sighted screen reader users. The evaluation involved tasks with questions answered by participants with information from texts with and without automatically generated headers. Results provided preliminary indicators of improvement in performance and reduction of cognitive load. The findings contribute to knowledge to improve tools to aid in text exploration. It also provides initial empirical evidence to be further explored to analyze the impact of automatically-generated headings in improving performance and reducing cognitive load for blind users.Keywords
Funding Information
- Fundação de Amparo à Pesquisa do Estado de Minas Gerais
- Financiadora de Estudos e Projetos
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação de Amparo à Pesquisa do Estado de São Paulo (2020/05187-5)
This publication has 24 references indexed in Scilit:
- Spoken Conversational Search2016
- So Much to Read, So Little TimePsychological Science in the Public Interest, 2016
- From screen reading to aural glancing2014
- Non-visual skimming on touch-screen devices2013
- Timing and Frequency of Mental Effort Measurement: Evidence in Favour of Repeated MeasuresApplied Cognitive Psychology, 2012
- Back navigation shortcuts for screen reader users2012
- Accessible skimming2012
- Text segmentation: A topic modeling perspectiveInformation Processing & Management, 2011
- Measuring Cognitive Load2011
- Multi-window displays for readers of lengthy textsInternational Journal of Man-Machine Studies, 1987