Ioannis Hatzilygeroudis (Editor)

Screen reader programs (such as JAWS for Windows) provide output in a linear, either audio or Braille, format. Due to this linearity, it is much easier for blind users to get disoriented in a complex hypertext environment. iCare-Assistant attempts to address content accessibility challenges for students without sight in accessing educational materials (as lecture notes, syllabi, assignments, project descriptions, and announcements) from existing course servers. In particular, in this paper we focus on the challenges associated with accessing discussion boards, used by teachers, assistants, and students, to exchange information. Threads of messages in discussion boards evolve with new postings, thus just by investigating the subject headings or contents of earlier postings in a message thread, a blind student may not be able to guess the contents of the postings deeper in the hierarchy. We see that, in order to overcome the navigation obstacle for users, especially those who are blind, it is essential to develop techniques that help identify how the content of a discussion board grows. In particular, we identify and implement two complementary enabling techniques to help students navigate effectively. The first technique is segmentation through generalizations and specializations of messages. This process provides knowledge that can be used in understanding the high-level flow of the discussion threads. Then, a rule-based context-sensitive message classification and annotation process enables enrichment of the discussion structures with coherent annotations to guide users through discussion segments relevant to their navigational goals.