Abstract
Studies of interaction log analysis are a common tool to investigate behavioural data and contribute to insights into users’ interaction patterns with a system [11,18]. We present a log analysis from a be-spoke conversational system,RealSAM1, an audio-only interaction media assistant in which users can navigate and interact with media content through natural language. The novel assistant is designed for people with a vision impairment or other disability that prevents a person from accessing printed material. The exploratory analysis was conducted to provide an initial insight into the communication and interaction behaviours. We focus on understanding how users utilise the application. The results are twofold, we highlight the (i)implications for the design of future voice-enabled systems such as “infinite-reading” mode, enhanced interaction management enabling file navigation or time-compression techniques, and (ii)challenges of analysing conversational logs and suggest guidelines making these logs more accessible for future research.