Examining users' partial query modification patterns in voice search

Abstract

This article investigates how to improve the effectiveness of voice search systems. Earlier research found that participants employed voice search much less frequently than keyboard search. The main reasons that participants disliked voice search are system mistakes and the inability to modify queries. In keyboard search, query reformulation is facilitated by partial query modification, which is not supported by most of the current voice search systems. Consequently, users need to speak the complete query in voice search even with only minor changes. This article focuses on examining partial query modification during voice search through a Wizard of Oz user experiment. It examines if users would prefer partial query modification and how they perform it in voice search. Thirty-two participants participated in the experiment. Results indicated that when given the opportunity, the users performed more partial query modifications than complete queries. Common partial query modification strategies and patterns emerged from the experiment. The results can be used to improve the voice search system design and benefit the research community in general. System implications and future work were discussed.

“Can You Search for Me?”: Understanding and ImprovingUser‐SystemDialogues for Complex Search Tasks

“…There are some inherent challenges in developing conversational systems, including but not limited to the absence of cognition and the dynamic nature of the search process. Findings from prior research (Sa & Yuan, 2020; Turunen et al, 2012; Luger & Sellen, 2016) have highlighted that conversation systems are task‐based and incapable of performing complex or exploratory search tasks.…”

Improving the effectiveness of voice search systems through partial query modification

“…To complete the query reformulation, in the baseline system, the participants had to speak the new query completely “when was television invented?” In the experimental system, the participants needed to modify the previous query by saying “change movie to television .” To make the system less complicated and to reduce the learning load of the users, only three common voice commands (Table 1) from (Sa & Yuan, 2020b) were implemented.…”

“…Among the few studies about reformulation operations during voice search, Allauzen et al (2012) built a model which could support voice query refinements of insert, delete, and substitute, and trained a system based on typed query logs. In our previous work (Sa & Yuan, 2020b), we conducted a Wizard of Oz user‐centered experiment to investigate how users would partially modify the previous query by speaking to the system. We found that when given the opportunity of editing the previous query by voice, the participants conducted more partial QMs than complete queries.…”

Use of ICTS for socio-economic development of marginalised communities in rural areas: Proposals for establishment of sectoral Rural Entrepreneurial Networks

“…Virtual assistance like Amazon Alexa, Cortana, Viv, Cortana and Siri use voice search on search engine. Google has noted that more than twenty percent of mobile device searches are done using voice search (Sa and Yuan, 2020).…”