Crowdsourcing User Preferences and Query Judgments for Speech-Only Search

  • Johanne R Trippas
  • Damiano Spina
  • Lawrence Cavedon
  • Mark Sanderson
SIGIR 1st International Workshop on Conversational Approaches to Information Retrieval (CAIR'17), 2017

Presenting search results over a speech-only channel (e.g., searching in devices such as Amazon Echo or Google Home) involves a number of challenges due to the transient nature of audio. We present two case studies which used a crowdsourcing methodology to gather user preferences and query judgments. We believe the design used in our previous experiments can inform the design of similar crowdsourcing tasks involving audio.

Paper

PDF 554.55kB

Poster

PDF 746.97kB 

@inproceedings{trippas2017crowdsourcing,
 author = {Trippas, Johanne R. and Spina, Damiano and Cavedon, Lawrence and Sanderson, Mark},
 title = {Crowdsourcing User Preferences and Query Judgments for Speech-Only Search},
 booktitle = {SIGIR 1st International Workshop on Conversational Approaches to Information Retrieval (CAIR'17)},
 series = {CAIR '17},
 year = {2017}
}
Damiano Spina