Crowdsourcing User Preferences and Query Judgments for Speech-Only Search
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.
@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} }