Clarifications and question specificity in synchronous social Q&A

Authors:
Makoto P. Kato;Ryen W. White;Jaime Teevan;Susan T. Dumais
Affiliations:
Kyoto University, Kyoto, Japan;Microsoft Research, Redmond, Washington, USA;Microsoft Research, Redmond, Washington, USA;Microsoft Research, Redmond, Washington, USA
Venue:
CHI '13 Extended Abstracts on Human Factors in Computing Systems
Year:
2013

Citing 8
Cited 0

An experimental study of common ground in text-based communication

CHI '91 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Information sought and information provided: an empirical study of user/expert dialogues

CHI '85 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Resolving ellipsis in clarification

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
On the means for clarification in dialogue

SIGDIAL '01 Proceedings of the Second SIGdial Workshop on Discourse and Dialogue - Volume 16
Synchronous broadcast messaging: the use of ICT

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Predicting information seeker satisfaction in community question answering

Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval
The anatomy of a large-scale social search engine

Proceedings of the 19th international conference on World wide web
Supporting synchronous social q&a throughout the question lifecycle

Proceedings of the 20th international conference on World wide web

Quantified Score

Hi-index	0.00

Visualization

Abstract

Synchronous social question-and-answer (Q&A) systems help people find answer by connecting them with others via instant messaging. To understand how such systems can quickly and effectively establish fruitful connections, we analyze conversations collected from a working enterprise social Q&A system. We show that when askers start with underspecified questions (e.g., "I need help with mail access"), they receive clarification requests, extended dialogs, and poor responses. To address this we are implementing and deploying support within a Q&A system to foster more complete questions, reduce the need for clarification, and benefit both askers and answerers.