TY - GEN
T1 - SMS-based web search for low-end mobile devices
AU - Chen, Jay
AU - Subramanian, Lakshmi
AU - Brewer, Eric
PY - 2010
Y1 - 2010
N2 - Short Messaging Service (SMS) based mobile information services have become increasingly common around the world, especially in emerging regions among users with low-end mobile devices. This paper presents the design and implementation of SMSFind, an SMS-based search system that enables users to obtain extremely concise (one SMS message of 140 bytes) and appropriate search responses for queries across arbitrary topics in one round of interaction. SMSFind is designed to complement existing SMS-based search services that are either limited in the topics they recognize or involve a human in the loop. Given an unstructured search query, SMSFind, uses a conventional search engine as a back-end to elicit several search responses and uses a combination of information retrieval techniques to extract the most appropriate 140-byte snippet as the final SMS search response. We show that SMSFind returns appropriate responses for 57.3% of ChaCha search queries in our test set; this accuracy rate is high given that ChaCha employs a human to answer the same questions. We have also deployed a pilot version of SMSFind for use with a small focus group in Kenya to explore the interaction issues of such a system and share our early experiences.
AB - Short Messaging Service (SMS) based mobile information services have become increasingly common around the world, especially in emerging regions among users with low-end mobile devices. This paper presents the design and implementation of SMSFind, an SMS-based search system that enables users to obtain extremely concise (one SMS message of 140 bytes) and appropriate search responses for queries across arbitrary topics in one round of interaction. SMSFind is designed to complement existing SMS-based search services that are either limited in the topics they recognize or involve a human in the loop. Given an unstructured search query, SMSFind, uses a conventional search engine as a back-end to elicit several search responses and uses a combination of information retrieval techniques to extract the most appropriate 140-byte snippet as the final SMS search response. We show that SMSFind returns appropriate responses for 57.3% of ChaCha search queries in our test set; this accuracy rate is high given that ChaCha employs a human to answer the same questions. We have also deployed a pilot version of SMSFind for use with a small focus group in Kenya to explore the interaction issues of such a system and share our early experiences.
KW - Cell phones
KW - Question/answering
KW - SMS
KW - Search
UR - http://www.scopus.com/inward/record.url?scp=78649281128&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78649281128&partnerID=8YFLogxK
U2 - 10.1145/1859995.1860011
DO - 10.1145/1859995.1860011
M3 - Conference contribution
AN - SCOPUS:78649281128
SN - 9781450301817
T3 - Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM
SP - 125
EP - 135
BT - MobiCom'10 and MobiHoc'10 - Proceedings of the 16th Annual International Conference on Mobile Computing and Networking and 11th ACM International Symposium on Mobile Ad Hoc Networking and Computing
PB - Association for Computing Machinery
T2 - 16th Annual Conference on Mobile Computing and Networking, MobiCom 2010
Y2 - 20 September 2010 through 24 September 2010
ER -