SMS-based web search for low-end mobile devices

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.