Tamil market: a spoken dialog system for rural India
CHI '06 Extended Abstracts on Human Factors in Computing Systems
A comparative study of speech and dialed input voice interfaces in rural India
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Avaaj Otalo: a field study of an interactive voice forum for small farmers in rural India
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Evaluating the accuracy of data collection on mobile phones: a study of forms, sms, and voice
ICTD'09 Proceedings of the 3rd international conference on Information and communication technologies and development
FOLKSOMAPS - towards community driven intelligent maps for developing regions
ICTD'09 Proceedings of the 3rd international conference on Information and communication technologies and development
HIV health information access using spoken dialogue systems: touchtone vs. speech
ICTD'09 Proceedings of the 3rd international conference on Information and communication technologies and development
Speech vs. touch-tone: telephony interfaces for information access by low literate users
ICTD'09 Proceedings of the 3rd international conference on Information and communication technologies and development
Freedom fone: dial-up information service
ICTD'09 Proceedings of the 3rd international conference on Information and communication technologies and development
Tangaza: frugal group messaging through speech and text
Proceedings of the First ACM Symposium on Computing for Development
Evaluation of IVR data collection UIs for untrained rural users
Proceedings of the First ACM Symposium on Computing for Development
Designing mobile interfaces for novice and low-literacy users
ACM Transactions on Computer-Human Interaction (TOCHI)
The Lwazi community communication service: design and piloting of a voice-based information service
Proceedings of the 20th international conference companion on World wide web
Designing a phone broadcasting system for urban sex workers in India
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
An asymmetric communications platform for knowledge sharing with low-end mobile phones
Proceedings of the 24th annual ACM symposium adjunct on User interface software and technology
Experiences of deploying and commercializing a community radio automation system in India
Proceedings of the 2nd ACM Symposium on Computing for Development
A voice service for user feedback on school meals
Proceedings of the 2nd ACM Symposium on Computing for Development
Emergent practices around CGNet Swara, voice forum for citizen journalism in rural India
Proceedings of the Fifth International Conference on Information and Communication Technologies and Development
PhonePeti: exploring the role of an answering machine system in a community radio station in India
Proceedings of the Fifth International Conference on Information and Communication Technologies and Development
Viral entertainment as a vehicle for disseminating speech-based services to low-literate users
Proceedings of the Fifth International Conference on Information and Communication Technologies and Development
Open data kit: tools to build information services for developing regions
Proceedings of the 4th ACM/IEEE International Conference on Information and Communication Technologies and Development
| Hi-index | 0.00 |
Many organizations in the developing world need to conduct phone surveys to collect data from low-income respondents. Such organizations generally have two options: employ a live operator, or utilize interactive voice response (IVR). Despite the relevance of this question, we are unaware of any work that rigorously compares the accuracy, speed, and cost of an IVR survey relative to a live operator. In this paper, we address these questions by giving two identical interviews -- one using IVR, and one using a live operator -- to 31 low-income job seekers in India. The IVR interview included a brief introduction by a live operator, to provide context for the call. Out of the 20 people who completed both surveys, we found that IVR incurs a 4.0% error rate (95% C. I. 2.5% -- 6.1%) and requires 2.5 times longer for users. We summarize our experience as a set of recommendations for practitioners in this space.