Abstract
A computer system was designed to telephone voters en masse and play a short campaign message in support of a candidate. The calling program used a new algorithm to detect and leave messages on answering machines, or, when a human answered, to observe telephone etiquette. It was tested in the Raleigh City Council election of 1993. Over 30,000 households were called in both a primary and final election. Immediately after the November election about 600 of the called households were polled by telephone (using human interrogators) to measure the effect of the calling campaign. Among persons reached who actually voted, 52% remembered the candidate's name, and 6.4% said the call had affected their vote.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles and news from researchers in related subjects, suggested using machine learning.References
Edgar, B. (1992).PC-Based Voice Processing, New York: Telecom Library Inc.
Frenkel, K.A. (1988). Computers and elections.Communications of the Association for Computing Machinery, 31 (10):1176–1183.
Garramore, G. (1990). Effects of negative political advertising on the political process.Journal of Broadcasting and Electronic Media, 34, (Summer):299.
Saltman, R.B. (1988). Accuracy, integrity and security in computerized vote-tallying.Communications of the Association for Computing Machinery, 31 (10):1184–1191, 1218.
Shannon, M.R. (1994). Political software buyer's guide.Campaigns & Elections 15(1):36–39.
Stevens, G. (1993). The positive side to negative advertising.State Government News, 36(July):16.
Tetschner, W. (1993).Voice Processing (2nd ed. Norwood, MA: Artech House, Inc.