Organizations rely on social outreach campaigns to raise financial support, recruit volunteers, and increase public awareness. In order to maximize response rates, organizations face the challenging problem of designing appropriately tailored interactions for each user. An interaction consists of a specific combination of message, media channel, sender, tone, and possibly many other attributes. The purpose of this paper is to address the problem of how to design tailored interactions for each user to maximize the probability of a desired response.
A nearest-neighbor (NN) algorithm is developed for interaction design. Simulation-based experiments are then conducted to compare positive response rates obtained by two forms of this algorithm against that of several control interaction design strategies. A factorial experimental design is employed which varies three user population factors in a combinatorial manner, allowing the methods to be compared across eight distinct scenarios.
The NN algorithms significantly outperformed all three controls in seven out of the eight scenarios. Increases in response rates ranging from approximately 20 to 400 percent were observed.
This work proposes a data-oriented method for designing tailored interactions for individual users in social outreach campaigns which can enable significant increases in positive response rates. Additionally, the proposed algorithm is relatively easy to implement.
The problem of optimal interaction design in social outreach campaigns is scarcely addressed in the literature. This work proposes an effective and easy to implement solution approach for this problem.
