Title: Predicting eBook purchases of heterogeneous social groups in a social network site using network metrics

Authors: Jongtae Yu; Dong-Yop Oh; Triss Ashton; Yang Wang

Addresses: King Fahd University of Petroleum and Minerals (KFUPM), Academic Belt Road, Dhahran 31261, Kingdom of Saudi Arabia ' Department of Information Systems, Auburn University at Montgomery, 7400 East Dr, Montgomery, AL 36117, USA ' Management Department, Tarleton State University, Box T-0330, Stephenville, TX 76402, USA ' Information Technology Management, University of Wisconsin-Milwaukee, Milwaukee, WI 53211, USA

Abstract: This study examines users' social influence on e-book purchases within a social network drawing on the structural equivalence model. Structural equivalence holds that higher social influence levels exist among socially equivalent people (Burt, 1987). Using structural equivalence, network users were classified as either equivalent or inequivalent. Given that measurement data on social relationships among people within a network are often limited, to assign users to groups, link estimation utilised product choices to calculate network measures. With that framework, purchasing behaviours were predicted using various algorithms. Consistent with structural equivalence, the findings demonstrate that the average accuracy under the various algorithms is significantly higher in equivalent than inequivalent networks. Finally, comparing results with and without the network measurement variables suggests that failing to consider social equivalence may mislead prediction results by overestimating the social influence effect in low equivalent groups or underestimating the effect of high social equivalent groups.

Keywords: social influence; social network analytics; structural equivalence; classification; sales prediction; algorithm testing; biased predictions; network prediction performance.

DOI: 10.1504/IJMC.2023.131803

International Journal of Mobile Communications, 2023 Vol.22 No.1, pp.92 - 110

Received: 02 Feb 2021
Accepted: 03 Aug 2021
Published online: 04 Jul 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article