Abstract
Conference Title: 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) Conference Start Date: 2017, Aug. 4 Conference End Date: 2017, Aug. 8 Conference Location: San Francisco, CA, USA Altruism i.e. an act that one does at her own expense that tends to enhance others well-being is a fundamental human behavior with implications for personal and societal welfare. As a result, understanding altruism is an important building block in designing well-functioning socio-technical systems and attaining the Internet of People vision. Traditional methods for understanding individual's altruistic propensities have been surveys and lab experiments. This paper proposes a new methodology to model altruism based on phoneotypes (mobile phones observations of a combination of people's traits) that ultimately aim to replace traditional methods like surveys with a low-cost, quick, automated method. The data in this paper were gathered from a 10-week field study involving 55 participants. We find that: (1) many phone-based features are potentially related to participant's altruistic propensities; (2) phone-based features and demographics when combined created a prediction model with promising results capable of predicting altruism in a better way than a demography-based model. This study provides an exciting opportunity to advance our knowledge in identifying altruism in numerous settings socially and commercially.