Altruism, i.e. an act that one does at their own expense that tends to enhance others well-being, is a fundamental human behavior with implications for personal and societal welfare. Hence, modeling altruism is an important building block in designing humancentered computing systems. Traditional methods for understanding an individual's altruistic propensities have been surveys and lab experiments. However, the emerging "personal big data" coming from mobile and ubiquitous devices allows for creation of lower-cost, quicker, automated methods for modeling human behaviors and propensities. We propose a new methodology to model altruism using phone data. Based on analysis of data from a 10-week field study (N=55 participants), we report that: (1) multiple phone-based features are associated with users' altruistic propensities; (2) phone features-based altruism prediction model yielded significantly better performance than a demography-based model. The results pave way for utilizing "personal big data" to model altruism in multiple commercial and social applications.
Interpersonal trust mediates multiple socio-technical systems and has implications for personal and societal well-being. Consequently, it is crucial to devise novel machine learning methods to infer interpersonal trust automatically using mobile sensor-based behavioral data. Considering that social relationships are often affected by neighboring relationships within the same network, this work proposes using a novel neighbor-aware deep learning architecture (NADAL) to enhance the inference of interpersonal trust scores. Based on analysis of call, SMS, and Bluetooth interaction data from a one-year field study involving 130 participants, we report that: (1) adding information about neighboring relationships improves trust score prediction in both shallow and deep learning approaches; and (2) a custom-designed neighbor-aware deep learning architecture outperforms a baseline feature concatenation based deep learning approach. The results obtained at interpersonal trust prediction are promising and have multiple implications for trust-aware applications in the emerging social internet of things.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.