Wnioskowanie o relacjach i cechach psychometrycznych z logów połączeń modelowanych 
z wykorzystaniem procesów punktowych Hawkesa
[Inferring relationships and psychometric traits from call logs modeled using Hawkes 
point processes]

Mateusz Nurek (Doctoral School - Information & Communication Technology, PWr, Wrocław)


It is not news that our mobile phones contain a wealth of private information about 
us, and that is why we try to keep them secure. But even the traces of how we 
communicate can also tell quite a bit about human behavior. In this work, we start 
from the calling and texting history of college students enrolled in two extensive 
longitudinal studies: NetSense and NetHealth. Then, we link it to students' 
relationships with their peers and their personality profiles as estimated from 
personality questionnaires. First, we show that a Hawkes point process model with a 
power-law decaying kernel can accurately account for temporal patterns in the 
calling activity between peers. Second, we show that the fitted parameters of the 
Hawkes model predicts the type of self-reported relationship and their temporal 
dynamics. Last, we build descriptors for the students in the study by jointly 
modeling the communication series initiated by them. 

We find that Hawkes-modeled communication patterns reveal important information 
about the students' "Big Five" psychometric traits. For some traits such as openness 
or extraversion, the results are comparable to the upper bound performances obtained 
on self-report data from surveys about hobbies, activities, well-being, grades 
received, and health conditions. These results have important implications, as they 
indicate that information usually residing outside the control of individuals (such 
as call and text logs) reveals information about dyadic relationships and even 
individual personality traits.