Machine learning for phone-based relationship estimation: The need to consider population heterogeneity

Tony Liu, Jennifer Nicholas, Max M. Theilig, Sharath C. Guntuku, Konrad Kording, David C. Mohr, Lyle Ungar

Research output: Contribution to journalArticlepeer-review

Abstract

Estimating the category and quality of interpersonal relationships from ubiquitous phone sensor data matters for studying mental well-being and social support. Prior work focused on using communication volume to estimate broad relationship categories, often with small samples. Here we contextualize communications by combining phone logs with demographic and location data to predict interpersonal relationship roles on a varied sample population using automated machine learning methods, producing better performance (F 1 = 0.68) than using communication features alone (F 1 = 0.62). We also explore the effect of age variation in the underlying training sample on interpersonal relationship prediction and find that models trained on younger subgroups, which is popular in the field via student participation and recruitment, generalize poorly to the wider population. Our results not only illustrate the value of using data across demographics, communication patterns and semantic locations for relationship prediction, but also underscore the importance of considering population heterogeneity in phone-based personal sensing studies.

Original languageEnglish (US)
Article number145
JournalProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Volume3
Issue number4
DOIs
StatePublished - Dec 2019

Keywords

  • Automated machine learning
  • Population heterogeneity
  • Semantic location-based features
  • Social relationship prediction

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Machine learning for phone-based relationship estimation: The need to consider population heterogeneity'. Together they form a unique fingerprint.

Cite this