# Phone-based Metric as a Predictor for Basic Personality Traits

arXiv: https://arxiv.org/abs/1604.04696 · HTML: https://mlsanity.com/paper/1604.04696/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2016.

## Built on by (most cited first, 3 of 3)

- [Using Mobile Data and Deep Models to Assess Auditory Verbal Hallucinations](https://mlsanity.com/paper/2304.11049/) (2023)
- [Causal Discovery and Inference towards Urban Elements and Associated Factors](https://mlsanity.com/paper/2503.06395/) (2025)
- [Can LLMs Infer Conversational Agent Users' Personality Traits from Chat History?](https://mlsanity.com/paper/2604.19785/) (2026)

## Abstract (arXiv)

Basic personality traits are typically assessed through questionnaires. Here we consider phone-based metrics as a way to asses personality traits. We use data from smartphones with custom data-collection software distributed to 730 individuals. The data includes information about location, physical motion, face-to-face contacts, online social network friends, text messages and calls. The data is further complemented by questionnaire-based data on basic personality traits. From the phone-based metrics, we define a set of behavioral variables, which we use in a prediction of basic personality traits. We find that predominantly, the Big Five personality traits extraversion and, to some degree, neuroticism are strongly expressed in our data. As an alternative to the Big Five, we investigate whether other linear combinations of the 44 questions underlying the Big Five Inventory are more predictable. In a tertile classification problem, basic dimensionality reduction techniques, such as independent component analysis, increase the predictability relative to the baseline from 11% to 23%. Finally, from a supervised linear classifier, we were able to further improve this predictability to 33%. In all cases, the most predictable projections had an overweight of the questions related to extraversion and neuroticism. In addition, our findings indicate that the score system underlying the Big Five Inventory disregards a part of the information available in the 44 questions.