What did you do today? Discovering daily routines from large-scale mobile data
What did you do today? Discovering daily routines from large-scale mobile data
We present a framework built from two Hierarchical Bayesian topic models to discover human location-driven routines from mobile phones. The framework uses location-driven bag representations of people's daily activities obtained from celltower connections. Using 68 000+ hours of real-life human data from the Reality Mining dataset, we successfully discover various types of routines. The first studied model, Latent Dirichlet Allocation (LDA), automatically discovers characteristic routines for all individuals in the study, including "going to work at 10am", "leaving work at night", or "staying home for the entire evening". In contrast, the second methodology with the Author Topic model (ATM) finds routines characteristic of a selected groups of users, such as "being at home in the mornings and evenings while being out in the afternoon", and ranks users by their probability of conforming to certain daily routines.
Algorithms, Human factors
849-852
Association for Computing Machinery
Farrahi, Katayoun
bc848b9c-fc32-475c-b241-f6ade8babacb
Gatica-Perez, Daniel
583e99b0-abef-4d2a-b54f-70ab7b498975
1 December 2008
Farrahi, Katayoun
bc848b9c-fc32-475c-b241-f6ade8babacb
Gatica-Perez, Daniel
583e99b0-abef-4d2a-b54f-70ab7b498975
Farrahi, Katayoun and Gatica-Perez, Daniel
(2008)
What did you do today? Discovering daily routines from large-scale mobile data.
In MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops.
Association for Computing Machinery.
.
(doi:10.1145/1459359.1459503).
Record type:
Conference or Workshop Item
(Paper)
Abstract
We present a framework built from two Hierarchical Bayesian topic models to discover human location-driven routines from mobile phones. The framework uses location-driven bag representations of people's daily activities obtained from celltower connections. Using 68 000+ hours of real-life human data from the Reality Mining dataset, we successfully discover various types of routines. The first studied model, Latent Dirichlet Allocation (LDA), automatically discovers characteristic routines for all individuals in the study, including "going to work at 10am", "leaving work at night", or "staying home for the entire evening". In contrast, the second methodology with the Author Topic model (ATM) finds routines characteristic of a selected groups of users, such as "being at home in the mornings and evenings while being out in the afternoon", and ranks users by their probability of conforming to certain daily routines.
This record has no associated files available for download.
More information
Published date: 1 December 2008
Venue - Dates:
16th ACM International Conference on Multimedia, MM '08, , Vancouver, BC, Canada, 2008-10-26 - 2008-10-31
Keywords:
Algorithms, Human factors
Identifiers
Local EPrints ID: 430374
URI: http://eprints.soton.ac.uk/id/eprint/430374
PURE UUID: 759bb352-f696-4a84-92c3-12a8471bc07a
Catalogue record
Date deposited: 26 Apr 2019 16:30
Last modified: 16 Mar 2024 04:31
Export record
Altmetrics
Contributors
Author:
Katayoun Farrahi
Author:
Daniel Gatica-Perez
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics