Urban activity pattern classification using topic models from online geo-location data

Abstract Location-based check-in services in various social media applications have enabled individuals to share their activity-related choices providing a new source of human activity data. Although geo-location data has the potential to infer multi-day patterns of individual activities, appropriate methodological approaches are needed. This paper presents a technique to analyze large-scale geo-location data from social media to infer individual activity patterns. A data-driven modeling approach, based on topic modeling, is proposed to classify patterns in individual activity choices. The model provides an activity generation mechanism which when combined with the data from traditional surveys is potentially a useful component of an activity-travel simulator. Using the model, aggregate patterns of users’ weekly activities are extracted from the data. The model is extended to also find user-specific activity patterns. We extend the model to account for missing activities (a major limitation of social media data) and demonstrate how information from activity-based diaries can be complemented with longitudinal geo-location information. This work provides foundational tools that can be used when geo-location data is available to predict disaggregate activity patterns.

[1]  M. Steyvers.  Combining Feature Norms and Text Data with Topic Models , 2022 .

[2]  Huan Liu,et al.  gSCorr: modeling geo-social correlations for new check-ins on location-based social networks , 2012, CIKM.

[3]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[4]  Eric I. Pas,et al.  A Flexible and Integrated Methodology for Analytical Classification of Daily Travel-Activity Behavior , 1983 .

[5]  Satish V. Ukkusuri,et al.  Understanding urban human activity and mobility patterns using large-scale location-based data from online social media , 2013, UrbComp '13.

[6]  Perry O. Hanson,et al.  THE TRAVEL-ACTIVITY PATTERNS OF URBAN RESIDENTS: DIMENSIONS AND RELATIONSHIPS TO SOCIODEMOGRAPHIC CHARACTERISTICS , 1981 .

[7]  Samiul Hasan.  Modeling urban mobility dynamics using geo-location data , 2013 .

[8]  Peter Norvig,et al.  The Unreasonable Effectiveness of Data , 2009, IEEE Intelligent Systems.

[9]  Davy Janssens,et al.  The usefulness of the Sequence Alignment Methods in validating rule-based activity-based forecasting models , 2012 .

[10]  Meredith Cebelak.  Location-based social networking data : doubly-constrained gravity model origin-destination estimation of the urban travel demand for Austin, TX , 2013 .

[11]  Kyumin Lee,et al.  Exploring Millions of Footprints in Location Sharing Services , 2011, ICWSM.

[12]  Will Recker,et al.  Activity Pattern Recognition by Using Support Vector Machines with Multiple Classes , 2013 .

[13]  Eric Horvitz,et al.  Predicting Depression via Social Media , 2013, ICWSM.

[14]  Ming Ni,et al.  Using Social Media to Predict Traffic Flow under Special Event Conditions , 2013 .

[15]  Daniel Gatica-Perez,et al.  Discovering routines from large-scale human locations using probabilistic topic models , 2011, TIST.

[16]  E. I. Pas.  The Effect of Selected Sociodemographic Characteristics on Daily Travel-Activity Behavior , 1984 .

[17]  Jure Leskovec,et al.  Friendship and mobility: user movement in location-based social networks , 2011, KDD.

[18]  Bin Ran,et al.  Location-Based Social Networking Data , 2014 .

[19]  Bin Ran,et al.  Dynamic Origin-Destination Travel Demand Estimation Using Location Based Social Networking Data , 2014 .

[20]  Bernt Schiele,et al.  Discovery of activity patterns using topic models , 2008 .

[21]  Mark Steyvers,et al.  Finding scientific topics , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[22]  Norman M. Sadeh,et al.  The Livehoods Project: Utilizing Social Media to Understand the Dynamics of a City , 2012, ICWSM.

[23]  Konstantinos Gkiotsalitis,et al.  A Probabilistic Activity Model for Predicting the Mobility Patterns of Homogeneous Social Groups Based on Social Network Data , 2014 .

[24]  Christian P. Robert,et al.  The Bayesian choice : from decision-theoretic foundations to computational implementation , 2007 .

[25]  Clarke Wilson,et al.  Activity patterns in space and time: calculating representative Hagerstrand trajectories , 2008 .

[26]  Eric I. Pas.  ANALYTICALLY DERIVED CLASSIFICATIONS OF DAILY TRAVEL-ACTIVITY BEHAVIOR: DESCRIPTION, EVALUATION, AND INTERPRETATION , 1982 .

[27]  Eric I. Pas,et al.  Travel-Activity Behavior in Time and Space: Methods for Representation and Analysis , 1985 .

[28]  Ta Theo Arentze,et al.  Activity pattern similarity : a multidimensional sequence alignment method , 2002 .

[29]  M. McNally,et al.  Travel/activity analysis: Pattern recognition, classification and interpretation , 1985 .

[30]  Thomas L. Griffiths,et al.  Probabilistic Topic Models , 2007 .

[31]  Cecilia Mascolo,et al.  An Empirical Study of Geographic User Activity Patterns in Foursquare , 2011, ICWSM.

[32]  Satish V. Ukkusuri,et al.  A novel transit rider satisfaction metric: Rider sentiments measured from online social media data , 2013 .

[33]  Ta Theo Arentze,et al.  Pattern Recognition in Complex Activity Travel Patterns: Comparison of Euclidean Distance, Signal-Processing Theoretical, and Multidimensional Sequence Alignment Methods , 2001 .