Discovering and predicting user routines by differential analysis of social network traces

Abstract

Abstract-The study of human activity patterns traditionally relies on the continuous tracking of user location. We approach the problem of activity pattern discovery from a new perspective which is rapidly gaining attention. Instead of actively sampling increasing volumes of sensor data, we explore the participatory sensing potential of multiple mobile social networks, on which users often disclose information about their location and the venues they visit. In this paper, we present automated techniques for filtering, aggregating, and processing combined social networking traces with the goal of extracting descriptions of regularly-occurring user activities, which we refer to as "user routines". We report our findings based on two localized data sets about a single pool of users: the former contains public geotagged Twitter messages, the latter Foursquare check-ins that provide us with meaningful venue information about the locations we observe. We analyze and combine the two datasets to highlight their properties and show how the emergent features can enhance our understanding of users' daily schedule. Finally, we evaluate and discuss the potential of routine descriptions for predicting future user activity and location.

Discovery of spatio-temporal patterns from location-based social networks

“…These sets of activities characterized the different groups of persons in a city, as a first step to extract user profiles. In (Pianese, An, Kawsar, & Ishizuka, 2013), data from Twitter cointaining Foursquare check-ins was used to predict user activity. Different clusterings of the events were obtained using as characteristics spatial location, time of the day and venue type.…”

Weak social ties improve content delivery in behavior-aware opportunistic networks

“…By contrast, the behavior of a user can be defined considering several aspects, and different behaviors shall be considered for content diffusion. As an example, in [30], the temporal, spatial, and activity profiles of the users are studied. In [23], user behavior is analyzed in terms of visited locations and accessed web domains.…”

Understanding Social Influence in Activity Location Choice and Lifestyle Patterns Using Geolocation Data from Social Media

“…As such, there are many opportunities to gain fundamental knowledge about user behavior analyzing these data at various levels of spatiotemporal resolution. Researchers are realizing the potential to harness the rich information provided by the location-based data, which have already enabled many novel applications, such as recommendation system for physical locations (or activity) (Zheng et al, 2010;Chang and Sun, 2011;Bao et al, 2012), recommending potential customers or friend (Zheng, 2011;Saez-Trumper et al, 2012), determining popular travel routes in a city (Wei et al, 2012), discovering mobility and activity choice behavior (Cheng et al, 2011;Noulas et al, 2012;Hasan et al, 2013;Pianese et al, 2013), activity recognition and classification (Lian and Xie, 2011;Hasan and Ukkusuri, 2014), estimating urban travel demand and traffic flow (Hasan, 2013;Liu et al, 2014;Wu et al, 2014), and modeling the influence of friendship on mobility patterns (Cho et al, 2011;Wang et al, 2011). In this paper, we analyze a dataset from a social media check-in service to understand the extent of social influence on individual activity behavior.…”