Potentials of using social media to infer the longitudinal travel behavior: A sequential model-based clustering method

This study explores the possibility of employing social media data to infer the longitudinal travel behavior. The geo-tagged social media data show some unique features including location-aggregated features, distance-separated features, and Gaussian distributed features. Compared to conventional household travel survey, social media data is less expensive, easier to obtain and the most importantly can monitor the individual’s longitudinal travel behavior features over a much longer observation period. This paper proposes a sequential model-based clustering method to group the high-resolution Twitter locations and extract the Twitter displacements. Further, this study details the unique features of displacements extracted from Twitter including the demographics of Twitter user, as well as the advantages and limitations. The results are even compared with those from traditional household travel survey, showing promises in using displacement distribution, length, duration and start time to infer individual’s travel behavior. On this basis, one can also see the potential of employing social media to infer longitudinal travel behavior, as well as a large quantity of short-distance Twitter displacements. The results will supplement the traditional travel survey and support travel behavior modeling in a metropolitan area.     

Forecasting current and next trip purpose with social media data and Google Places

Trip purpose is crucial to travel behavior modeling and travel demand estimation for transportation planning and investment decisions. However, the spatial-temporal complexity of human activities makes the prediction of trip purpose a challenging problem. This research, an extension of work by Ermagun et al. (2017) and Meng et al. (2017), addresses the problem of predicting both current and next trip purposes with both Google Places and social media data. First, this paper implements a new approach to match points of interest (POIs) from the Google Places API with historical Twitter data. Therefore, the popularity of each POI can be obtained. Additionally, a Bayesian neural network (BNN) is employed to model the trip dependence on each individual’s daily trip chain and infer the trip purpose. Compared with traditional models, it is found that Google Places and Twitter information can greatly improve the overall accuracy of prediction for certain activities, including “EatOut”, “Personal”, “Recreation” and “Shopping”, but not for “Education” and “Transportation”. In addition, trip duration is found to be an important factor in inferring activity/trip purposes. Further, to address the computational challenge in the BNN, an elastic net is implemented for feature selection before the classification task. Our research can lead to three types of possible applications: activity-based travel demand modeling, survey labeling assistance, and online recommendations.     

Parking preferences among tourists in Newport,Rhode Island

Like many tourist destinations, Newport, Rhode Island relies upon high season tourist volumes for its economic health. Most visitors arrive by car, concentrated during certain hours on summer weekends, severely congesting the town’s major arteries and forcing many visitors to spend considerable time in their car. A transportation planning strategy which reduced congestion would enhance the quality of the visiting experience, increase the time visitors are able to spend in shops and at attractions, and draw additional visitors. However, identifying effective solutions requires understanding factors that affect tourists’ transit choices. We develop a conceptual model of Newport visitors’ parking and transit choices, expanding traditional transit choice models to include features such as scenery we expect to influence tourists. Using a stated preference survey of visitors, we find scenery, transit mode options and congestion are the major drivers of tourists’ parking choices. We also develop welfare estimates to enable analysis of proposed transportation plans.     

Social networks and joint/solo activity–travel behavior

The social dimension of activity–travel behavior has recently received much research attention. This paper aims to make a contribution to this growing literature by investigating individuals’ engagements in joint activities and activity companion choices. Using activity–travel diary data collected in Hong Kong in 2010, this study examines the impact of social network attributes on the decisions between solo and joint activities, and for joint activities, the choices of companions. Chi-square difference tests are used to assess the importance of social network variables in explaining joint activity behavior. We find that the inclusion of social network attributes significantly improves the goodness-of-fit of the model with only socioeconomic variables. Specifically, individuals receiving emotional support and social companionship from family members/relatives are found to more likely undertake joint activities with their family members/relatives; the size of personal social networks is found to be a significant determinant of companion choices for joint activities; and activity companions are found to be significant determinants of travel companions. The findings of this study improve the understanding about activity–travel, especially joint activity–travel decisions.     

Identifying trip ends from raw GPS data with a hybrid spatio-temporal clustering algorithm and random forest model: a case study in Shanghai

ABSTRACT

Smartphones have been advocated as the preferred devices for travel behavior studies over conventional surveys. But the primary challenges are candidate stops extraction from GPS data and trip ends distinction from noise. This paper develops a Resident Travel Survey System (RTSS) for GPS data collection and travel diary verification, and then uses a two-step method to identify trip ends. In the first step, a density-based spatio-temporal clustering algorithm is proposed to extract candidate stops from trajectories. In the second step, a random forest model is applied to distinguish trip ends from mode transfer points. Results show that the clustering algorithm achieves a precision of 96.2%, a recall of 99.6%, mean absolute error of time within 3?min, and average offset distance within 30 meters. The comprehensive accuracy of trip ends identification is 99.2%. The two-step method performs well in trip ends identification and promotes the efficiency of travel survey systems.     

An adaptive hawkes process formulation for estimating time-of-day zonal trip arrivals with location-based social networking check-in data

Location-Based Social Networking (LBSN) services, such as Foursquare, Facebook check-ins, and Geo-tagged Twitter tweets, have emerged as new secondary data sources for studying individual travel mobility patterns at a fine-grained level. However, the differences between human social behavioral and travel patterns can cause significant sampling bias for travel demand estimation. This paper presents a dynamic model to estimate time-of-day zonal trip arrival patterns. In the proposed model, the state propagation is formulated by the Hawkes process; the observation model implements LBSN sampling. The proposed model is applied to Foursquare check-in data collected from Austin, Texas in 2010 and calibrated with Origin-Destination (OD) data and time of day factor from Capital Area Metropolitan Planning Organization (CAMPO). The proposed model is compared with a simple aggregation model of trip purposes and time of day based on a prior daily OD estimation model using the LBSN data. The results illustrate the promising benefits of applying stochastic point process models and state-space modeling in time-of-day zonal arrival pattern estimation with the LBSN data. The proposed model can significantly reduce the number of parameters to calibrate in order to reduce the sampling bias of LBSN data for trip arrival estimation.     

Analysis of tourist behaviour based on the tracking data collected using a mobile communication instrument

Recently, tracking-type travel data collection methods using mobile communication instruments have developed rapidly. The detailed and accurate travel data are useful for understanding travel behaviour and evaluating the actual effects of transport policy such as traffic demand management. This paper studies a simple index of a tourist behaviour using tracking data collected with a mobile instrument. Based on the proposed index and actual data collected in Kobe, cluster analysis is applied to find the topological characteristics of tourist behaviour.     

Nudging people towards more sustainable residential choice decisions: an intervention based on focalism and visualization

Transportation - There have been numerous behavior change studies focused on sustainable travel mode choices. In this study we focused on the residential choices that in turn influence travel...     

Vehicle kilometers traveled reduction impacts of Transit-Oriented Development: Evidence from Shanghai City

The role of residential self-selection has become a major subject in the debate over the relationships between the built environment and travel behavior. Numerous previous empirical studies on this subject have provided valuable insights into the associations between the built environment and travel behavior. However, the vast majority of the studies were conducted in North American and European cities; yet this research is still in its infancy in most developing countries, including China, where residential and transport choices are likely to be more constrained and travel-related attitudes quite different from those in the developed world. Using the data collected from 2038 residents currently living in TOD neighborhoods and non-TOD neighborhoods in Shanghai City, this paper aims to partly fill the gaps by investigating the causal relationship between the built environment and travel behavior in the Chinese context. More specifically, this paper employs Heckman’s sample selection model to examine the reduction impacts of TOD on personal vehicle kilometers traveled (VKT), controlling for self-selection. The results show that whilst the effects of residential self-selection are apparent; the built environment exhibits the most significant impacts on travel behavior, playing the dominant role. These findings produce a sound basis for local policymakers to better understand the nature and magnitude toward the impacts of the built environment on travel behavior. Providing the government department with reassurance that effective interventions and policies on land use aimed toward altering the built environment would actually lead to meaningful changes in travel behavior.     

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

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.     

Analyzing high speed rail passengers’ train choices based on new online booking data in China

This study explores two nonparametric machine learning methods, namely support vector regression (SVR) and artificial neural networks (ANN), for understanding and predicting high-speed rail (HSR) travelers’ choices of ticket purchase timings, train types, and travel classes, using ticket sales data. In the train choice literature, discrete choice analysis is the predominant approach and many variants of logit models have been developed. Alternatively, emerging travel choice studies adopt non-utility-based methods, especially nonparametric machine learning methods including SVR and ANN, because (1) those methods do not rely on assumptions on the relations between choices and explanatory variables or any prior knowledge of the underlying relations; (2) they have superb capabilities of iteratively identifying patterns and extracting rules from data. This paper thus contributes to the HSR train choice literature by applying and comparing SVR and ANN with a real-world case study of the Shanghai-Beijing HSR market in China. A new normalized metric capturing both the load factor and the booking lead time is proposed as the target variable and several train service attributes, such as day of week, departure time, travel time, fare, are identified as input variables. Computational results demonstrate that both SVR and ANN can predict the train choice behavior with high accuracy, outperforming the linear regression approach. Potential applications of this study, such as rail pricing reform, have also been identified.     

Spatial and temporal characterization of travel patterns in a traffic network using vehicle trajectories

This paper presents a trajectory clustering method to discover spatial and temporal travel patterns in a traffic network. The study focuses on identifying spatially distinct traffic flow groups using trajectory clustering and investigating temporal traffic patterns of each spatial group. The main contribution of this paper is the development of a systematic framework for clustering and classifying vehicle trajectory data, which does not require a pre-processing step known as map-matching and directly applies to trajectory data without requiring the information on the underlying road network. The framework consists of four steps: similarity measurement, trajectory clustering, generation of cluster representative subsequences, and trajectory classification. First, we propose the use of the Longest Common Subsequence (LCS) between two vehicle trajectories as their similarity measure, assuming that the extent to which vehicles’ routes overlap indicates the level of closeness and relatedness as well as potential interactions between these vehicles. We then extend a density-based clustering algorithm, DBSCAN, to incorporate the LCS-based distance in our trajectory clustering problem. The output of the proposed clustering approach is a few spatially distinct traffic stream clusters, which together provide an informative and succinct representation of major network traffic streams. Next, we introduce the notion of Cluster Representative Subsequence (CRS), which reflects dense road segments shared by trajectories belonging to a given traffic stream cluster, and present the procedure of generating a set of CRSs by merging the pairwise LCSs via hierarchical agglomerative clustering. The CRSs are then used in the trajectory classification step to measure the similarity between a new trajectory and a cluster. The proposed framework is demonstrated using actual vehicle trajectory data collected from New York City, USA. A simple experiment was performed to illustrate the use of the proposed spatial traffic stream clustering in application areas such as network-level traffic flow pattern analysis and travel time reliability analysis.     

Exploring the capacity of social media data for modelling travel behaviour: Opportunities and challenges

In the past few years, the social science literature has shown significance attention to extracting information from social media to track and analyse human movements. In this paper the transportation aspect of social media is investigated and reviewed. A detailed discussion is provided about how social media data from different sources can be used to indirectly and with minimal cost extract travel attributes such as trip purpose, mode of transport, activity duration and destination choice, as well as land use variables such as home, job and school location and socio-demographic attributes including gender, age and income. The evolution of the field of transport and travel behaviour around applications of social media over the last few years is studied. Further, this paper presents results of a qualitative survey from travel demand modelling experts around the world on applicability of social media data for modelling daily travel behaviour. The result of the survey reveals positive view of the experts about usefulness of such data sources.     

An automatic segmentation procedure for studying variations in mode choice behaviour

Urban areas are very complex and heterogeneous in terms of their population composition and activity systems. The transport system, modal choices and service levels available to the population also varies considerably across space and time. These similarities and differences in choices and levels of explanatory variables facing individual tripmakers have to be explicitly considered in any study of transport behvior. The common practice has been to include user attributes, in addition to the system characteristics, in the modal utility functions to help capture differences in choice behavior across individuals. However, it could well be that the mode-choice behavior of a segment of the population is fundamentally different from other segments of the population. In view of this, some studies have applied segmentation schemes to help identify the subgroups of presumably different travel responses. Typically, such schemes have been based on stratification of the population by a single variable, chosen either based on a priori notions or one-way cross tabulations. These have their shortcomings. Thus, this paper develops an analytical procedure that simultaneously deals with level of service, socioeconomic and spatial factors to determine the relative role each plays in determining travel behavior. The procedure is applied to data from the Toronto region to illustrate its use.     

Selfishness and altruism in the distribution of travel time and income

Most economic models assume that individuals act out their preferences based on self-interest alone. However, there have also been other paradigms in economics that aim to capture aspects of behavior that include fairness, reciprocity, and altruism. In this study we empirically examine preferences of travel time and income distributions with and without the respondent knowing their own position in each distribution. The data comes from a Stated Preference experiment where subjects were presented paired alternative distributions of travel time and income. The alternatives require a tradeoff between distributional concerns and the respondent’s own position. Choices also do not penalize or reward any particular choice. Overall, choices show individuals are willing forgo alternatives where they would be individually well off in the interest of distributional concerns in both the travel time and income cases. Exclusively self-interested choices are seen more in the income questions, where nearly 25 % of respondents express such preferences, than in the travel time case, where only 5 % of respondents make such choices. The results also suggest that respondents prioritize their own position differently relative to regional distributions of travel time and income. Estimated choice models show that when it comes to travel time, individuals are more concerned with societal average travel time followed by the standard deviation in the region and finally their own travel time, while in the case of income they are more concerned with their own income, followed by a desire for more variability, and finally increasing the minimum income in their region. When individuals do not know their fate after a policy change that affects regional travel time, their choices appear to be mainly motivated by risk averse behavior and aim to reduce variability in outcomes. On the other hand, in the income context, the expected value appears to drive choices. In all cases, population-wide tastes are also estimated and reported.     

Investigating heterogeneity in social influence by social distance in car-sharing decisions under uncertainty: A regret-minimizing hybrid choice model framework based on sequential stated adaptation experiments

The present study is designed to investigate social influence in car-sharing decisions under uncertainty. Social influence indicates that individuals’ decisions are influenced by the choices made by members of their social networks. An individual may experience different degrees of influence depending on social distance, i.e. the strength of the social relationship between individuals. Such heterogeneity in social influence has been largely ignored in the previous travel behavior research. The data used in this study stems from an egocentric social network survey, which measures the strength of the social relationships of each respondent. In addition, a sequential stated adaptation experiment was developed to capture more explicitly the effect of social network choices on the individual decision-making process. Social distance is regarded as a random latent variable. The estimated social distance and social network choices are incorporated into a social influence variable, which is treated as an explanatory variable in the car-sharing decision model. To simultaneously estimate latent social distance and the effects of social influence on the car-sharing decision, we expand the hybrid choice framework to incorporate the latent social distance model into discrete choice analysis. The estimation results show substantial social influence in car-sharing decisions. The magnitude of social influence varies according to the type of relationship, similarity of socio-demographics and the number of social interactions.     

Would personal carbon trading reduce travel emissions more effectively than a carbon tax?

The application of personal carbon trading (PCT) to transport choices has recently been considered in the literature as a means of reducing CO₂ emissions. Its potential effectiveness in changing car travel behavior is compared to the conventional carbon tax (CT) by means of a stated preferences survey conducted among French drivers (N ∼ 300). We show evidence that PCT could effectively change travel behavior and hence reduce transport emissions from personal travel. There is however a definite reluctance to reduce car travel. We were unable to demonstrate any significant difference between the effectiveness of PCT and the CT with regard to changing travel behavior. However, in the experiment, the PCT scheme provided consistent results while this was not the case for the CT scheme. Further research is needed into the “social norm” conveyed by a personal emissions allowance.     

Modeling the charging and route choice behavior of BEV drivers

Due to the limited cruising range of battery electric vehicle (BEV), BEV drivers show obvious difference in travel behavior from gasoline vehicle (GV) drivers. To analyze BEV drivers’ charging and route choice behaviors, and extract the differences between BEV and GV drivers’ travel behavior, two multinomial logit-based and two nested logit-based models are proposed in this study based on a stated preference survey. The nested structure consists of two levels: the upper level represents the charging decision, and the lower level shows the route choices corresponding to the charging and no-charging situations respectively. The estimated results demonstrate that the nested structure is more appropriate than the multinomial structure. Meanwhile, it is observed that the initial state of charge (SOC) at origin of BEV is the most important factor that affects the decision of charging or not, and the SOC at destination becomes an important impact factor affecting BEV drivers’ route choice behavior. As for the route choice behavior when BEV has charging demand, the charging station attributes such as charging time and charging station’s location have significant influences on BEV drivers’ decision-making process. The results also show that BEV drivers incline to choose the routes with charging station having less charging time, being closer to origin and consistent with travel direction. Finally, based on the proposed models, a series of numerical analysis has been conducted to verify the effect of range anxiety on BEV charging and route choice behavior and to reveal the variation of comfortable initial SOC at origin with travel distance. Meanwhile, the effects of charging time and distance from origin to charging station also have been discussed.     

Modelling the dynamics of bus use in a changing travel environment using panel data

Panel data offers the potential to represent the influence on travel choices of changing circumstances, past history and persistent individual differences (unobserved heterogeneity). A four-wave panel survey collected data on the travel choices of residents before and after the introduction of a new bus rapid transit service. The data shows gradual changes to bus use over the four waves, implying time was required for residents to become aware of the new service and to adapt to it. Ordered response models are estimated for bus use over the survey period. The results show that the influence of level of service (LOS) is underestimated if unobserved heterogeneity is not taken into account. The delayed response to the new service is able to be well represented by including LOS as a lagged variable. Current bus use is found to be conditioned on past bus use, but with additional influence of lagged LOS and unobserved heterogeneity. It is shown how different model specifications generate different evolution patterns with the most realistic predictions arising from a model which takes into account lagged responses to change in LOS and unobserved heterogeneity. The paper demonstrates the feasibility of developing panel data models that can be applied to forecasting the effect of interventions in the travel environment. Longer panels—encompassing periods of both stability and change—are required to support future efforts at modelling travel choice dynamics.