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.     

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.     

Locating new passenger facilities on a transportation network

This paper examines the problem of locating additional passenger facilities on a transportation network to supplement ones that already exist. A distinction is made between “supporting” facilities which operate only in concert with already existing ones and “new” facilities which are self-sufficient and operate independently. It is shown that, when the objective is to maximize the utility of travel times to all users, at least one set of optimal locations for the new facilities exist on the nodes of the network if the utility function for travel times is convex. This result is proven under very general conditions including the assumption of a probabilistic transportation network, i.e. a network where travel times on network branches are random variables. A straightforward algorithm for solving a specific simple case is also provided and the results are illustrated by examples.     

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.     

Towards modal choice decision-making models: A case study of Lagos state transport corporation bus riders

Identification of the socioeconomic factors which affect the demand for buses, and the analysis of the use of the other transport modes by bus users are the two main objectives of this article. Work and school trips are highlighted as being very important trip purposes in Lagos metropolis by the multiple discriminant analysis model. It identifies mode of transport, distance, travel time, reliability, and the number of stops as significant mode choice variables. Multiple linear regression models for work and school trips identify mode of transport, transfort fare, travel time, annual income, and crew behaviour as significant variables in the choice of transport mode. These findings support the two alternative hypotheses of the study that the choice of bus is related to the individual perception of the quality of service of the different modes and that socioeconomic characteristics of the riders influence the patronage of buses. The attention of policy makers for the 22 transport corporations that operate inter-and intra-urban services in all the 21 states and the federal capital of Abuja in Nigeria is drawn to the importance of these variables for decisions.     

Modelling contact mode and frequency of interactions with social network members using the multiple discrete–continuous extreme value model

Communication patterns are an integral component of activity patterns and the travel induced by these activities. The present study aims to understand the determinants of the communication patterns (by the modes face-to-face, phone, e-mail and SMS) between people and their social network members. The aim is for this to eventually provide further insights into travel behaviour for social and leisure purposes. A social network perspective brings value to the study and modelling of activity patterns since leisure activities are influenced not only by traditional trip measures such as time and cost but also motivated extensively by the people involved in the activity. By using a multiple discrete-continuous extreme value model (Bhat, 2005), we can investigate the means of communication chosen to interact with a given social network member (multiple discrete choices) and the frequency of interaction by each mode (treated as continuous) at the same time. The model also allows us to investigate satiation effects for different modes of communication. Our findings show that in spite of people having increasingly geographically widespread networks and more diverse communication technologies, a strong underlying preference for face-to-face contact remains. In contrast with some of the existing work, we show that travel-related variables at the ego level are less important than specific social determinants which can be considered while making use of social network data.     

Modelling the relationship between travel behaviours and social disadvantage

The purpose of this paper is to model the travel behaviour of socially disadvantaged population segments in the United Kingdom (UK) using the data from the UK National Travel Survey 2002–2010. This was achieved by introducing additional socioeconomic variables into a standard national-level trip end model (TEM) and using purpose-based analysis of the travel behaviours of certain key socially disadvantaged groups. Specifically the paper aims to explore how far the economic and social disadvantages of these individuals can be used to explain the inequalities in their travel behaviours.The models demonstrated important differences in travel behaviours according to household income, presence of children in the household, possession of a driver’s licence and belonging to a vulnerable population group, such as being disabled, non-white or having single parent household status. In the case of household income, there was a non-linear relationship with trip frequency and a linear one with distance travelled. The recent economic austerity measures that have been introduced in the UK and many other European countries have led to major cutbacks in public subsidies for socially necessary transport services, making results such as these increasingly important for transport policy decision-making. The results indicate that the inclusion of additional socioeconomic variables is useful for identifying significant differences in the trip patterns and distances travelled by low-income.     

Park-and-ride lot choice model using random utility maximization and random regret minimization

This research aims to understand the park-and-ride (PNR) lot choice behaviour of users i.e., why PNR user choose one PNR lot versus another. Multinomial logit models are developed, the first based on the random utility maximization (RUM) concept where users are assumed to choose alternatives that have maximum utility, and the second based on the random regret minimization (RRM) concept where users are assumed to make decisions such that they minimize the regret in comparison to other foregone alternatives. A PNR trip is completed in two networks, the auto network and the transit network. The travel time of users for both the auto network and the transit network are used to create variables in the model. For the auto network, travel time is obtained using information from the strategic transport network using EMME/4 software, whereas travel time for the transit network is calculated using Google’s general transit feed specification data using a backward time-dependent shortest path algorithm. The involvement of two different networks in a PNR trip causes a trade-off relation within the PNR lot choice mechanism, and it is anticipated that an RRM model that captures this compromise effect may outperform typical RUM models. We use two forms of RRM models; the classical RRM and µRRM. Our results not only confirm a decade-old understanding that the RRM model may be an alternative concept to model transport choices, but also strengthen this understanding by exploring differences between two models in terms of model fit and out-of-sample predictive abilities. Further, our work is one of the few that estimates an RRM model on revealed preference data.

     

Estimating metro passengers’ path choices by combining self-reported revealed preference and smart card data

With the help of automated fare collection systems in the metro network, more and more smart card (SC) data has been widely accumulated, which includes abundant information (i.e., Big Data). However, its inability to record passengers’ transfer information and factors affecting passengers’ travel behaviors (e.g., socio-demographics) limits further potential applications. In contrast, self-reported Revealed Preference (RP) data can be collected via questionnaire surveys to include those factors; however, its sample size is usually very small in comparison to SC data. The purpose of this study is to propose a new set of approaches of estimating metro passengers’ path choices by combining self-reported RP and SC data. These approaches have the following attractive features. The most important feature is to jointly estimate these two data sets based on a nested model structure with a balance parameter by accommodating different scales of the two data sets. The second feature is that a path choice model is built to incorporate stochastic travel time budget and latent individual risk-averse attitude toward travel time variations, where the former is derived from the latter and the latter is further represented based on a latent variable model with observed individual socio-demographics. The third feature is that an algorithm of combining the two types of data is developed by integrating an Expectation-Maximization algorithm and a nested logit model estimation method. The above-proposed approaches are examined based on data from Guangzhou Metro, China. The results show the superiority of combined data over single data source in terms of both estimation and forecasting performance.     

Travel-based multitasking: review of the role of digital activities and connectivity

ABSTRACT

Travel-based multitasking, also referred to as travel time use, is now a well-established concept, whose existence is supported by the technological trajectories, with mobile information and communication technologies (ICT) and vehicle automation working together to allow travel time to be more productive and enjoyable. Despite existence of reviews of travel-time multitasking studies, the systematic overview of the role digital activities, i.e. those that necessarily require modern ICT equipment to participate, has been limited, often wrapped under the umbrella term “use of ICT”, potentially obscuring their complexity and sophistication. Similarly, the role of connectivity and its attributes, e.g. speed (bandwidth), reliability, price, ease of use, data allowance or security, deserves a more systematic overview given its key role in enabling digital online activities and hence the travel-based multitasking options. This paper provides a review of 77 empirical travel-based multitasking-studies that explored the role of digital activities or connectivity. In particular, the review discusses the existing typologies of digital activities, dividing them into hardware-centric, function-centric or a combination of both (mixed). Subsequently, key contributions are discussed with respect to the treatment of digital activities and connectivity and its attributes. Based on the review, it is possible to observe that the existing studies have looked only at a handful of rather restricted online activities that do not sufficiently capture the sophistication with which individuals interact with the virtual world nowadays. Furthermore, the role of connectivity, although deeply embedded in the “C” of the “ICT” concept, has not been looked at or modelled in any detail in studies related to travel time use or its quality. This existing shortcoming might have resulted in an insufficient understanding of the mechanisms driving travel time use, the associated experience indicators of customer satisfaction, productivity or the consequences for relative attractiveness of transport modes. All of these considerations remain, however, crucial for designing, appraising and operating transport infrastructure and services that are able to take the advantage of lifestyle digitisation to meet the increasing customer needs while also delivering broader economic, social benefits and possibly also environmental benefits.     

A mixed Bayesian network for two-dimensional decision modeling of departure time and mode choice

The modeling of travel decision making has been a popular topic in transportation planning. Previous studies focused on random-utility discrete choice models and machine learning methods. This paper proposes a new modeling approach that utilizes a mixed Bayesian network (BN) for travel decision inference. The authors use a predetermined BN structure and calculate priori and posterior probability distributions of the decision alternatives based on the observed explanatory variables. As a “utility-free” decision inference method, the BN model releases the linear structure in the utility function but assumes the traffic level of service variables follow multivariate Gaussian distribution conditional on the choice variable. A real-world case study is conducted by using the regional travel survey data for a two-dimensional decision modeling of both departure time choice and travel mode choice. The results indicate that a two-dimensional mixed BN provides better accuracy than decision tree models and nested logit models. In addition, one can derive continuous elasticity with respect to each continuous explanatory variable for sensitivity analysis. This new approach addresses a research gap in probabilistic travel decision making modeling as well as two-dimensional travel decision modeling.     

Dynamic diurnal social taxonomy of urban environments using data from a geocoded time use activity-travel diary and point-based business establishment inventory

In this paper, we explore the diurnal dynamics of joint activity participation in a small city in Pennsylvania, USA, using behavioral data and an inventory of business establishments. We account for the variation caused by the collective impact of social, temporal and spatial choices of individuals to produce predicted space–time visualizations of activity participation. The focus is on how social contexts of an activity impact the temporal and spatial decisions regarding the activity locations and how this impact varies depending on activity types. A comparison across activity types and social interaction types is made among spatial patterns during a day. The CentreSIM dataset, which is a household-based activity diary survey collected in Centre County (Pennsylvania, USA) in 2003, provides very detailed social interaction information enabling the analysis of social, spatial and temporal aspects of activity participation. In this paper we use this information to develop a spatio-temporal interpolation method and demonstration based on kriging. In this way, we extract the dynamic social taxonomy of places from the behavioral information in the dataset and suggest how urban and transportation models can be informed from the dynamics of places by observing “what is taking place” (activities being pursued in the context of this paper) combined with “what exists” (business establishments) or “what is available” (businesses that are open). The method here can also be used to improve the design of urban environments (e.g., filling gaps in desired activity locations), manage specific places (e.g., extending the opening and closing times of businesses), study transportation policies that are sensitive to time of day (e.g., pricing of parking to discourage crowding and traffic congestion), and modeling of spatio-temporal decisions of social activities in travel demand models (e.g., to guide the development of model specification and representation of the space in which behavioral models are applied).     

Social influences on household location, mobility and activity choice in integrated micro-simulation models

Agent-based approaches to simulating long-term location and mobility decisions and short-term activity and travel decisions of households and individuals are receiving increasing attention in land-use and transportation interaction (LUTI) models to predict land-use changes and travel behaviour in mutual interaction. Social interactions between households and between individuals potentially have an influence on a wide range of the long-term and short-term choices involved in these systems. In this paper we identify the areas in which social interactions play a role and address the question how these influences can be modelled in the context of agent-based LUTI models. We distinguish impacts on activity participation (joint activity participation, support-and-help activities) and impacts on decision making (information exchange, social adaptation of preferences and aspirations) as the two main areas of social influence. A prototype of a LUTI model is proposed that accounts for impacts of the social network on longer-term mobility decision making through information exchange and social adaptation of preferences and aspirations. The model is demonstrated in a numerical simulation.     

An integrated Bayesian approach for passenger flow assignment in metro networks

This paper proposes an integrated Bayesian statistical inference framework to characterize passenger flow assignment model in a complex metro network. In doing so, we combine network cost attribute estimation and passenger route choice modeling using Bayesian inference. We build the posterior density by taking the likelihood of observing passenger travel times provided by smart card data and our prior knowledge about the studied metro network. Given the high-dimensional nature of parameters in this framework, we apply the variable-at-a-time Metropolis sampling algorithm to estimate the mean and Bayesian confidence interval for each parameter in turn. As a numerical example, this integrated approach is applied on the metro network in Singapore. Our result shows that link travel time exhibits a considerable coefficient of variation about 0.17, suggesting that travel time reliability is of high importance to metro operation. The estimation of route choice parameters conforms with previous survey-based studies, showing that the disutility of transfer time is about twice of that of in-vehicle travel time in Singapore metro system.     

Exploring the links between personal networks, time use, and the spatial distribution of social contacts

Although the study of the role of the social context in travel behavior and activity patterns has recently gained attention, the empirical evidence supporting the relationship between social networks and the temporal and spatial characteristics of social activities is still limited. With this motivation, this paper studies the link between “longer term” (social networks) and “shorter term” (social activities) social decisions, by exploring the intertwined relationship between the individuals’ personal networks attributes, and the spatiotemporal characteristics of their daily social activities. The paper contributes to the literature by adding two key aspects to the study of the role of social networks on travel behavior: the social networks’ structure, and the spatiality of all individuals participating on the social activities. Based on data which link people’s personal networks and time use, and using a structural equation modeling approach, the paper studies the influence of individual and interactional attributes on the duration, distance, and number of people involved in social daily activities. The results show that aspects such as tie social closeness, gender and age similarity, and network density, help to understand social activity duration and distance, complementing traditional socio-demographic aspects such as income, occupation, and accessibility to services. In this way, socio-demographic attributes are not enough to explain the spatiotemporal dimension of daily activities which makes necessary to include variables related to the social context to explain with a higher level of accuracy both the duration and distance traveled to the activity.     

Tour-based mode choice of joint household travel patterns on weekend and weekday

Joint household travel, with or without joint participation in an activity, constitutes a fundamental aspect in modelling activity-based travel behaviour. This paper examines joint household travel arrangements and mode choices using a utility maximising approach. An individual tour-based mode choice model is formulated contingent on the choice of joint tour patterns where joint household activities and shared ride arrangements are recognised as part of the joint household decision-making that influences the travel modes of each household member. Two models, one for weekend and one for weekday, are estimated using empirical data from the Sydney Household Travel Survey. The results show that weekend travel is characterised by a high joint household activity participation rate while weekday travel is distinguished by more intra-household shared ride arrangements. The arrangements of joint household travel are highly associated with travel purpose, social and mobility constraints and household resources. On weekends, public transport is mainly used by captive users (i.e., no-car households and students) and its share is about half of that on weekdays. Also, the value of travel time savings (VOTs) are found to be higher on weekends than on weekdays, running entirely counter to the common belief that weekend VOTs are lower than weekday VOTs. This paper highlights the importance of studying joint household travel and using different transport management measures for alleviating traffic congestion on weekdays and weekends.     

Dynamic process model of mass effects on travel demand

Whereas transportation planners commonly predict the negative impacts of mass transportation, there is increasing empirical evidence of the existence of positive mass effects, whereby increased use of a mode by the ‘mass’ will generally increase its attractiveness for future travellers. In this paper we consider the dynamic impact of such an effect on the problem of travel demand forecasting, with particular regards to social network effects. Our proposed modelling approach is inspired by literature from social physics, evolutionary game theory and marketing. For simplicity of exposition, our model is specified for a scenario in which (a) there is a binary choice between two mobility lifestyles, referred to as car-oriented and transit-oriented, and (b) there are two population groups, where one is the “leading” or “innovative” population group and the other the “following” or “imitating” population group. This latter distinction follows the rather well-known Bass model from the marketing literature (1969). We develop the transition probabilities and transition dynamics. We illustrate with a numerical case study that despite lower intrinsic utility for the transit lifestyle, significant changes towards this lifestyle can be achieved by considering congestion, service improvements and mass effects. We further illustrate that mass effects can be positive or negative. In all cases we explore the sensitivity of our conclusions to the assumed parameter values.     

Barriers to Passenger Rail Use: A Review of the Evidence

Research has shown that even when rail travel is the most cost-effective mode of transport for a particular journey, many travellers will still choose other modes. This indicates the existence of non-financial barriers to rail use, and this paper reviews the evidence on the importance of such barriers, focusing particularly on the UK but also considering research from other countries. A total of 37 distinct barriers were identified, and these can be divided into “hard”, “soft” and “complementary” factors. Travellers are unlikely to consider these barriers individually, viewing them instead as a package, which can make it difficult to identify which barriers are most significant. In many cases, all barriers which exist for a particular traveller will need to be addressed before mode shift occurs. After considering the relative importance of the different barriers, the paper concludes by making some suggestions as to the most effective ways in which these barriers can be overcome and mode shift to rail achieved. This has key implications for transport policy, as it can inform the targeting of the limited funds available to influence travel behaviour and increase the sustainability of travel patterns.     

A discrete choice framework for modeling and forecasting the adoption and diffusion of new transportation services

Major technological and infrastructural changes over the next decades, such as the introduction of autonomous vehicles, implementation of mileage-based fees, carsharing and ridesharing are expected to have a profound impact on lifestyles and travel behavior. Current travel demand models are unable to predict long-range trends in travel behavior as they do not entail a mechanism that projects membership and market share of new modes of transport (Uber, Lyft, etc.). We propose integrating discrete choice and technology adoption models to address the aforementioned issue. In order to do so, we build on the formulation of discrete mixture models and specifically Latent Class Choice Models (LCCMs), which were integrated with a network effect model. The network effect model quantifies the impact of the spatial/network effect of the new technology on the utility of adoption. We adopted a confirmatory approach to estimating our dynamic LCCM based on findings from the technology diffusion literature that focus on defining two distinct types of adopters: innovator/early adopters and imitators. LCCMs allow for heterogeneity in the utility of adoption for the various market segments i.e. innovators/early adopters, imitators and non-adopters. We make use of revealed preference (RP) time series data from a one-way carsharing system in a major city in the United States to estimate model parameters. The data entails a complete set of member enrollment for the carsharing service for a time period of 2.5 years after being launched. Consistent with the technology diffusion literature, our model identifies three latent classes whose utility of adoption have a well-defined set of preferences that are significant and behaviorally consistent. The technology adoption model predicts the probability that a certain individual will adopt the service at a certain time period, and is explained by social influences, network effect, socio-demographics and level-of-service attributes. Finally, the model was calibrated and then used to forecast adoption of the carsharing system for potential investment strategy scenarios. A couple of takeaways from the adoption forecasts were: (1) placing a new station/pod for the carsharing system outside a major technology firm induces the highest expected increase in the monthly number of adopters; and (2) no significant difference in the expected number of monthly adopters for the downtown region will exist between having a station or on-street parking.