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.     

Time use in travel surveys and time use surveys – Two sides of the same coin?

An in-depth understanding of travel behaviour determinants, including the relationship to non-travel activities, is the foundation for modelling and policy making. National Travel Surveys (NTS) and time use surveys (TUS) are two major data sources for travel behaviour and activity participation. The aim of this paper is to systematically compare both survey types regarding travel activities and non-travel activities. The analyses are based on the German National Travel Survey and the German National Time Use Survey from 2002.The number of trips and daily travel time for mobile respondents were computed as the main travel estimates. The number of trips per person is higher in the German TUS when changes in location without a trip are included. Location changes without a trip are consecutive non-trip activities with different locations but without a trip in-between. The daily travel time is consistently higher in the German TUS. The main reason for this difference is the 10-min interval used. Differences in travel estimates between the German TUS and NTS result from several interaction effects. Activity time in NTS is comparable with TUS for subsistence activities.Our analyses confirm that both survey types have advantages and disadvantages. TUS provide reliable travel estimates. The number of trips even seems preferable to NTS if missed trips are properly identified and considered. Daily travel times are somewhat exaggerated due to the 10-min interval. The fixed time interval is the most important limitation of TUS data. The result is that trip times in TUS do not represent actual trip times very well and should be treated with caution.We can use NTS activity data for subsistence activities between the first trip and the last trip. This can potentially benefit activity-based approaches since most activities before the first trip and after the last trip are typical home-based activities which are rarely substituted by out-of-home activities.     

The design of environmentally aware travel diaries

Any policy addressing the concerns and trends associated with the impact of travel on the environment should be based on a solid understanding of the activities giving rise to them. While the measurement of the total environment loads by air or noise measurement stations is essential, it needs to be matched by the observation of the human behaviours creating them. This is especially true in the transport sector, which has been rightly or wrongly identified as having the potential to make a substantial contribution to the reduction of air and noise pollution. While the contribution of freight transport is of growing concern and importance, this paper focuses on the measurement of passenger transport throughout.

In the past transport planners have largely relied on the travel diary as their prime instrument to measure traveller behaviour. The travel diary is a survey instrument designed to record all movements during the course of one or more days including their relevant details. It is complemented by spearate household and personal forms for recording general information. In the following paper the term travel diary implies all three elements (the diary, the person form and the household form).

The remainder of the paper discusses to what extent and how the travel diary can be used to capture data for the assessment of policies directed at reducing the impact of transport on the social and natural environment. The requirements of a travel diary and the potential uses of new technologies in realising such a travel diary are then presented. A brief outlook on the possibilities of reasling such a diary concludes the paper.     

Should we abandon activity type analysis? Redefining activities by their salient attributes

This paper poses a challenge and begins a search. The challenge is to reconsider the usefulness of traditional activity types (“work”, “shopping”, etc.) in the understanding and modelling of travel behaviour. The search is for the more salient attributes of activities that may serve to better explain complex travel behaviours—such as activity scheduling and tour formation. In particular, this paper focuses on explicit measures of the spatial, temporal and interpersonal flexibility of activities, along with several traditional attributes (frequency, duration, involved persons, travel time, and location). Data from a recent in-depth week-long activity scheduling survey was used to define and compare these attributes. Results show that considerable variability in the attributes between and within traditional activity groups is evident. This casts considerable uncertainty on assumptions that statically assign levels of spatial, temporal, and interpersonal flexibility to any given activity type. A Principal Components Analysis further revealed eight new distinct clusters of activities that share like attributes. The relative role of each attribute in each component is examined, and subjective interpretations emerged (e.g., “Long and frequent”, “Space and time flexible” “Social networking”). The implications of these results for future model development and research are discussed. Future research should continue to expand the search for salient attributes and link them more directly to decision processes.     

Exploring the role of social capital influence variables on travel behaviour

This paper explores the potential role of individual trip characteristics and social capital network variables in the choice of transport mode. A sample of around 100 individuals living or working in one suburb of Madrid (i.e. Las Rosas district of Madrid) participated in a smartphone short panel survey, entering travel data for an entire working week. A Mixed Logit model was estimated with this data to analyze shifts to metro as a consequence of the opening of two new stations in the area. Apart from classical explanatory variables, such as travel time and cost, gender, license and car ownership, the model incorporated two “social capital network” variables: participation in voluntary activities and receiving help for various tasks (i.e. child care, housekeeping, etc.). Both variables improved the capacity of the model to explain transport mode shifts. Further, our results confirm that the shift towards metro was higher in the case of people “helped” and lower for those participating in some voluntary activities.     

Investigation and analysis of evidence of asymmetric churn in travel demand models

There is a large amount of research work that has been devoted to the understanding of travel behaviour and for the prediction of travel demand and its management. Different types of data including stated preference and revealed preference, as well as different modelling approaches have been used to predict this. Essential to most travel demand forecasting models are the concepts of utility maximisation and equilibrium, although there have been alternative approaches for modelling travel behaviour. In this paper, the concept of asymmetric churn is discussed. That is travel behaviour should be considered as a two way process which changes over time. For example over time some travellers change their mode of travel from car to bus, but more travellers change their mode from bus to car. These changes are not equal and result in a net change in aggregate travel behaviour. Transport planners often aim at producing this effect in the opposite direction. It is important therefore to recognise the existence of churns in travel behaviour and to attempt to develop appropriate policies to target different groups of travellers with the relevant transport policies in order to improve the transport system. A data set collected from a recent large survey, which was carried out in Edinburgh is investigated to analyse the variations in departure time choice behaviour. The paper reports on the results of the investigation.     

Transport and society1

In 1963, the Buchanan Report in the UK advocated a combination of new road capacity, improved public transport and traffic restraint as a means to tackle congestion. Forty years on, and the advice from many transport experts remains the same. However, the scale and complexity of the problems associated with a mobility‐dependent society have grown. The need for politicians to make tough but realistic policy decisions on transport is now becoming unavoidable. They must confront the realities of living with the car as must the general public. Policymakers now also have social well‐being and sustainable development moving higher on their agendas alongside transport. Against such a backdrop, the paper makes the case for transport research, policy and practice to acknowledge more fully the inherent links between transport and society. It argues that greater recognition and understanding of such links is crucial to confronting the present realities. Transport does not merely serve society: it shapes society, as in turn society shapes transport. The future of each is dependent on the other, and this fact must be recognized. The paper advocates in turn that the transport profession must move from its heartlands in engineering and economics also to embrace more fully such disciplines as sociology and psychology. A factual picture of the many facets of present‐day society is presented and the implications for travel demand are discussed. Through considering phenomena such as social norms and habitual behaviour, it is then argued that the travel choices and behaviour of individuals are not simply a matter of economic optimization. This points to the need for decision‐makers to be furnished with better evidence about the transport problems faced and the potential efficacy of measures that might be taken. Discussion of public attitudes and the role of the media are included in the context of assessing how politicians can be encouraged and supported in their implementation of realistic but unpopular policies. Evidence and experience within the paper are UK based, although many of the issues and arguments apply world wide.     

Sociological perspectives on travel and mobilities: A review

There is increasing interest in understanding and achieving changes in travel behaviour, but a focus on individual behaviour change may overlook the potential for achieving change via transformation at the levels of institutions, cultures and societies – the domains of sociological inquiry. In this paper, we review sociological contributions to the literature on travel and ‘mobilities’. We summarise four key themes which supplement or contradict arguments made in mainstream transport debates on behaviour change. The first involves focusing on travel ‘practices’ as social entities with dynamics of their own, rather than on individual behaviours. The second relates to the changing natures of societies, and the implications for travel. The third explores and interprets the issue of car dependence in ways which highlight the ethical, experiential and emotional dimensions associated with car use, its symbolic role in societies increasingly concerned with consumption, and its differing roles within different cultures. Finally, the ‘new mobilities paradigm’ highlights issues such as the increasing links between travel and new technologies, and the primacy of social networks in influencing travel decisions. These themes emphasise the importance of understanding the broader contexts in which travel choices are made. In particular, the implication is that the creation of more sustainable travel patterns will require changes at a range of social levels, not simply in individual behaviours, and that changes to transport will inevitably be linked with, and influenced by, broader changes in the values and practices developed by societies as a whole.     

Machine learning applications in activity-travel behaviour research: a review

ABSTRACT

This paper reviews the activity-travel behaviour literature that employs Machine Learning (ML) techniques for empirical analysis and modelling. Machine Learning algorithms, which attempt to build intelligence utilizing the availability of large amounts of data, have emerged as powerful tools in the fields of pattern recognition and big data analysis. These techniques have been applied in activity-travel behaviour studies since the early ’90s when Artificial Neural Networks (ANN) were employed to model mode choice decisions. AMOS, an activity-based modelling system developed in the mid-’90s, has ANN at its core to model and predict individual responses to travel demand management measures. In the dawn of 2000, ALBATROSS, a comprehensive activity-based travel demand modelling system, was proposed by Arentze and Timmermans using Decision Trees. Since then researchers have been exploring ML techniques like Support Vector Machines (SVM), Decision Trees (DT), Neural Networks (NN), Bayes Classifiers, and more recently, Ensemble Learners to model and predict activity-travel behaviour. A large number of publications over the years and an upward trend in the number of published articles over time indicate that Machine Learning is a promising tool for activity-travel behaviour analysis and prediction. This article, first of its kind in the literature, reviews these studies and explores the trends in activity-travel behaviour research that apply ML techniques. The review finds that mode choice decisions have received wide attention in the literature on ML applications. It was observed that most of the studies identify the lack of interpretability as a serious shortcoming in ML techniques. However, very few studies have attempted to improve the interpretability of the models. Further, some studies report the importance of feature engineering in ML-based studies, but very few studies adopt feature engineering before model development. Spatiotemporal transferability of models is another issue that has received minimal attention in the literature. In the end, the paper discusses possible directions for future research in the area of activity-travel behaviour modelling using ML techniques.     

Behavioural economics,travel behaviour and environmental-transport policy

The transport sector creates much environmental pressure. Many current policies aimed at reducing this pressure are not fully effective because the behavioural aspects of travellers are insufficiently recognised. Insights from behavioural economics can contribute to a better understanding of travel behaviour and choices, and the impact of these on policies. Nevertheless, few studies have examined this issue. We review these and provide a broader, more encompassing perspective on environmental policy focused on transport, and taking into account bounded rationality as well as social preferences.     

Estimation of a route choice model for urban public transport using smart card data

This paper describes a logit model of route choice for urban public transport and explains how the archived data from a smart card-based fare payment system can be used for the choice set generation and model estimation. It demonstrates the feasibility and simplicity of applying a trip-chaining method to infer passenger journeys from smart card transactions data. Not only origins and destinations of passenger journeys can be inferred but also the interchanges between the segments of a linked journey can be recognised. The attributes of the corresponding routes, such as in-vehicle travel time, transfer walking time and to get from alighting stop to trip destination, the need to change, and the time headway of the first transportation line, can be determined by the combination of smart card data with other data sources, such as a street map and timetable. The smart card data represent a large volume of revealed preference data that allows travellers' behaviour to be modelled with higher accuracy than by using traditional survey data. A multinomial route choice model is proposed and estimated by the maximum likelihood method, using urban public transport in ?ilina, the Slovak Republic, as a case study     

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.     

Towards a microeconomic framework for modelling the joint choice of activity–travel behaviour and ICT use

The rapid development of information and communication technologies (ICT) has been argued to affect time use patterns in a variety of ways, with consequent impacts on travel behaviour. While there exists a significant body of empirical studies documenting these effects, theoretical developments have lagged this empirical work and in particular, microeconomic time allocation models have not to date been fully extended to accommodate the implications of an increasingly digitised society. To address this gap, we present a modelling framework, grounded in time allocation theories and the goods–leisure framework, for joint modelling of the choice of mode of activity (physical versus tele-activity), travel mode and route, and ICT bundle. By providing the expression for a conditional indirect utility function, we use hypothetical scenarios to demonstrate how our framework can conceptualise various activity–travel decision situations. In our scenarios we assume a variety of situations such as the implications of severe weather, the introduction of autonomous vehicles, and the interaction between multiple decision makers. Moreover, our approach lays the microeconomic foundations for deriving subjective values of ICT qualities such as broadband speed or connection reliability. Finally, we also demonstrate the means by which our framework could be linked to various data collection protocols (stated preference exercises, diaries of social interactions, laboratory experiments) and modelling approaches (discrete choice modelling, hazard-based duration models).     

Does the income elasticity of road traffic depend on the source of income?

An extensive body of literature addresses the income elasticity of road traffic, in which income is typically treated as a homogenous quantity. Here we report evidence of heterogeneity in cross-sectional estimates of the elasticity of vehicle-kilometres of travel (VKT) with respect to income, when household income is disaggregated on the basis of income source.The results are generally intuitive, and show that the cross-sectional income elasticity of road traffic is not homogeneous as is typically specified in transport planning models. We show that in a number of circumstances the cross-sectional elasticity with respect to aggregate household income is of the opposite sign in comparison to more refined estimates of elasticity disaggregated by income source. If further research confirms that the elasticities we report here are causal in nature, neglecting the elemental effects could result in misleading results affecting practical infrastructure-investment and policy decisions, particularly as the mix of income sources shifts (e.g. if, as society ages, pension income increases as a share of all income).These results are of interest to both researchers and forecasters of travel demand, as well as designers of future travel survey instruments; the latter group must decide how to generate data about respondents’ income. Current expert guidance is to collect a single estimate of aggregate income at the household level. Future travel survey design choices will bound the analyses that can be supported by the resulting survey data, and therefore methodological research to re-visit the trade-offs associated with such choices is warranted.     

Applying behavioural theories to studying the influence of climate change on young people’s future travel intentions

Transport policy in the UK is seeking to promote the development of low carbon transport technology and to encourage people to choose to use low carbon travel options. This paper draws on existing behavioural theories to study young people’s travel behaviour intentions and the influence on these from their knowledge of, and willingness to act on, climate change. The study involved a series of focus groups with young people aged 11-18 years, where attitudes to transport modes, attitudes towards climate change and travel behaviour intentions were discussed. Knowledge and values are established as the key determinants of young people’s attitudes and behaviour intentions towards transport in the context of climate change. More specifically it is established that young people’s values emphasise speed and freedom and that it is important to young people that the mode of transport they choose is reflective of the image they want to portray.     

Identifying tourists and analyzing spatial patterns of their destinations from location-based social media data

Reliable travel behavior data is a prerequisite for transportation planning process. In large tourism dependent cities, tourists are the most dynamic population group whose size and travel choices remain unknown to planners. Traditional travel surveys generally observe resident travel behavior and rarely target tourists. Ubiquitous uses of social media platforms in smartphones have created a tremendous opportunity to gather digital traces of tourists at a large scale. In this paper, we present a framework on how to use location-based data from social media to gather and analyze travel behavior of tourists. We have collected data of about 67,000 users from Twitter using its search interface for Florida. We first propose several filtering steps to create a reliable sample from the collected Twitter data. An ensemble classification technique is proposed to classify tourists and residents from user coordinates. The accuracy of the proposed classifier has been compared against the state-of-the-art classification methods. Finally, different clustering methods have been used to find the spatial patterns of destination choices of tourists. Promising results have been found from the output clusters as they reveal most popular tourist spots as well as some of the emerging tourist attractions in Florida. Performance of the proposed clustering techniques has been assessed using internal clustering validation indices. We have analyzed temporal patterns of tourist and resident activities to validate the classification of the users in two separate groups of tourists and residents. Proposed filtering, identification, and clustering techniques will be significantly useful for building individual-level tourist travel demand models from social media data.     

Exploring transport carbon futures using population microsimulation and travel diaries: Beijing to 2030

Evaluating transport policy for cities in developing countries is often constrained by data availability that limits the use of conventional appraisal models. Here, we present a new ‘bottom-up’ methodology to estimate transport CO₂ emission from daily urban passenger travel for Beijing, a megacity with relatively sparse data on travel behaviour. A spatial microsimulation, based on an activity diary survey and two sample population censuses, is used to simulate, for Beijing’s urban districts, a realistic synthetic population, and their daily travel and CO₂ emission over 2000–2010. This approach provides greater insight into the spatial variability of transport CO₂ emission than has previously been possible for Beijing, and further, enables an examination of the role of socio-demographics, urban form and transport developments in contributing to emissions over the modelled period.Using the 2000–2010 CO₂ emission estimates as a baseline, CO₂ emissions from passenger travel are then modelled to 2030 under scenarios exploring politically plausible strategies on transport (public transport infrastructure investment, and vehicle constraint), urban development (compaction) and vehicle technology (faster adoption of clean vehicle technology). The results showed that, compared to the trend scenario, employing both transport and urban development policies could reduce total passenger CO₂ emission to 2030 by 24%, and by 43% if all strategies were applied together. The study reveals the potential of microsimulation in emission estimation for large cities in developing countries where data availability may constrain more traditional approaches.     

I can’t believe your attitude: a joint estimation of best worst attitudes and electric vehicle choice

The number of conventionally fuelled motor vehicles in use is increasing worldwide despite warnings about finite fossil fuel and the detrimental impacts of burning such fuels. While electric vehicles, the subject of much research, generate far less emissions and offer the potential for power from renewable sources, they are yet to significantly penetrate the market. Tangible barriers such as price and vehicle range still exist, but consumer attitudes also drive behaviour. This paper examines attributes in a framework relatively new to transportation and energy policy; best–worst scaling. This method is widely considered an improvement over traditional methods of eliciting attitudes and beliefs, where respondents select attitudes they find best or worst from a set of attitudinal statements. To avoid potential endogeneity bias, we jointly model attitudes and choice for the first time with best–worst data. It is found that energy crisis, air quality and climate change concerns influence behaviour with respect to vehicle range and that travel behaviour change and forms of government incentives are needed influences on behaviour with respect to vehicle emissions. It is argued that correctly modelling attitudes reduces the error term of the vehicle choice model and provides policy makers with an improved lens for assessing behaviour. Additionally, the methods described within can easily be adapted to other policy scenarios.