Adrian B. Ellison

Driver behaviour profiles for road safety analysis

Driver behaviour is a contributing factor in over 90 percent of road crashes. As a consequence, there is significant benefit in identifying drivers who engage in unsafe driving practices. Driver behaviour profiles (DBPs) are introduced here as an approach for evaluating driver behaviour as a function of the risk of a casualty crash. They employ data collected using global positioning system (GPS) devices, supplemented with spatiotemporal information. These profiles are comprised of common risk scores that can be used to compare drivers between each other and across time and space. The paper details the development of these DBPs and demonstrates their use as an input into modelling the factors that influence driver behaviour. The results show that even having controlled for the influence of the road environment, these factors remain the strongest predictors of driver behaviour suggesting different spatiotemporal environments elicit a variety of psychological responses in drivers. The approach and outcomes will be of interest to insurance companies in enhancing the risk-profiling of drivers with on-road driving and government through assessing the impacts of behaviour-change interventions.

Evaluating changes in driver behaviour: A risk profiling approach

New road safety strategies continue to be devised by researchers and policy makers with pay-as-you-drive (PAYD) schemes gaining increasing attention. However, empirically measuring the effectiveness of these strategies is challenging due to the influence of the road environment and other factors external to the driver. The analysis presented here applies Temporal and Spatial Identifiers to control for the road environment and Driver Behaviour Profiles to provide a common measure of driving behaviour based on the risk of a casualty crash for assessing the effectiveness of a PAYD scheme on reducing driving risks. The results show that in many cases personalised feedback alone is sufficient to induce significant changes, but the largest reductions in risk are observed when drivers are also awarded a financial incentive to change behaviour. Importantly, the more frequent the exposure to the speeding information, the greater the magnitude of the change. However, the changes are disproportionately associated with those that were already safer drivers in the baseline period suggesting that some drivers may be predisposed to changing their behaviour. These results suggest that it would be beneficial to provide real-time or daily feedback on speeding behaviour in conjunction with a financial reward scheme, potentially as a component of insurance premiums.

Analysis of Speeding Behavior: Multilevel Modeling Approach

Data collected from Global Positioning System technology are used to examine the variability in speeding for 147 motorists during a 5-week period. A multilevel modeling approach is used to decompose speeding behavior into four major levels of variation: interindividual variation, temporal variation, trip-level variation, and segment-level variation. Initially, a null model (i.e., excludes the explanatory variables) is estimated to assess the variations at each level. Results suggest that the driver is more a factor in speeding as the speed limit increases but that the majority of variation in speeding goes unexplained. This finding is followed by progressively including explanatory variables (e.g., age, gender, vehicle type, trips, and purpose) at each of the four levels to assess how much more of the variation in speeding can be explained. Results suggest that the reduction in unexplained variance in speeding varies markedly by speed zone and that difference indicates the disproportionately different impacts of explanatory factors.

Building Business Resilience with Social Media in B2B Environments: The Emergence of Responsive Customer Relationship Management Processes on Twitter

Companies operating in the business-to-consumer (B2C) space have been increasingly using the social media platform, Twitter, to conduct customer relationship management activities. Similar practices are also gradually emerging in business-to-business (B2B) environments. However, B2B service providers are yet to incorporate social media into their overall business strategy to the extent that this has become common practice amongst B2C companies. Engaging with customers over social media poses both risks and opportunities for companies. This paper examines the customer relationship management activities of a B2B service provider, Shopify, to identify opportunities for improving brand perception and business resilience.

Creation of unstructured big data from customer service: The case of parcel shipping companies on Twitter

Customer service provision is a growing phenomenon on social media and parcel shipping companies have been among the most prominent adopters. This has coincided with greater interest in the development of analysis techniques for unstructured big data from social media platforms, such as the micro-blogging platform, Twitter. Given the growing use of dedicated customer service accounts on Twitter, the purpose of this paper is to investigate the effectiveness with which parcel shipping companies use the platform.,This paper demonstrates the use of a combination of tools for retrieving, processing and analysing large volumes of customer service-related conversations generated between parcel shipping companies and their customers in Australia, UK and the USA. Extant studies using data from Twitter tend to focus on the contributions of individual entities and are unable to capture the insights provided by a holistic examination of the interactions.,This study identifies the key issues that trigger customer contact with parcel shipping companies on Twitter. It identifies similarities and differences in the approaches that these companies bring to customer engagement and identifies the opportunities for using the medium more effectively.,The development of consumer-centric supply chains and relevant theories require researchers and practitioners to have the ability to include insights from growing quantities of unstructured data gathered from consumer engagement. This study makes a methodological contribution by demonstrating the use of a set of tools to gather insight from a large volume of conversations on a social media platform.