The use of mobile devices to deliver traveler information such as situation awareness andnavigation guidance is on the rise. However, an optimal experience – and even morewidespread use – may be impeded by the lack of personalized, user-tailored applications. Theissue is that users react differently to traffic information, and information perceived useful byone user may be considered as nuisance by another. We provide evidence of this from a pilotfield test performed on a situation awareness application that alerts the user of approachingslow traffic 1.6 km ahead. We furthermore propose a machine learning algorithm based on asupport vector machine that segregates alerts into “favorable” vs. “nuisance” based on userfeedback and user GPS trace analysis. Our preliminary findings reveal that for 50% of usersparticipating in the experiment, 80% or more of the alerts perceived as nuisance could havebeen suppressed.
展开▼
