Extraction of travellers’ preferences using their tweets

Abstract

New mapping and location service applications have focused on offering improved usability and service based on multimodal passenger experiences from door to door. This helps citizens to develop greater confidence in and adherence to multimodal transport services. These applications focus on adapting to the needs of users during their journeys thanks to the data, statistics and trends provided by the passenger experiences while using these platforms. The My-Trac application is dedicated to the research and development of these user-centred services to improve the multimodal experience using various techniques. Among these techniques are preference extraction systems, which extract user information from social networks such as twitter. In this article we present a system that allows the creation of a profile of preferences of a certain user based on the tweets published in his Twitter account. The system extracts the tweets from the profile and analyzes them using the proposed algorithms and returns them as a result in a document containing the categories and the degree of affinity that the user maintains with each one. In this way the user can be offered activities or services during the route to be taken with a high degree of affinity.