The purpose of this paper is to provide a better understanding of the reasons why people use or do not use carpooling. A further aim is to collect and analyze empirical evidence concerning the advantages and disadvantages of carpooling.
A large-scale text analytics study has been conducted: the collection of the peoples’ opinions have been realized on Twitter by means of a dedicated web crawler, named “Twitter4J.” After their mining, the collected data have been treated through a sentiment analysis realized by means of “SentiWordNet.”
The big data analysis identified the 12 most frequently used concepts about carpooling by Twitter’s users: seven advantages (economic efficiency, environmental efficiency, comfort, traffic, socialization, reliability, curiosity) and five disadvantages (lack of effectiveness, lack of flexibility, lack of privacy, danger, lack of trust).
Although the sample is particularly large (10 percent of the data flow published on Twitter from all over the world in about one year), the automated collection of people’s comments has prevented a more in-depth analysis of users’ thoughts and opinions.
The research findings may direct entrepreneurs, managers and policy makers to understand the variables to be leveraged and the actions to be taken to take advantage of the potential benefits that carpooling offers.
The work has utilized skills from three different areas, i.e., business management, computing science and statistics, which have been synergistically integrated for customizing, implementing and using two IT tools capable of automatically identifying, selecting, collecting, categorizing and analyzing people’s tweets about carpooling.
