Data Gathering and Preparation for Social Media Data Utilisation in Road and Traffic Safety

Abstract

Social media has altered the communications environment. Now people are more and more acquiring news and road safety as well as traffic related info from the internet, particularly the social media. Social media portals function as new sources of prolific observational data for studies based on opinions. Although the number of research works that deploy social data is increasing speedily, only a limited number of these works clearly describe their approaches for gathering and refining the data. Search filters as well as keywords used for social data constitute the basis on which researchers might see what and how individuals communicate regarding a specific subject. Such technologies are also beneficial for enabling them to externalise their individual experiences as well as views, and share them with other people. In this work, we come up with the generic process of how to gather social media data related to road safety and traffic concerns, utilisation and setup through direct scraping and Application Programming Interfaces (APIs). Furthermore, we deliberate the sampling technique and ethical concerns encompassed in data gathering through social media. The contribution of this work lies in dealing with the technical issues when it comes to mining social media information from the perspective of road safety and traffic, setting up the bases for more exploration in this domain.