Understanding the domain of driving distraction with knowledge graphs

Abstract

This paper aims to provide insight into the driving distraction domain systematically on the basis of scientific knowledge graphs. For this purpose, 3,790 documents were taken into consideration after retrieving from Web of Science Core Collection and screening, and two types of knowledge graphs were constructed to demonstrate bibliometric information and domain-specific research content respectively. In terms of bibliometric analysis, the evolution of publication and citation numbers reveals the accelerated development of this domain, and trends of multidisciplinary and global participation could be identified according to knowledge graphs from Vosviewer. In terms of research content analysis, a new framework consisting of five dimensions was clarified, including “objective factors”, “human factors”, “research methods”, “data” and “data science”. The main entities of this domain were identified and relations between entities were extracted using Natural Language Processing methods with Python 3.9. In addition to the knowledge graph composed of all the keywords and relationships, entities and relations under each dimension were visualized, and relations between relevant dimensions were demonstrated in the form of heat maps. Furthermore, the trend and significance of driving distraction research were discussed, and special attention was given to future directions of this domain.

A Bibliometric Analysis of Recent Developments and Trends in Knowledge Graph Research (2013–2022)

“…During a given research span, the nodes of the keywords map were marked with different colors accordingly. For instance, the keywords with dark green indicate the earlier occurrence [36], while the keywords with light yellow mean the later occurrence. The observed publications in the past three years have focused on the following terms, such as "graph neural network" (avg.…”