Topic Evolution Analysis for Social Robots Based on Latent Dirichlet Allocation

ABSTRACT

With the rapid growth of the robotics market, social robots have garnered increasing global attention. Investigating service innovation within the domain of social robots enables a better understanding of the field's developmental trajectory and emerging trends. Such insights can support enterprises and researchers in the development of innovative technologies and related applications. This study collected a total of 1406 abstracts related to social robots published over the past 15 years from the Web of Science journal database, which served as the primary research corpus. The thematic evolution of social robots was analysed from two perspectives: the evolution of thematic intensity and the evolution of thematic content. The findings are as follows: (1) In the early stages, research was predominantly focused on system technologies. As these technologies matured, they facilitated the diversification of research topics, leading to a relative decline in system technology research and a corresponding rise in studies from other domains. (2) The development of social robots has primarily followed three main trajectories: system technologies, research concerning children and research concerning the elderly. Subtopics such as healthcare, companionship, education, interaction and innovative applications in commercial services have evolved independently while also aligning with these major trajectories, resulting in a diversified research landscape.