Towards automated analysis of research methods in library and information science

Abstract Previous studies of research methods in Library and Information Science (LIS) lack consensus how to define or classify methods, there have been no on automated recognition the scientific literature this field. This work begins fill these gaps by studying scope “research methods” LIS has evolved, challenges automatically identifying usage literature. We collected 2,599 articles from three journals. Using a combination content analysis text mining sample collection is coded into 29 different concepts then used test rule-based method for reported show that field characterized use an increasingly diverse range many which originate outside conventional boundaries LIS. implies increasing complexity methodology suggests need new approach towards classifying capture complex structure relationships between aspects methods. Our first its kind LIS, sets important reference future research.