Deep learning meets bibliometrics: A survey of citation function classification
Yang Zhang, Yufei Wang, Quan Z. Sheng, Lina Yao, Haihua Chen, Kai Wang, Adnan Mahmood, Wei Emma Zhang, Munazza Zaib, Subhash Sagar, Rongying Zhao
Abstract
With the advent and progression of Natural Language Processing (NLP) methodologies, the domain of automatic citation function classification has gained popularity and considerable research efforts have been contributed to this task. Automatic citation function classification has a joint computational linguistic and bibliometrics background. However, due to the different expertise in both fields, there is rarely a comprehensive and unified analysis of this task. We provide a detailed and nuanced examination analysis of the evolution of citation function classification task from the dimensions of citation function annotation schemes, widely employed benchmarks, and computational models. We first present the origins and the development of the citation function classification task. From the perspective of multi-disciplinary integration, we then discuss how bibliometrics and NLP can be better combined to contribute to the citation function classification task. Finally, based on the deficiencies that we have found in the task, we suggest some promising prospects in both bibliometrics and NLP to be investigated. • Reviews citation function classification in various dimensions. • Analyzes annotation schemes, datasets, and computational models. • Explores the synergy between bibliometrics and NLP. • Identifies challenges and suggests future research directions. • Among the first detailed analyses in this field.