A Decade of In-text Citation Analysis based on Natural Language\n Processing and Machine Learning Techniques: An overview of empirical studies

Citation analysis is one of the most frequently used methods in research\nevaluation. We are seeing significant growth in citation analysis through\nbibliometric metadata, primarily due to the availability of citation databases\nsuch as the Web of Science, Scopus, Google Scholar, Microsoft Academic, and\nDimensions. Due to better access to full-text publication corpora in recent\nyears, information scientists have gone far beyond traditional bibliometrics by\ntapping into advancements in full-text data processing techniques to measure\nthe impact of scientific publications in contextual terms. This has led to\ntechnical developments in citation context and content analysis, citation\nclassifications, citation sentiment analysis, citation summarisation, and\ncitation-based recommendation. This article aims to narratively review the\nstudies on these developments. Its primary focus is on publications that have\nused natural language processing and machine learning techniques to analyse\ncitations.\n