@misc{YuekselErguenLitzelPeng2024, author = {Yueksel-Erguen, Inci and Litzel, Ida and Peng, Hanqiu}, title = {Integrating Large Citation Datasets}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-98033}, year = {2024}, abstract = {This paper explores methods for building a comprehensive citation graph using big data techniques to evaluate scientific impact more accurately. Traditional citation metrics have limitations, and this work investigates merging large citation datasets to create a more accurate picture. Challenges of big data, like inconsistent data formats and lack of unique identifiers, are addressed through deduplication efforts, resulting in a streamlined and reliable merged dataset with over 119 million records and 1.4 billion citations. We demonstrate that merging large citation datasets builds a more accurate citation graph facilitating a more robust evaluation of scientific impact.}, language = {en} }