@misc{10481/80532, year = {2022}, month = {12}, url = {https://hdl.handle.net/10481/80532}, abstract = {Wikipedia is one of the most visited websites in the world and is also a frequent subject of scientific research. However, the analytical possibilities of Wikipedia information have not yet been analyzed considering at the same time both a large volume of pages and attributes. The main objective of this work is to offer a methodological framework and an open knowledge graph for the informetric large-scale study of Wikipedia. Features of Wikipedia pages are compared with those of scientific publications to highlight the (dis)similarities between the two types of documents. Based on this comparison, different analytical possibilities that Wikipedia and its various data sources offer are explored, ultimately offering a set of metrics meant to study Wikipedia from different analytical dimensions. In parallel, a complete dedicated data set of the English Wikipedia was built (and shared) following a relational model. Finally, a descriptive case study is carried out on the English Wikipedia data set to illustrate the analytical potential of the knowledge graph and its metrics.}, organization = {Ministry of Science and Innovation, Spain (MICINN) Spanish Government PID2019-109127RB-I00/SRA Spanish Government FPU18/05835}, organization = {Reincorporation Programme for Young Researchers of the University of Granada}, organization = {South African DSI-NRF Centre of Excellence in Scientometrics and Science, Technology and Innovation Policy (SciSTIP)}, publisher = {MIT}, keywords = {Altmetrics}, keywords = {Data}, keywords = {Informetrics}, keywords = {Knowledge graph}, keywords = {Metrics}, keywords = {Wikipedia}, title = {Wikinformetrics: Construction and description of an open Wikipedia knowledge graph data set for informetric purposes}, doi = {10.1162/qss_a_00226}, author = {Arroyo Machado, Wenceslao and Torres Salinas, Daniel}, }