posted on 2017-02-05, 22:25authored byLunjun Zhang, Justin Palombo, Sarah Costa
The goal of the project is to analyze altmetric data regarding published scientific papers in 2016, and to specifically determine which interdisciplinary fields are impactful. After taking some random samples, the program designed uses data clustering as well as data representation techniques to analyze the altmetric data. Trying to classify the papers into different levels of impact, k-means clustering is applied in a creative way. With the focus on the interdisciplinary fields, three kinds of matrices are now calculated to illustrate the strength of the connection between every possible pairing combination: average altmetric score, percentage of published papers in this interdisciplinary field, and total altmetric score. Sorting based on the values obtained in the matrices and comparing three matrices can yield insightful results and help people understand the connections between different subjects better.