we measure the knowledge flows among the countries by analyzing publication and citation data. We argue that not all citations are equally important, therefore, in contrast to existing techniques that utilize absolute citation counts to quantify knowledge flows among different entities, our model employs citation context analysis technique using machine learning approach to distinguish between important and non-important citations.
We use 14 novel features (including context based, cue words based and textual based) to train Random Forest classifier on labeled dataset of 20,527 publications downloaded from the Association for Computational Linguistics anthology (http://allenai.org/data.html). Finally, we present a case study to elucidate our deployed method on the dataset of PLoS ONE full text publications in the field of Computer and Information Sciences. Our results show significant volume of important knowledge flows from the United States consumed by the international scientific community. Of the total knowledge flow from China, we find relatively less proportion (only 4.11%) fall under the category of important knowledge flow. We believe that such analyses are helpful to understand the dynamics of the relevant knowledge flows across the nations.
Saeed-Ul Hassan, Anam Akram, Awais Asghar and Naif Radi Aljohani “Knowledge Flows by Citation Context Analysis”Read Paper