Research policy makers, funding agencies, universities, and government organizations evaluate research output or impact based on the traditional citation count, peer review, h-index and journal impact factors. These impact measures also known as bibliometric indicators are limited to the academic community and cannot provide the broad perspective of research impact in public, government or business. The understanding that scholarly impact outside scientific and academic sphere has given rise to an area of scientometrics called alternative metrics or "altmetrics". Moreover, researchers in this area incline to center around gauging scientific activity via social media namely Twitter. However, these count-based measurements of impact are sensitive to gaming as they lack concrete references to the primary source. In this work, we expand a conventional citation graph to a heterogeneous graph of publications, scientists, venues, organizations based on more reliable social media sources such as mainstream news and weblogs. Our method is composed of two components: the first one is combining the bibliometric data with social media data like blogs and mainstream news. The second component investigates how standard graph-based metrics can be applied to a heterogeneous graph to predict the academic impact. Our result showed moderate correlations and positive associations between the computed graph-based metrics with academic impact and also reasonably predict the academic impact of researchers.

Abstract. Altmetrics measure scientific impact outside of traditional scientific literature. While different methods adopting citation counts measure the impact within scientific literature, altmetrics may look for research impact on government policies or public discourse by exploring alternative data sources such as news, articles, blogs, social media or government documents. We identify mentions of scientific research or entities like researchers, academic or research organizations. We collect a corpus containing blogs, articles, news items etc and manually analyse it for patterns of such informal mentions. We then apply text mining techniques by developing extraction rules for mining informal mentions. We apply them to our development corpus and present our results. This work takes us closer to developing concrete altmetrics for determining research impact on news, public discourse ultimately leading to government policies.

No abstract

No abstract

No abstract