{"id":670875,"date":"2020-07-01T14:15:41","date_gmt":"2020-07-01T21:15:41","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-blog-post&p=670875"},"modified":"2020-07-01T14:15:41","modified_gmt":"2020-07-01T21:15:41","slug":"visualizing-academic-impact","status":"publish","type":"msr-blog-post","link":"https:\/\/www.microsoft.com\/en-us\/research\/articles\/visualizing-academic-impact\/","title":{"rendered":"Visualizing academic impact"},"content":{"rendered":"
We’re excited to announce that starting today Microsoft Academic users have a new way of visualizing academic impact.\u00a0\u00a0 This feature, available on author, conference, journal, institution and topic detail pages, provides a visualization of the impact an entity has in relation to other types of entities. For example, this allows you to see which journals or conferences an author has most impacted with their publications, or which institutions have published the most impactful work in a specific journal.<\/p>\n
Before we jump in, it’s important to define Impact and how it’s measured.<\/p>\n
When our graph is built, each entity is evaluated along with its connected entities and an individual rank is assigned.\u00a0 This is done based on a few factors, including the rank of its connected entities through references or citations.\u00a0 In this way, rank is not solely driven by citation count, but also by the rank of an entity\u2019s connections in the graph. Additionally, it is known that citations are a lagging indicator of impact because it takes time for research to be duly recognized and its impacts to be fully appreciated, leading to an age bias favoring older work. To adjust for this bias, we have employed a reinforcement learning algorithm (opens in new tab)<\/span><\/a> that utilizes the massive historical data we have to train a ranker that recognizes the momentum of new publications and projects their future impacts. This way, newer work is not at a disadvantage when comparing to older work. We refer to this rank as an entity\u2019s \u2018Saliency\u2019 (for a more detailed description of Saliency, see recent our paper (opens in new tab)<\/span><\/a>).\u00a0 The “top” entity relationships we previously showed on entity pages already reflected impact through saliency.<\/p>\n It is common for an author or an institution to achieve higher impact by being prolific. Saliency ranks are therefore often conflating productivity and the impact of individual publications. While aggregate rank of impact is useful, it is also interesting to take into consideration productivity and ask; \u201cWhat volume of work was done to achieve a given rank?\u201d, and \u00a0\u201cwhat is the average per-article impact?\u201d.\u00a0 To show this, we show the publication normalized saliency by using a feature in MAG called paper families <\/em>to properly count the number of articles that should be regarded as a single publication.\u00a0 Paper families are a grouping of papers that we have found to be identical, or nearly identical, which have been published in different venues.\u00a0 Take for instance a paper an author has written that has been published in a pre-print repository, a conference and a journal.\u00a0 We record each of these publications as separate entity\u2019s in the graph, but these publications represent the same work and are thus grouped into a paper family in MAG.\u00a0 Using this value for an entity\u2019s publication count, we normalize the saliency and determine an entity\u2019s productivity.<\/p>\n