Since 2014, Microsoft Research has been proud to have one of its AI research projects contribute to the open exchange of knowledge within the academic research community. This AI research project will be supported until the end of calendar year 2021, upon which time MAS will be retired.
We are now evolving our focus to explore how we can advance these AI technologies in Microsoft 365 to empower every person and organization to derive valuable insights from their content.
What this means for each service:
Microsoft Research will continue to support the automated AI agents powering Microsoft Academic services through the end of calendar year 2021. During this time, we encourage existing Microsoft Academic users to begin transitioning to other equivalent services. Below are just a few of the many great options available to the community.
When you exercise a muscle, you are concentrating all of your effort on that muscle. That is called FOCUS. Each step in the Microsoft Academic search helps you to better FOCUS your search results. Let's flex some research muscle!
MeSH is a controlled and hierarchically organized vocabulary that the National Institute of Health (NIH) maintains for indexing, cataloging, and facilitating search in biomedical databases such as PubMed. Since releasing the Microsoft Academic in 2016, many user queries are phrased using MeSH terminology.
Due to the prevalence of biomedical literature in the Microsoft Academic Graph (MAG) semantic search capabilities are now integrated into MA’s unique semantic search capabilities. Users on MA can now access MeSH using two new semantic attributes: MeSH descriptors signified by , and MeSH qualifiers:
"Composite attributes" group concepts that should be processed together, and one area that can further demonstrate its efficacy is in handling Medical Subject Headings (MeSH).
In Microsoft Academic (MA), two basic types of MeSH records are included: the descriptor ( main MeSH heading) and the qualifier (MeSH subheading). Descriptors characterize the subject matter or content of an article, while qualifiers are used in connection with descriptors to define a particular aspect of a subject.
Unlike keyword searching in databases, Microsoft Academic (MA) has always emphasized semantic search. In contrast to keyword search where a search engine performs best when users select the “right” keywords that match how the contents are indexed, semantic search is designed for the cases when it is not clear what the “right” keywords should be.
Diabetes: A condition results from insufficient production of insulin, causing high blood sugar.
For example, suppose you want to find the most influential publications in Diabetes Care using the query “ diabetes care” with a keyword-based search engine, you will get results where the query terms explicitly appear in the paper title/body, which misses the influential publications on AI that do not contain those specific terms. A semantic search engine like MA, on the other hand, will be able to overcome this limitation.
Your assignment may be: Develop a care plan and supporting patient educational material for Diabetes Mellitis, Type 2. When you enter "diabetes care" the top topic is Medicine. When you choose medicine, other subtopics appear, such as Type 2 Diabetes Mellitis. Since this is more specific, I check the box for Diabetes Melitis Type 2.
Select the filter to JOURNAL: and then choose the top journal for Diabetes Care. The journal name is Diabetes Care.
Our next step is to focus our search using Descriptor filter. I chose Type 2 Diabetes Mellitis.
Next I set my qualifier. Mesh Subheadings — (also called qualifiers) are attached to MeSH headings to describe a specific aspect of a concept.
.When thinking critically about the assignment, Prevention & Control is the nursing intervention used to zero in on in my PICO statement. How can I help my patient prevent or control their Diabetes?
Have you ever wondered why your Nursing or Allied Health professor wants you to restrict your search to the last 5 or 10 years? Healthcare standards, prescribed treatments and industry practices change over time and she/he wants you to observe current standard practices in your profession. So, I scroll up to the top of the column and select my timeline.
Lastly, I check my parent and child subjects one last time on the right hand side of the page.
Once you have narrowed your search and retrieved your result set, you can explore your topic more thoroughly by creating a Microsoft Academic Graph (visual cluster map -- or visual cluster analysis). All of the articles in your search are grouped according to their major topic. See the picture below that shows you how to change tabs and explore your topic.
Under Explore, CHOOSE TOPICS. (see picture below)
The Microsoft Academic Graph (MAG) is a helpful way to visualize and explore the topic hierarchy of your search results. The Microsoft Academic Graph (MAG) uses fields of study to categorize articles. These fields of study are hierarchical in nature, grouping specific fields of study under larger, more generic fields of study. This helps researchers visualize the topic hierarchy and the connections within it.
This can be used as a visual search mechanism. Before you go here, run a search in CINAHL first or in the PubMed MeSH browser to make sure you are familiar with the MeSH headings for your topic.
Navigating through the 700K+ topics can be a difficult task. A Topic browser control allows you to search for topics you are interested in. Once a desired topic is selected, parent and child topics are displayed to help researchers understand the hierarchical nature of topics and navigate between them.
The new MAG release gives the user perspective on the scale of topics available and how they are connected.
A visual representation of your topic hierarchy give researchers users better context. The images are represented in parent-child topics. Seeing their relationships in a graph brings perspective to the the search results.
It also brings a bit of fun to exploring the topic graph as well. In its default state, the topic graph explorer shows all the top-level topics and allows you to expand down the graph. Nodes are color coded to the level of the hierarchy in which they appear and sized based on the number of publications contained in them.
Many times, students don't think through their topic or their assignment before searching. That's why we always recommend making a PICO or PICOT chart. A PICOT chart helps you think through your assignment and logically plan it.
A good search is like finding the proverbial golden needle in a haystack. A wide scoping search finds all the information in all areas of a topic. A focused search finds a few good nuggets of information -- articles that support Evidence Based Medicine (EBM).
As you navigate around the graph, child and parent nodes are drawn and connected. Depending on which visual analytics page you are viewing, information about each entity within that topic will be shown. Above is a zoomed-out view of the Diabetes Care topic. On the left, you can see the search results parent relationship with Diabetes Care and its shared child topics. On the right, you can see detailed information on the topic and the authors within.
Evidence Based Medicine (EBM)
*Throughout our online Library, Nursing & Allied Health classes, you will hear these terms. MeSH, PICOT and EBM.