An Overview of Microsoft Academic Service (MAS) and Applications

By Arnab Sinha, Zhihong Shen, Yang Song, Hao Ma, Darrin Eide, B. Hsu, Kuansan Wang. 2015

1,142 citations recorded by the source corpus.

In this paper we describe a new release of a Web scale entity graph that serves as the backbone of Microsoft Academic Service (MAS), a major production effort with a broadened scope to the namesake vertical search engine that has been publicly available since 2008 as a research prototype. At the core of MAS is a heterogeneous entity graph comprised of six types of entities that model the scholarly activities: field of study, author, institution, paper, venue, and event. In addition to obtaining these entities from the publisher feeds as in the previous effort, we in this version include data mining results from the Web index and an in-house knowledge base from Bing, a major commercial search engine. As a result of the Bing integration, the new MAS graph sees significant increase in size, with fresh information streaming in automatically following their discoveries by the search engine. In addition, the rich entity relations included in the knowledge base provide additional signals to disambiguate and enrich the entities within and beyond the academic domain. The number of papers indexed by MAS, for instance, has grown from low tens of millions to 83 million while maintaining an above 95% accuracy based on test data sets derived from academic activities at Microsoft Research. Based on the data set, we demonstrate two scenarios in this work: a knowledge driven, highly interactive dialog that seamlessly combines reactive search and proactive suggestion experience, and a proactive heterogeneous entity recommendation.

Subfields: Artificial Intelligence, Information Systems, Statistical and Nonlinear Physics, Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Statistical and Nonlinear Physics

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

SciBERT: A Pretrained Language Model for Scientific Text (2019, methodology): “The Paper Field dataset is built from the Microsoft Academic Graph (Sinha et al., 2015) 3 and maps paper titles to one of 7 ﬁelds of study.”
CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability (2021, methodology): “Data queried using Microsoft Academic Graph (Sinha et al., 2015), based on keyword occurrence in the abstract.”
Review of IoT applications in agro-industrial and environmental fields (2017, background): “These facts can be explained because IEEExplore and Scopus have complete and usable advanced search systems and they have been operating continuously unlike Microsoft’s counterpart (Sinha et al., 2015a).”
ScholarBERT: Bigger is Not Always Better (2022, methodology): “The Paper Field dataset (Beltagy et al., 2019), built from the Microsoft Academic Graph (Sinha et al., 2015), maps paper titles to one of seven ﬁelds of study (geography, politics, economics, business, sociology, medicine, and psychology), with each ﬁeld of study having around 12K training examples.”
Historical comparison of gender inequality in scientific careers across countries and disciplines (2019, methodology): “To demonstrate the robustness of our findings to database bias and author disambiguation errors, we independently replicated our results in two additional datasets: the Microsoft Academic Graph (MAG) (31) and the Digital Bibliography & Library Project (DBLP), each using different criteria for public”
Scaling Graph Neural Networks with Approximate PageRank (2020, methodology): “The resulting MAG-Scholar graph is a few orders of magnitude larger then the commonly used benchmark graphs (12.4M nodes, 173M edges, 2.8M node features).”
Over-optimization of academic publishing metrics: observing Goodhart’s Law in action (2018, positive): “InthisstudyweprimarilyusedtheMAG[72],whichwasreleased as part of the 2016 KDD Cup [73].”
OAG-BERT: Pre-train Heterogeneous Entity-augmented Academic Language Models (2021, methodology): “Other large academic corpora including AMiner [40], OAG [40, 46], and Microsoft Academic Graph (MAG) [19] also integrate massive publications with rich graph information as well, such as authors and research fields.”
Heterogeneous Graph Transformer (2020, methodology): “tract meta paths that are important for downstream tasks†. 5.1 Web-Scale Datasets To examine the performance of the proposed model and its realworld applications, we use the Open Academic Graph (OAG) [16, 20, 28] as our experimental basis. OAG consists of more than 178 million nodes and 2.236 billio”
Bootstrapped Representation Learning on Graphs (2021, methodology): “ogbn-arXiv This is another citation network, where nodes represent CS papers on arXiv indexed by the Microsoft Academic Graph (Sinha et al., 2015).”
Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding (2017, methodology): “Microsoft uses its Microsoft Academic Graph to build academic dialog and recommendation systems [20].”
SPECTER: Document-level Representation Learning using Citation-informed Transformers (2020, methodology): “For our evaluation, we derive a document classification dataset from the level 1 topics, where a paper is labeled by its corresponding level 1 MAG topic.”
Self-Supervised Learning of Graph Neural Networks: A Unified Review (2021, background): “[113] construct four additional node-level datasets, Coauthor-CS, Coauthor-Physics from the Microsoft Academic Graph [114], Amazon-Photos, and Amazon-Computers”