A5043260495- Research Data Management Practices
- Data Quality and Management
- Scientific Computing and Data Management
- Topic Modeling
- Data Mining Algorithms and Applications
- Human-Automation Interaction and Safety
- Artificial Intelligence in Healthcare and Education
- Ethics and Social Impacts of AI
- Emergency and Acute Care Studies
- Software Engineering Techniques and Practices
- Natural Language Processing Techniques
- Data Management and Algorithms
- Data-Driven Disease Surveillance
- Machine Learning in Healthcare
- Biomedical Text Mining and Ontologies
- Library Science and Information Systems
- Chronic Disease Management Strategies
- Frailty in Older Adults
- Big Data and Business Intelligence
- Software Reliability and Analysis Research
- Semantic Web and Ontologies
- Technology Assessment and Management
University of Washington
2023
Microsoft Research (United Kingdom)
2023
Microsoft (United States)
2013-2019
Human-AI collaboration for decision-making strives to achieve team performance that exceeds the of humans or AI alone. However, many factors can impact success teams, including a user’s domain expertise, mental models an system, trust in recommendations, and more. This article reports on study examines users’ interactions with three simulated algorithmic models, all equivalent accuracy rates but each tuned differently terms true positive negative rates. Our examined user non-trivial blood...
KDD Cup 2013 challenged participants to tackle the problem of author name ambiguity in a digital library scientific publications. The competition consisted two tracks, which were based on large-scale datasets from snapshot Microsoft Academic Search, taken January and including 250K authors 2.5M papers. Participants asked determine papers an profile are truly written by given (track 1), as well identify duplicate profiles 2). Track 1 track 2 launched respectively April 18 20, 2013, with...
Over the past decade as data science has become integral to research workflow, we, like many others, have learned that good requires high-quality software engineering. Unfortunately, our experience is projects can be limited by absence of engineering processes. We advocate should incorporate what we call 3Rs engineering: readability (human understandable codes), resilience (fails rarely/gracefully), and reuse (can easily used others embedded in other software). This article discusses...
We present a system called ALIAS, that is designed to search for duplicate authors from Microsoft Academic Search Engine dataset. Author-ambiguity prevalent problem in this dataset, as many publish under several variations of their own name, or different share similar same name. ALIAS takes an author name input (who may not exist the corpus), and outputs set names database, are determined duplicates author. It also provides confidence score with each output. Additionally, has feature finding...
Progress in machine learning and artificial intelligence promises to advance research understanding across a wide range of fields activities. In tandem, increased awareness the importance open data for reproducibility scientific transparency is making inroads that have not traditionally produced large publicly available datasets. Data sharing requirements from publishers funders, as well other stakeholders, also created pressure make datasets with and/or public interest value through digital...
Microsoft Academic Search is a free search engine specific to scholarly material. It currently covers more than 50 million publications and over 19 authors across variety of domains. One the main challenges in correctly indexing this material author name ambiguity resulting noise profiles. KDD Cup 2013 invited participants tackle problem 2 ways: (1) by automatically determining which papers an profile are truly written given author, (2) identifying profiles need be merged because they belong...
The following tutorials are presented: (1) Cloud Computing for Science and Engineering: Scaling in the Cloud; (2) Parallelizing Trajectory Stream Analysis on Platforms; (3) Building Secure Architectures Ecosystems usung Patterns.
In this paper, we discuss Microsoft Research Open Data, a new data repository in the cloud dedicated to facilitating collaboration across global research community. The provides single, convenient location for datasets. convenient, cloud-hosted location, datasets many domains such as computer science, social biology, genomics and others, representing years of curation efforts by researchers. are accompanied meaningful assets meta publications. can seamlessly be copied user's subscription on...
Human-AI collaboration for decision-making strives to achieve team performance that exceeds the of humans or AI alone. However, many factors can impact success teams, including a user's domain expertise, mental models an system, trust in recommendations, and more. This work examines users' interaction with three simulated algorithmic models, all similar accuracy but different tuning on their true positive negative rates. Our study examined user non-trivial blood vessel labeling task where...