The Great(er) Bear - using @Wikidata to generate better artwork. Wikipedia holds structured #data about people and things. It uses SPARQL to query that data. @edent writes something to query Wikidata to generate a more accurate artwork #dataviz #graphDB

#schema.org 5.0 is out. No additions to core, but vocabulary for classification of #healthcare topics for more real estate properties in development. New releases on 1st of month, changes in "Pending" section #SEO #semantics #Google h/t @danbri @aaranged

Reasoning over paths in large scale #knowledgegraphs has many applications. @healx #research on approach to automatically build & rank paths between source & target entity pair with learned embeddings using a knowledge base completion model #EmergingTech

Graphs #Analytics for Fraud Detection, using Graph #NeuralNetworks for Anomaly detection. GraphSAGE is Stanford #opensource project: deep neural network-based NRL toolkit, implemented in Tensorflow, making it ideal to develop an anomaly detection system

#semantic understanding of scenes is important for #apps. But in what space should diverse information be grounded, in what structure? 3D Scene Graph outputs a layered graph. Layers have nodes, nodes have attributes, edges between nodes h/t @drfeifei

#Knowledgegraphs have proven to be effective for high-quality recommendation. This #research designs a novel attentive knowledge graph embedding (AKGE) framework for recommendation, which exploits both semantics & topology in interaction-specific manner

#Semantic Datatypes For Fun and Profit. How do you model identifiers? This seemingly simple question can reveal a surprising amount of complexity about the nature of identity & modeling, how we handle units in #datamodel #database #datascience @kurt_cagle

#Microsoft Project Cortex Builds A Custom #KnowledgeGraph for Your Company. Service brings #AI to the vast quantities of #data companies store within #Microsoft365. Unlocks knowledge stored about a topic/client/project inside of documents, surfaces them

More and more #opendata platforms are becoming linked #data. The ONS, @WikiData & Scottish Government all offer SPARQL endpoints to their #linkeddata. SPARQL acts as pattern-matching language @digidatajen @ODcamp #tutorial #knowledgegraph h/t @linkedktk

A case for response time focused query processing by @olafhartig at #ISWC19 Rethinking optimization criteria for Web querying. Optimizing Query execution time is not the same as optimizing Query Response time #research #www #linkeddata #keynote

Property graphs provide a lot of flexibility in data modeling; but how do you know when to use which feature?

#ontology has advantages over more common #data structures: Easy Architectural Changes, Inference, Linking Systems Together, Data Surfing. Ontology will become fundamental to how we organize and distribute data @ExagoInc h/t @aaranged

How "talking semantics" can help you perform better #DataScience. @palexop #StrataData talk in New York slides now available #dataModeling #semantics

"What are Links in Linked Open Data? A Characterization and Evaluation of Links between Knowledge Graphs on the Web."(Haller et al, 2019)https://t.co/wE8nEH0ugn pic.twitter.com/2q22ow6jB4— WikiResearch (@WikiResearch) October 10, 2019

Natural language question answering over #knowledgegraphs enables accurate answers in intuitive manner. But bridging the gap between unstructured questions & knowledge graphs is a challenge. Novel notion: structural query pattern #research #AI #NLP

A Practical Guide to Build an Enterprise #KnowledgeGraph for Investment Analysis. 1. Schema Design 2. D2R Transformation 3. Information Extraction 4. Data Fusion with Instance Matching 5. Storage Design and Query Optimization

.@Wikidata is a community-maintained knowledge base that epitomizes FAIR principles of Findability, Accessibility, Interoperability, Reusability. Collection of #opensource tools simplify addition synchronization of Wikidata w source #databases h/t @danbri

.@shivamshaz #datascientist who rules #DataScience for Good competitions on #Kaggle wants to apply expertise in #ML to solve micro-finance problems for underbanked population in developing countries using network science, graph theory, unstructured data

#Knowledgegraphs are dynamic, evolve over time w addition or deletion of triples. Most existing models focus on embedding static KGs. New context-aware Dynamic Knowledge Graph Embedding (DKGE) method supports embedding learning in online fashion #research

.@healx a Cambridge, U.K.-based startup using AI to help discover new treatments for rare diseases, raised $56 million in Series B funding. They focus on rare genetic diseases and have the world’s leading biomedical #knowledgegraph for rare diseases

MP voting records are public record in the UK, detailed #data is available about how each MP has voted in each bill @PublicWhip collect data & make it accessible @joshua_e_k explores how to use a #GraphDatabase to look at MP’s voting record similarity

How to model #Facebook posts and user reactions, using #Neo4j #graphdatabase #socialmedia #data #analytics #softwareengineering #knowledgegraph

.@jQAssistant is a #QA tool which allows definition & validation of project specific rules on a structural level. Built upon #Neo4j #graphdatabase, can be plugged into build process. Now w/ #PlantUML class diagrams #dataviz #softwareengineering

#KnowledgeGraphs can be considered to be fulfilling an early vision in Computer Science of creating intelligent systems that integrate knowledge & data at large scale. A Brief History of Knowledge Graph's Main Ideas: A tutorial by @juansequeda http://knowledgegraph.today/paper.html

#Google Applying BERT models to Search, understanding searches better than ever before. Last year, #opensource #neuralnetwork-based technique for natural language processing was introduced enabling anyone to train question answering system #AI #ML

ClaimsKG, a #knowledgegraph of fact-checked claims, which facilitates structured queries about their truth values, authors, dates, journalistic reviews and other kinds of metadata. Harvests data from popular fact-checking sites, annotates w @DBpedia

On the Role of #KnowledgeGraphs in Explainable #AI: A #MachineLearning Perspective @freddylecue @Inria h/t @aaranged @iswc_conf #iswc2019 #semex2019 #research http://www-sop.inria.fr/members/Freddy.Lecue/presentation/ISWC2019-FreddyLecue-Thales-OnTheRoleOfKnowledgeGraphsInExplainableAI.pdf

Querying @DBPedia #LinkedData From Jupyter Notebooks – Music Genres Related to Heavy Metal and Music Venues in England. #data #tech #dataviz #knowledgegraph #datascience @psychemedia h/t @aaranged

Towards the @BoschGlobal Materials Science Knowledge Base #Industry40 #data #knowledgemanagement #knowledgegraph use case in #iswc_conf #digitaltransformation #business #tech @metaphacts http://ceur-ws.org/Vol-2456/paper89.pdf