Research Knowledge Graphs at GESIS & NFDI4DataScience
0 likes•139 views
The document discusses the development and significance of research knowledge graphs (KGs) at GESIS and NFDI4DS, focusing on the sharing and reuse of research data and resources. It highlights challenges like inconsistent persistent identifiers and a lack of structured data representation, emphasizing the importance of interoperability and machine-interpretable links through established standards. Additionally, it showcases the creation of KGs from various data sources, including social media, to facilitate scholarly research and understanding of scientific processes.
Research Knowledge Graphs at GESIS & NFDI4DataScience
- 1. Research Knowledge Graphs at GESIS & NFDI4DS „Faire Datenökonomie“, Berlin Stefan Dietze, 15.03.2022
- 2. Sharing & Reuse of Research Data, Resources, Knowledge ▪ Research Data ▪ Publications ▪ Code/Scripts ▪ ML Models ▪ Methods ▪ Claims ▪ Metrics Relations between scientific resources, data, knowledge Research Data Cycle
- 3. Common questions for researchers • Which top-tier publications cite which data/method? („dataset authority“) • Which data was used to train/evaluate which method? Which method to produce what data? • Which claims are supported/cited/rejected by what dataset or publication? ▪ Research Data ▪ Publications ▪ Code/Scripts ▪ ML Models ▪ Methods ▪ Claims ▪ Metrics Relations between scientific resources, data, knowledge Sharing & Reuse of Research Data, Resources, Knowledge
- 4. Challenges • Data & metadata about resources and concepts not represented in structured, machine-interpretable, integrated manner (hidden in publications, web pages etc) • Persistent identifiers (e.g. DOIs) used inconsistently (e.g. on publications/datasets) • Relations and semantics not explicit • Reproducibility crisis in CS/DS/AI ▪ Research Data ▪ Publications ▪ Code/Scripts ▪ ML Models ▪ Methods ▪ Claims ▪ Metrics Relations between scientific resources, data, knowledge Sharing & Reuse of Research Data, Resources, Knowledge
- 5. Knowledge Graphs for FAIR Research Data • Improving data interoperability and reuse through established W3C standards for data sharing (on the Web), e.g. RDF, JSON, shared vocabularies (e.g. schema.org, DCAT, DDI), APIs for data reuse and linking • Making links between resources and concepts explicit & machine-interpretable (e.g. which publications cite what dataset? Which claim is supported/rejected by publication X/dataset Y?) • Consistent use of persisent IDs (e.g. URIs, DOIs) across all data, e.g. concepts, resources etc („DOIs for all“) Resources ▪ Datasets ▪ Publications ▪ Code ▪ Software Concepts ▪ Terms & Definitions ▪ Claims ▪ Methods ▪ Topics ▪ Entities
- 6. 6 © Frank van Harmelen KGs in practice
- 7. 7 Research KGs in Practice: integrated search @ GESIS https://search.gesis.org/ Dataset Rel. Publications
- 8. 8 From publications to machine-interpretable metadata KGs Disambiguation of dataset & software/script citations https://data.gesis.org/softwarekg ▪ Training deep learning- based model for extraction software & data references in large-scale data (3.5 M publications) ▪ Data lifting into KG ▪ 300+ M triples / statements ▪ Search across data/software/publications (GESIS Search)
- 9. From publications to machine-interpretable metadata KGs Understanding scientific software/data usage https://data.gesis.org/softwarekg (Schindler et al., CIKM2021) ▪ Understanding SW usage, citation habits and their evolution across disciplines ▪ Rise of data science = rise of software usage
- 10. From publications to machine-interpretable metadata KGs Understanding scientific software/data usage https://data.gesis.org/softwarekg ▪ Top adopters of data science/AI/software…
- 11. From publications to machine-interpretable metadata KGs Understanding scientific software/data usage https://data.gesis.org/softwarekg ▪ Top adopters of data science/AI/software… ▪ …follow the worst citation habits
- 12. http://dbpedia.org/resource/Tim_Berners-Lee wna:positive-emotion onyx:Intensity "0.75" onyx:Intensity "0.0" http://dbpedia.org/resource/Solid wna:negative-emotion From social media to machine-interpretable research data KGs https://data.gesis.org/tweetskb Building a public research knowledge graph from Twitter data
- 13. From social media to machine-interpretable research data KGs https://data.gesis.org/tweetskb TweetsKB – a large-scale research KG of societal opinions ▪ Harvesting & archiving of 10 Billion tweets (permanent collection from Twitter 1% sample since 2013) ▪ Information extraction pipeline to build a KG of entities, interactions & sentiments (distributed batch processing via Hadoop Map/Reduce) o Entity linking with knowledge graph/DBpedia (“president”/“potus”/”trump” => dbp:DonaldTrump) o Sentiment analysis/annotation o Geotagging o Lifting into knowledge graph schema ▪ Public, large-scale research corpus of public opinions and their evolution => interdisciplinary research P. Fafalios, V. Iosifidis, E. Ntoutsi, and S. Dietze, TweetsKB: A Public and Large-Scale RDF Corpus of Annotated Tweets, ESWC'18.
- 14. RKG-based social science research using TweetsKB https://dd4p.gesis.org Investigating Vaccine Hesitancy in DACH countries
- 15. Investigating Vaccine Hesitancy in DACH countries Germany suspends vaccinations with Astra Zeneca RKG-based social science research using TweetsKB https://dd4p.gesis.org Twitter discourse zu “Impfbereitschaft”
- 16. RKG-based discourse analysis using TweetsKB Vaccine Hesitancy– key topics in “safety” category „Schwangerschaft“ „Kimmich“ „Alter“ „Nebenwirkungen“ „Herzinfarkt“ „Zulassung“ https://dd4p.gesis.org
- 17. Knowledge Graphs for Research Data: Initiatives 17
- 18. Summary: Research KGs @ GESIS 18 Tools for constructing scholarly knowledge graphs ● NLP and deep learning-powered methods for extracting large-scale KGs about methods, claims, data, software involved in the scientific process Large-scale scholarly KGs, e.g. ● KGs about scholarly use of software & research data (e.g. SoftwareKG: 1.8 M disambiguated software mentions extracted from 3 M publications, https://data.gesis.org/softwarekg/) ● Web mined KGs of social science research data, e.g. public opinions, claims and attitudes expressed on social media (e.g. TweetsKB: > 10 Bn semantically annotated tweets, sentiments, https://data.gesis.org/tweetskb) Semantic Search powered by KGs and related tools ● RKG-powered search across scholarly publications, datasets, methods and their relations (e.g. GESIS Search, https://search.gesis.org) https://gesis.org/en/kts https://search.gesis.org
- 19. Outlook: a joint Research KG in NFDI4DS 19 19 Resources ▪ Datasets ▪ Publications ▪ Code ▪ Software Concepts ▪ Terms & Definitions ▪ Claims ▪ Methods ▪ Topics ▪ Entities • Community • Expert-curation/annotation workflow/tools • Focus point & hub • PIDs https://www.nfdi4datascience.de/ • Large-scale knowledge graphs • Automated deep learning- based methods for extracting KGs • Populating ORKG