Marco Spruit is Principle Investigator in the Applied Data Science Lab at the Information and Computing Sciences department of Utrecht University in the Netherlands. His research focuses on NATURAL LANGUAGE PROCESSING SYSTEMS for Self-Service Data Science.

The emerging importance of self-servicing data science brings many new opportunities, but also new research challenges. First, we should empower researchers, domain professionals and citizens to maximise the societal impact of data science technologies. Second, we should evaluate our Analytic Systems in daily practice, where they are needed: Society is our Lab! Third, we should beforehand incorporate all relevant knowledge into our analytic systems to improve their potential and afterwards curate our resulting findings as meta-algorithmic models for improved reusability and reproducibilty.

Marco serves on the editorial boards of the international journals on Semantic Web and Information Systems, Computer Information Systems, and Business Intelligence Research, among others. Before 2007 Marco worked in industry as a Big Data & Natural Language Processing engineer for fourteen years.

Please refer to my Research Theme page for more information, or my Research Projects page for active projects in this theme. 


Top 5 Publications

  1. Spruit,M., & Lytras,M. (2018). Applied Data Science in Patient-centric Healthcare: Adaptive Analytic Systems for Empowering Physicians and Patients. Telematics and Informatics, 35(4), 643–653. [IF: 3.714] [pdf] [online]
  2. Menger,V., Scheepers,F., & Spruit,M. (2018). Comparing Deep Learning and Classical Machine Learning Approaches for Predicting Inpatient Violence Incidents from Clinical Text. Applied Sciences, 8(6), Data Analytics in Smart Healthcare, 981. [IF: 2.217] [pdf]
  3. Menger,V., Scheepers,F., Wijk,L. van, & Spruit,M. (2018). DEDUCE: A pattern matching method for automatic de-identification of Dutch medical text. Telematics and Informatics, 35(4), 727–736. [IF: 3.714] [pdf] [online]
  4. Syed,S., Borit,M., & Spruit,M. (2018). Narrow lenses for capturing the complexity of fisheries: A topic analysis of fisheries science from 1990 to 2016. Fish and Fisheries, 1–19. [IF: 6.665] [pdf] [online]
  5. Tawfik,N., & Spruit,M. (2019). UU_TAILS at 2019 MEDIQA Challenge: Learning Textual Entailment in the Medical Domain. Proceedings of the BioNLP 2019 workshop (pp. 493–499). BioNLP 2019, August 1, 2019, Florence, Italy: Association for Computational Linguistics (ACL). [pdf]

Top 5 Projects

  1. COVIDA: Computing Visits Data for Dutch Natural Language Processing in Mental Healthcare. EUR 230K (2019-2021). Two-year postdoc, parttime scientific programmer, and deployment infrastructure. Financer(s): Alliance Fund UU-UMCU-TU/e. Applicant(s): Spruit,M., Scheepers,F., & Kaymak,U. et al. Remark: Grant total: 492K EUR.
  2. OPERAMOPtimising thERapy to prevent Avoidable hospital admissions in the Multimorbid elderly. EUR 250K (2015-2020). PhD and postdoc position for the STRIP Assistant (STRIPA) prescriptive analytics platform. Financer: PHC 17-2014. Remark: #634238; grant total: 6.6M EUR.
  3. SMESEC: Protecting Small and Medium-sized Enterprises digital technology through an innovative cyber-SECurity framework. EUR 280K (2017-2020). Two PhD positions for cybersecurity maturity modelling. Financer: H2020-DS-2016-2017. Remark: #740787; grant total: 5.6M EUR.
  4. SAF21: Social Aspects in 21st Century Fisheries. EUR 200K (2015–2018). PhD Project on Natural Language Processing (NLP) applications for a Ph.D student stationed at Manchester Metropolitan University (MMU). Financer: MSCA-ITN-2014-ETN. Remark: #642080; grant total: 2.7M EUR.
  5. STRIMP: Implementatie van de STRIP Assistent ter verbetering van de STRIP medicatiebeoordeling. EUR 110K (2018-2019). Postdoc to integrate the STRIP Assistant within Dutch daily primary care. Financer: ZonMW/Goed Gebruik Geneesmiddelen – Stimulering Toepassing In de Praktijk (GGG – STIP Ronde 3). Remark: Grant total: 350K EUR.

Subpages (2): Projects & Team Team