Using CNNs to Detect Graphical Representations of Structural Equation Models in IS Papers

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Literature reviews are an essential but time-consuming part of every research endeavor and play an important role in the quality of the research findings. Traditional tools and literature databases only make use of the textual information and do not consider graphical representations like figures of structural equation models (SEMs). These models are often used in empirical studies to visualize theoretical models and key results. We design and implement an application for image recognition to simplify the search for relevant papers, by automatically recognizing SEM figures in scientific papers stored as PDF files. To classify whether a page in a paper contains an SEM figure we make use of convolutional neural networks and achieve an F1 score of 98,7% together with a recall of 100% for the SEM class. We further describe how we intend to automatically extract information from these SEM figures.

Original languageEnglish
Title of host publicationEntwicklungen, Chancen und Herausforderungen der Digitalisierung : Proceedings der 15. Internationalen Tagung Wirtschaftsinformatik 2020
EditorsN. Gronau, M. Heine, H. Krasnova, K. Pousttchi
Number of pages6
Volume1
Place of PublicationBerlin
PublisherGITO mbH Verlag
Publication date09.03.2020
Pages115-120
Article number8
ISBN (electronic)978-3-95545-335-0
DOIs
Publication statusPublished - 09.03.2020
EventInternationale Tagung Wirtschaftsinformatik - WI 2020: Changing Landscapes - Shaping Digital Transformation and its Impact - Universität Potsdam, Potsdam, Germany
Duration: 09.03.202011.03.2020
Conference number: 15
https://wi2020.de/de/start

Bibliographical note

Bd. 1: Zentrale Tracks. Motto “Changing Landscapes"

Publisher Copyright:
© Proceedings of the 15th International Conference on Business Information Systems 2020 "Developments, Opportunities and Challenges of Digitization", WIRTSCHAFTSINFORMATIK 2020.

    Research areas

  • Business informatics - Structural equation models, deep neural networks, information extraction, literature review

DOI

Recently viewed

Publications

  1. A MODEL FOR QUANTIFICATION OF SOFTWARE COMPLEXITY
  2. Single Robust Proportional-Derivative Control for Friction Compensation in Fast and Precise Motion Systems With Actuator Constraint
  3. PLM ‑supported automated process planning and partitioning for collaborative assembly processes based on a capability analysis
  4. Kit based motion generator for a soft walking robot
  5. Errors, error taxonomies, error prevention, and error management
  6. Appendix A: Design, implementation, and analysis of the iGOES project
  7. Mixed Pickels
  8. Graph-Based Early-Fusion for Flood Detection
  9. Design optimization of spiral coils for textile applications by genetic algorithm
  10. On the utility of indirect methods for detecting faking
  11. Biodiversity-multifunctionality relationships depend on identity and number of measured functions
  12. Development of a simulative approach in order to estimate the impact of smart services on a production system
  13. Image compression based on periodic principal components
  14. Predicting recurrent chat contact in a psychological intervention for the youth using natural language processing
  15. Efficacy of a Web-Based Intervention With Mobile Phone Support in Treating Depressive Symptoms in Adults With Type 1 and Type 2 Diabetes
  16. Transcending Methodological Nationalism through a Transversal Method?
  17. QSPR Using MOLGEN-QSPR: The challenge of fluoroalkane boiling points
  18. Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence
  19. Computergestütztes Repetitorium der Elementarmathematik
  20. Integrative inspection methodology for enhanced PCB remanufacturing using artificial intelligence
  21. Note on the Lingen case
  22. Emotional reactivity and interoceptive sensitivity
  23. Perceptron and SVM learning with generalized cost models
  24. Sicht von oben