Computer-generated publication
88 pages

The Artist’s Machine is a computational research project with the outcome of a publication, generated by an algorithm called ARCU. From researching topic-relevant literature, detecting semantic structures in hundreds of papers and books, to finally generating a publication with illustrations and paraphrased text citations, every step in the process has been performed automatically – initiated by a simple research phrase that was given as input.

The main focus of this project is to develop a method for computational text curation and automated research, an experimental artistic use case for established Machine Learning services, search engines and databases.

Please note that this method has been elaborated in an applied experimental process. The algorithm can be considered as a proof of concept and a first goal-driven attempt to experiment with automated research and computational curation. Read more…

Download the PDF version here (CC-By Attribution 4.0 International). If you wish to purchase a physical copy of the book, please drop me an email.

Application Programming Interfaces

Cloud Natural Language API by Google Cloud Platform. (accessed from August to December 2017)

Cloud Translation API by Google Cloud Platform. (accessed January 2018)

Natural Language Understanding (API) by IBM Watson. understanding/api/v1/ (accessed from August to December 2017)

Cloud Vision API by Google Cloud Platform. (accessed January 2018)


CompArt daDA: Digital art database. (accessed January 2018)

Crossref: Bibliographic database. (accessed from August to September 2017)

DBpedia: Semantic web database from Wikipedia. Dataset version 2016-04. (accessed from September to October 2017)

Google Scholar: Bibliographic database. (accessed from August to September 2017)

Media Art Net: Media art database. (accessed January 2018) Thesaurus, dictionary. (accessed August 2017)

Wikimedia Commons: Media repository. (accessed January 2018)

Software and Tools

Gephi: Graph Visualization and Manipulation software. Version 0.9.2 for Mac OS.

Google-api-python-client: Google API Client Library for Python. Version 1.6.3.

Google-cloud: Google Cloud Client Library for Python. Version 0.32.0.

Habanero: Low Level Client for Crossref Search API. Version 0.6.0.

NetworkX: Python package for creating and manipulating graphs and networks. Version 2.0.

NLTK: Natural Language Toolkit. Version 3.2.4.

Pdfminer3k: PDF parser and analyzer. Version 1.3.1.

PyDictionary: Python Module to get meanings, translations, synonyms and antonyms of words. Version 1.5.2.

Python: Python Language Reference. Version 3.5.2.

SPARQLWrapper: SPARQL Endpoint interface to Python. Version 1.8.0.

Watson-developer-cloud: Client library to use the IBM Watson Services. Version 0.26.0.