Martin Potthast

Bauhaus-Universität Weimar
Digital Bauhaus Lab
Bauhausstraße 9a · Room 206
99423 Weimar, Germany

Email: martin.potthast[at]
Phone: +49 (0)3643 - 58 3567

Short Curriculum Vitae

Martin Potthast studied computer science at the University of Paderborn. After completing his diploma thesis in 2006 he joined the working group Web Technology and Information Systems at the Bauhaus-Universität Weimar. Martin graduated as Dr. rer. nat. in December 2011 and works since as Postdoc at the Digital Bauhaus Lab. His research interests include information retrieval, machine learning, and web technology.


My primary research activities are the following:

  • digital text forensics
  • writing assistance technologies,
  • Big Data, and,
  • science reproducibility.

In this connection I have made significant algorithmic contributions to research on

  • plagiarism detection
  • Wikipedia vandalism detection, and
  • evaluation as a service technologies.

I have conducted award-winning research on technologies required for the aforementioned tasks, such as information retrieval models, document fingerprinting, multidimensional scaling, near-duplicate detection, inverted indexing, cross-language information retrieval, corpus linguistics, information retrieval evaluation, authorship attribution, clustering, opinion mining, and social software misuse detection.

I take a leading role in a number of projects where much of the aforementioned research is applied within large-scale web services:

  • Netspeak, a writing assistance tool,
  • Picapica, a text reuse search engine,
  • TIRA, a service for evaluation as a service,
  • ChatNoir, a web search engine for static web crawls, and
  • AItools, a programming library for information retrieval.

Professional Activities

I am one of the initiators and organizers of the PAN workshop and competition series on digital text forensics. Since 2009, PAN has hosted successful shared tasks on plagiarism detection, Wikipedia vandalism detection, author identification, and author profiling. 

I regularly serve on the program committees of high-ranked conferences and journals, such as SIGIR, ACL, TKDE, and TOIS.

At Bauhaus-Universität, I've served on the Board for Science and Projects, responsible for the local funding of creative and innovative research, and on the search committee for the junior professorship Mobile Medien (mobile media). I have been repeatedly teaching assistant for the lectures Databases, Web Technology (foundations), and Web Technology (advanced) at this working group.

At the Digital Bauhaus Lab, I oversee its large-scale computing infrastructure for massively parallel Big Data processing and high-performance computing. In this connection, I have coordinated the planning and acquisition of the infrastructure worth about 1 million Euros.

I have successfully acquired funding and supervised a startup project from the German Federal Ministry of Economic Affairs and Energy worth 100.000 Euros.