Krestel, R., S. Bergler, and R. Witte, "Modeling human newspaper readers: The Fuzzy Believer approach", Natural Language Engineering, vol. 20, no. 02, pp. 261–288, April 2014.

Krestel, R., The Fuzzy Believer System: Computing Beliefs by analyzing Newspaper Articles, Vdm Verlag, 2007.

Krestel, R., Automatic Analysis and Reasoning on Reported Speech in Newspaper Articles, , Karlsruhe, Germany : Universität Karlsruhe (TH), Fakultät für Informatik, Institut für Programmstrukturen und Datenorganisation (IPD), 2007.

Qu, Y., J. Shanahan, and J. Wiebe (Eds.), Bergler, S., M. Doandes, C. Gerard, and R. Witte, "Attributions", Exploring Attitude and Affect in Text: Theories and Applications, Stanford, California, USA : AAAI Press, pp. 16–19, March 22–25, 2004.

Krestel, R., S. Bergler, and R. Witte, "Minding the Source: Automatic Tagging of Reported Speech in Newspaper Articles", Proceedings of the Sixth International Language Resources and Evaluation Conference (LREC 2008), Marrakech, Morocco : European Language Resources Association (ELRA), May 28–30, 2008.

Coinciding with the presentation of our paper on Minding the Source: Automatic Tagging of Reported Speech in Newspaper Articles at LREC 2008, we are happy to announce the first public release of our free/open source Reported Speech Tagging Components.

Reported speech in the form of direct and indirect reported speech is an important indicator of evidentiality in traditional newspaper texts, but also increasingly in the new media that rely heavily on citation and quotation of previous postings, as for instance in blogs or newsgroups. We developed an NLP component in form of a GATE resource that can automatically detect and tag reported speech constructs, in particular the source, reporting verb and content. This is intended as a first module for more sophisticated representation and reasoning with attributed information, such as belief reasoning based on nested belief structures.

The growing number of publicly available information sources makes it impossible for individuals to keep track of all the various opinions on one topic. The goal of our fuzzy believer project is to extract and analyze statements of opinion from newspaper articles.

Beliefs are modeled using a fuzzy-theoretic approach applied after NLP-based information extraction. A fuzzy believer models a human agent, deciding what statements to believe or reject based on different, configurable strategies.