Mining for truth, belief, and conspiracy using graph paradigms


  • Muhammad Talha


The ISEBEL project aims to build an international search engine that is able to harvest data from folktale databases. The initial project concentrates on belief legends [1] found in the three well known digital collections by Evald Tang Kristensen from Denmark (etkspace), Richard Wossidlo from Mecklenburg (wossidia) and several collectors and narrators from the Netherlands (verhaalenbank). Part of the project is on data and graph mining [2,3] for frequent patterns. The WossiDiA system [4] itself as one of the databases harvested by ISEBEL uses typed, directed hypergraphs [5] for representing the collections by Richard Wossidlo [6].

Combining conspiracy-theoretical approaches [7, 8, 9] and experiences, models, and algorithms developed within the ISEBEL project, different concepts for mining truth, belief and conspiracy should be investigated. Based on that, a framework should be designed and implemented building upon state-of-the-art techniques [10, 11].

A prototype implementation should focus on extracting graph data from social network platforms, building a data integration pipeline for relating entities from different sources and should apply graph based cluster analyzing techniques. A proof-of-concept should be done by an up-to-date topic choosen.

Road Map

  • Presenting the state-of-the-art in graph mining concepts, techniques and tools for social network analyzes and conspiracy

  • Defining a general workflow for data extraction from social networks, relating data from different sources and applying graph analysis functionality

  • Designing a framework based on selected software tools for graph-based mining and analyzing for conspiracy experiences

  • Prototype implementation and proof-of-concept using an up-to-date scenario


  1. Usó-Doménech, J.L. & Nescolarde-Selva, What are Belief Systems?. J. Found Sci (2016) 21: 147.

  2. Charu C. Aggarwal, Haixun Wang: Managing and Mining Graph Data. Advances in Database Systems 40, Springer 2010, ISBN 978-1-4419-6044-3

  3. DianeJ.Cook,LawrenceB.Holder(eds),MiningGraphData.Wiley,Hoboken,New Jersey, 2006

  4. HolgerMeyer,Alf-ChristianScheringandChristophSchmitt,WossiDiA–TheDigital Wossidlo Archive, in: Holger Meyer, Christoph Schmitt, Thomas Jansen and Alf-

Christian Schering (Hrsg.), Corpora ethnographica online – Strategien der Digitalisierung kultureller Archive und ihrer Präsentation im Internet, Volume 5 of Rostocker Beiträge zur Volkskunde und Kulturgeschichte, Waxmann, 2014, 61–84.

  1. Meyer, Holger, Alf-Christian Schering, and Andreas Heuer. The Hydra. PowerGraph System. Datenbank-Spektrum (2017): 1-17.

  2. Baker,Lynda.(2006).Observation:AComplexResearchMethod.LibraryTrends.55. 10.1353/lib.2006.0045.

  3. David Chong, Erl Lee, Matthew Fan, Pavan Holur, Shadi Shahsavari, Timothy R. Tangherlini, Vwani Roychowdhury: A real-time platform for contextualized conspiracy theory analysis. ICDM (Workshops) 2021: 118-127

  4. Shahsavari,Shadi,etal."Conspiracyinthetimeofcorona:Automaticdetectionof emerging COVID-19 conspiracy theories in social media and the news." Journal of computational social science 3.2 (2020): 279-317.

  5. PavanHolur,TianyiWang,ShadiShahsavari,TimothyR.Tangherlini,Vwani Roychowdhury: Which side are you on? Insider-Outsider classification in conspiracy-theoretic social media. CoRR abs/2203.04356 (2022)

  6. Shadi Shahsavari, Ehsan Ebrahimzadeh, Behnam Shahbazi, Misagh Falahi, Pavan Holur, Roja Bandari, Timothy R. Tangherlini, Vwani P. Roychowdhury: An Automated Pipeline for Character and Relationship Extraction from Readers Literary Book Reviews on WebSci 2020: 277-286.

  7. Tangherlini, Timothy R., et al. "An automated pipeline for the discovery of conspiracy and conspiracy theory narrative frameworks: Bridgegate, Pizzagate and storytelling on the web." PloS one 15.6 (2020): e0233879.