Working Papers

2018
The INFOCORE Dictionary. A multilingual dictionary for automatically analyzing conflict-related discourse
Baden, C., Jungblut, M., Micevski, I., Stalpouskaya, K., Tenenboim Weinblatt, K., Berganza Conde, R., Dimitrakopoulou, D., et al. (2018). The INFOCORE Dictionary. A multilingual dictionary for automatically analyzing conflict-related discourse. Publisher's VersionAbstract

This dictionary was created as part of the INFOCORE research project, coordinated by Romy Fröhlich, Ludwig Maximilian University Munich;

as part of the work of the Methodological Working Group: Content Analysis, headed by Christian Baden, The Hebrew University of Jerusalem;

which was a joint effort of Work Package 5: Social Media, headed by Dimitra Dimitrakopoulou, Massachusetts Institute of Technology; Work Package 6: Strategic Communication, headed by Romy Fröhlich, Ludwig Maximilian University Munich; Work Package 7: Journalistic Transformation, headed by Keren Tenenboim-Weinblatt, The Hebrew University of Jerusalem; and Work Package 8: Parliamentary Discourse, headed by Rosa Berganza Conde, King Juan Carlos University Madrid.

The INFOCORE Dictionary includes…

  • 3,738 measured concepts in conflict-related discourse, ordered into four main groups: Semantic concepts (IDs 1####); Actors (2####); Times/Events (3####); Locations (4####)
  • 8 languages: Albanian, Arabic, English, French, German, Hebrew, Macedonian, and Serbian
  • 78,984 unique search phrases with 191,408 disambiguation criteria (Albanian: 9,595 + 22,915; Arabic: 9,592 + 10,816; English: 10,464 + 38,459; French: 7,476 + 19,470; German: 14,054 + 46,208; Hebrew: 11,708 + 14,853; Macedonian: 7,727 + 18,450; Serbian: 8,368 + 20,237)

The INFOCORE Dictionary is built for use in conjunction with the jamcode coding script available on Github, and the AmCAT open source text analysis platform.