MARKUS

Responsible person(s):        Hilde De Weerdt (Leiden University); Brent/Hou Ieong Ho (Leiden University)

Synopsis:    MARKUS is a reading and text analysis platform with a wide range of functionality including 1) automated tagging and identification of personal and place names, official titles, and time references in classical Chinese; 2) manual and batch tagging of user-supplied keyword lists in all languages and creation of custom tags; 3) generation of keywords based on text analysis (keyword clipper); 4) flexible filtering of tagged content; 5) linking to a range of online reference tools including geographical and biographical databases and language and domain-specific dictionaries for online reading; 6) export to wide range of formats including html and TEI to ensure interoperability; 7) automatic export of tagged content and linked data from China Biographical Database to visualization platforms for exploration and analysis of tagged content in the associated VISUS visualization interface (maps, network graphs, tables, timelines, pie charts, tagclouds) ; 8) linking to textual databases such as Donald Sturgeon's ctext.org for easy import of broad range of texts; 9) machine learning to improve accuracy and recall for large corpora     

Content type:        text analysis and visualization platform linking geographic, biographical, linguistic, domain-specific databases, chronologies, and user-generated content of various types

Intended audience:        readers of Chinese texts, students and researchers at all levels

Host institution:            Leiden University (The Netherlands)