• Inspection of existing and development of new hermeneutic hypothesis by combination of hermeneutic and algorithmic methods, based on the study ‘A History of poetics’, to retrace qualitative and quantitative complementarities, historic relations and dynamics of the corpus.

  • Creation of TEI-compliant XML-documents of the poetics enriched by extensive (bibliographic, structural and contextual) metadata. These originate initially from the hermeneutic analysis of the corpus, but are extended in cooperation with the information technology, which is facilitated by the development of new tools for metadata harvesting.

  • Analysis of text and corpus by means of natural language processing technology: language analysis of the corpus, statistic methods (computation of quantitative conclusions to support hermeneutic hypotheses), text mining (named entity recognition + detection of user defined concepts), part of speech tagging, parsing, sentiment analysis, topic segmentation + recognition, automatically generated abstracts (word clouds), semi supervised machine learning (user trainable tools of analysis)

  • Support of analysis and visualization of the results by techniques of visual analytics: visualization of information (fast verification resp. falsification of hermeneutic hypotheses), text and context viewing (fast access to text and annotation), smooth scroll (simultaneous visualization of different document layers), interactive tools of analysis (interactive mechanisms of feedback and training)