engleski

EuroParliament Corpus Analysis

The idea is to store the data in a graph database for a complex representation of the social ontology of the political behaviour involving various social entities, communication processes as well as to apply basic statistic summarization, text classification, community and centrality graph analytics for the research of social, linguistic and conceptual network. The information ontology will enable comparable data analysis processes for analyzing topicality, Information extraction and retrieval, Word sense disambiguation, semantic- syntactic functions, pragmatic functions, framing strategies, Document structuring and categorization, social network analysis, the patterns of expression of emotion in the language, ... >We would like to apply and further develop an existing graph-database based Croatian NLP model to other languages data sets and compare the results for the crosslinguistic and diachronic analysis of the data. By now I have been involved in the CLARIN Parliamentary group and would like to work with other interested partners in applying the comparable tools that would allow a different type of complex queries to produce greater insight into this complex social issue.

parliament, corpus, digital humanities

nije evidentirano