Who said what to whom?: capturing the structure of debates

ABSTRACT

Transcripts of meetings are a document genre characterized by a complex narrative structure. The essence is not only what is said, but also by who and to whom. This paper investigates whether we can use semantic annotations like the speaker in order to capture this debate structure, as well as the related content of the debate. The structure is visualized in a graph, while the content is condensed into word clouds, that are created using a parsimonious language model. Evaluation shows that both tools adequately capture the structure and content of the debate at an aggregated level.

REFERENCES

• 1: T. Gielissen and M. Marx. Exemelification of parliamentary debates. In Proceedings of the 9th Dutch-Belgian Workshop on Information Retrieval (DIR 2009), 2009.
• 2: Djoerd Hiemstra , Stephen Robertson , Hugo Zaragoza, Parsimonious language models for information retrieval, Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval, July 25-29, 2004, Sheffield, United Kingdom [doi>10.1145/1008992.1009025]
• 3: Paul Rayson , Roger Garside, Comparing corpora using frequency profiling, Proceedings of the Workshop on Comparing Corpora, p.1-6, October 07-07, 2000, Hong Kong

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Search process

General Terms:
Experimentation, Measurement, Performance

Keywords:
political data, visualization, word clouds