Automatic Summarization of Online Debates

Abstract

Debate summarization is one of the novel and challenging research areas in automatic text summarization which has been largely unexplored. In this paper, we develop a debate summarization system to summarize key topics which are discussed or argued in the two opposing sides of online debates. We view that the generation of debate summaries can be achieved by clustering and visualization. In our work, we generate the summaries by applying an ontological term-based clustering and cluster labeling approach. We visualize the results using bar charts. We think that our results are a smooth entry for users aiming to receive the first impression about what is discussed within a debate topic containing a large number of argumentations.

Keywords: online debate summarization, text summarization, X-means clustering, term-based clustering, ontology

References

Download paper (PDF) Download BibTeX

BibTeX entry

@proceedings{2017_Sanchan_Aker_Bontcheva,
  author    = {Sanchan, Nattapong and Aker, Ahmet and Bontcheva, Kalina},
  title     = {Automatic Summarization of Online Debates},
  booktitle = {Proceedings of the 1st Workshop on Natural Language Processing and Information Retrieval associated with RANLP 2017},
  month     = {September},
  year      = {2017},
  address   = {Varna, Bulgaria},
  publisher = {INCOMA Inc.},
  pages     = {19--27},
  url       = {https://doi.org/10.26615/978-954-452-038-0_003}
}

Rich-text citation (copy & paste)

Sanchan, N., Aker, A., and Bontcheva, K. (2017). Automatic summarization of online debates. In Proceedings of the 1st Workshop on Natural Language Processing and Information Retrieval associated with RANLP 2017, pages 19–27, Varna, Bulgaria. INCOMA Inc.

More information

This paper is a continuing work in the Domain-Focused Summarization of Polarized Debates project: