Abstract: We investigate whether one can determine from the transcripts of U.S. Congressional floor debates whether the speeches represent support of or opposition to proposed legislation. To address this problem, we exploit the fact that these speeches occur as part of a discussion; this allows us to use sources of information regarding relationships between discourse segments, such as whether a given utterance indicates agreement with the opinion expressed by another. We find that the incorporation of such information yields substantial improvements over classifying speeches in isolation.

Paper formats: ps, pdf. The versions posted are December 2006 updates to the originally published version; changes from the EMNLP 2006 paper are clearly marked.

Data: http://www.cs.cornell.edu/home/llee/data/convote.html

BibTeX entry:

@InProceedings{Thomas+Pang+Lee:06a,
  author =       {Matt Thomas and Bo Pang and Lillian Lee},
  title =        {Get out the vote: {Determining}  support or opposition from
  {Congressional} floor-debate transcripts},
  booktitle =    {Proceedings of EMNLP},
  pages={327--335},
  year =         2006
}