Summary of the paper

Title Automatically Identifying Changes in the Semantic Orientation of Words
Authors Paul Cook and Suzanne Stevenson
Abstract The meanings of words are not fixed but in fact undergo change, with new wordsenses arising and established senses taking on new aspects of meaning orfalling out of usage. Two types of semantic change are amelioration andpejoration; in these processes a word sense changes to become more positive ornegative, respectively. In this first computational study of amelioration andpejoration we adapt a web-based method for determining semantic orientation tothe task of identifying ameliorations and pejorations in corpora from differingtime periods. We evaluate our proposed method on a small dataset of knownhistorical ameliorations and pejorations, and find it to perform better than arandom baseline. Since this test dataset is small, we conduct a furtherevaluation on artificial examples of amelioration and pejoration, and againfind evidence that our proposed method is able to identify changes in semanticorientation. Finally, we conduct a preliminary evaluation in which we applyour methods to the task of finding words which have recently undergoneamelioration or pejoration.
Language Acquisition
Topics Lexicon, lexical database, Semantics, Acquisition
Full paper Automatically Identifying Changes in the Semantic Orientation of Words
Bibtex @InProceedings{COOK10.657,
  author = {Paul Cook and Suzanne Stevenson},
  title = {Automatically Identifying Changes in the Semantic Orientation of Words},
  booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)},
  year = {2010},
  month = {may},
  date = {19-21},
  address = {Valletta, Malta},
  editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {2-9517408-6-7},
  language = {english}
 }
Powered by ELDA © 2010 ELDA/ELRA