Summary of the paper
| Title | Learning Subjectivity Phrases missing from Resources through a Large Set of Semantic Tests |
|---|---|
| Authors | Matthieu Vernier, Laura Monceaux and Béatrice Daille |
| Abstract | In recent years, blogs and social networks have particularly boosted interestsfor opinion mining research. In order to satisfy real-scale applicative needs,a main task is to create or to enhance lexical and semantic resources onevaluative language. Classical resources of the area are mostly built forenglish, they contain simple opinion word markers and are far to cover thelexical richness of this linguistic phenomenon. In particular, infrequentsubjective words, idiomatic expressions, and cultural stereotypes are missingfrom resources. We propose a new method, applied on french, to enhanceautomatically an opinion word lexicon. This learning method relies onlinguistic uses of internet users and on semantic tests to infer the degree ofsubjectivity of many new adjectives, nouns, verbs, noun phrases, verbal phraseswhich are usually forgotten by other resources. The final appraisal lexiconcontains 3,456 entries. We evaluate the lexicon enhancement with and withouttextual context. |
| Language | Tools, systems, applications |
| Topics | Emotion Recognition/Generation, Lexicon, lexical database, Tools, systems, applications |
Full paper  |
Learning Subjectivity Phrases missing from Resources through a Large Set of Semantic Tests |
| Bibtex | @InProceedings{VERNIER10.208, author = {Matthieu Vernier, Laura Monceaux and Béatrice Daille}, title = {Learning Subjectivity Phrases missing from Resources through a Large Set of Semantic Tests}, 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} } |