Summary of the paper
| Title | Predictive Features for Detecting Indefinite Polar Sentences |
|---|---|
| Authors | Michael Wiegand and Dietrich Klakow |
| Abstract | In recent years, text classification in sentiment analysis has mostly focusedon two types of classification, the distinction between objectiveand subjective text, i.e. subjectivity detection, and the distinction betweenpositive and negative subjective text, i.e. polarity classification.So far, there has been little work examining the distinction between definitepolar subjectivity and indefinite polar subjectivity. Whilethe former are utterances which can be categorized as either positive ornegative, the latter cannot be categorized as either of these twocategories. This paper presents a small set of domain independent features todetect indefinite polar sentences. The features reflect thelinguistic structure underlying these types of utterances. We give evidence forthe effectiveness of these features by incorporating theminto an unsupervised rule-based classifier for sentence-level analysis andcompare its performance with supervised machine learningclassifiers, i.e. Support Vector Machines (SVMs) and Nearest NeighborClassifier (kNN). Thedata used for the experiments are web-reviews collectedfrom three different domains. |
| Language | Semantics |
| Topics | Document Classification, Text categorisation, Information Extraction, Information Retrieval, Semantics |
Full paper  |
Predictive Features for Detecting Indefinite Polar Sentences |
| Bibtex | @InProceedings{WIEGAND10.362, author = {Michael Wiegand and Dietrich Klakow}, title = {Predictive Features for Detecting Indefinite Polar Sentences}, 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} } |