Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/www2012/poster/9> ?p ?o. }
Showing items 1 to 16 of
16
with 100 items per page.
- 9 creator aoying-zhou.
- 9 creator jingwei-zhang.
- 9 creator xiaoling-wang.
- 9 creator yuming-lin.
- 9 type InProceedings.
- 9 label "Sentiment Classification via Integrating Multiple Feature Presentations".
- 9 sameAs 9.
- 9 abstract "In general, the documents are converted into vectors accordingto predefined features together with weighting mechanism.But each feature presentation has its character and it isdifficult to perform very well for all domains. It is hard todetermine which one should be chosen for a specific domain,especially for the users who are not familiar with the domain.This paper explores the integration of various featurepresentations in order to improve the classification accuracy.A general two phases framework is proposed. In the firstphase, we train multiple base classifiers with various vectorspaces and use these classifiers to predict the class of testingsamples respectively. In the second phase, the previouspredicted results are integrated into the ultimate class viastacking with SVM. The experimental results demonstratethe effectiveness of our solution.".
- 9 hasAuthorList authorList.
- 9 isPartOf proceedings.
- 9 isPartOf proceedings.
- 9 keyword "base classifiers".
- 9 keyword "integrating".
- 9 keyword "multiple feature presentations".
- 9 keyword "sentiment classification".
- 9 title "Sentiment Classification via Integrating Multiple Feature Presentations".