mirage   mirage   mirage

On feature relevance feedback methods : incorporating labeled user features

DSpace/Manakin Repository

Show simple item record

dc.contributor.advisor Wong, Weng-Keen
dc.creator Oberst, Ian
dc.date.accessioned 2010-08-06T15:42:15Z
dc.date.available 2010-08-06T15:42:15Z
dc.date.copyright 2010-06-07
dc.date.issued 2010-08-06T15:42:15Z
dc.identifier.uri http://hdl.handle.net/1957/17411
dc.description Graduation date: 2011 en
dc.description.abstract In text classification, labeling features is often less time consuming than labeling entire documents. In situations where very little labeled training data is available, feature relevance feedback has the potential to dramatically increase classification performance. We review previous work on incorporating feature relevance feedback in the form of labeled features and introduce a new method, the Feature Contrast Method, for using feature relevance feedback with locally weighted logistic regression. We show that our method is responsive to user feedback and significantly outperforms previously developed feature relevance feedback methods while remaining robust to noise in feature and training data. We also highlight several key issues that affect the performance of feature feedback methods. en
dc.language.iso en_US en
dc.subject feature relevance feedback en
dc.subject logistic regression en
dc.subject locally weighted logistic regression en
dc.subject user feedback en
dc.subject machine learning en
dc.subject feature contrast method en
dc.subject support vector machine en
dc.subject.lcsh Information retrieval en
dc.title On feature relevance feedback methods : incorporating labeled user features en
dc.type Thesis/Dissertation en
dc.degree.name Master of Science (M.S.) in Computer Science en
dc.degree.level Master's en
dc.degree.discipline Engineering en
dc.degree.grantor Oregon State University en
dc.contributor.committeemember Dietterich, Thomas
dc.contributor.committeemember Burnett, Margaret
dc.contributor.committeemember Lachenbruch, Peter

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record

Search ScholarsArchive@OSU

Advanced Search


My Account