Unsupervised Sentiment-Bearing Feature Selection for Document-Level Sentiment Classification

スポンサーリンク

概要

• 論文の詳細を見る

• Text sentiment classification aims to automatically classify subjective documents into different sentiment-oriented categories (e.g. positive/negative). Given the high dimensionality of features describing documents, how to effectively select the most useful ones, referred to as sentiment-bearing features, with a lack of sentiment class labels is crucial for improving the classification performance. This paper proposes an unsupervised sentiment-bearing feature selection method (USFS), which incorporates sentiment discriminant analysis (SDA) into sentiment strength calculation (SSC). SDA applies traditional linear discriminant analysis (LDA) in an unsupervised manner without losing local sentiment information between documents. We use SSC to calculate the overall sentiment strength for each single feature based on its affinities with some sentiment priors. Experiments, performed using benchmark movie reviews, demonstrated the superior performance of USFS.

• The Institute of Electronics, Information and Communication Engineersの論文

著者

• Li Yan

  School Of Chemistry & Chemical Engineering Jinan University

• QIN Zhen

  School of Information and Communication Engineering, Beijing University of Posts and Telecommunications

• GUO Jun

  School of Information and Communication Engineering, Beijing University of Posts and Telecommunications

• LI Yan

  School of Information and Communication Engineering, Beijing University of Posts and Telecommunications

• XU Weiran

  School of Information and Communication Engineering, Beijing University of Posts and Telecommunications

• JI Heng

  Rensselaer Polytechnic Institute (RPI)

関連論文

• Malnutrition improvement for infants under 18 months old of Dai minority in Luxi, China
• A Highly Sensitive and Rapid Assay for Protein Determination in Human Urine and Penicillin Using a Rayleigh Light-Scattering Technique with Benzeneazo-8-acetylamino-1-naphthol-3,6-disulfonic Acid Sodium Salt
• Pharmacokinetics and Tissue Distribution of Spinosin after Intravenous Administration in Rats
• Combination of HPLC chromatogram and hypoglycemic effect identifies isoflavones as the principal active fraction of Belamcanda chinensis leaf extract in diabetes treatment
• Unsupervised Sentiment-Bearing Feature Selection for Document-Level Sentiment Classification

スポンサーリンク