Article ID Journal Published Year Pages File Type
385434 Expert Systems with Applications 2011 7 Pages PDF
Abstract

Supervised sentiment classification systems are typically domain-specific, and the performance decreases sharply when transferred from one domain to another domain. Building these systems involves annotating a large amount of data for every domain, which needs much human labor. So, a reasonable way is to utilize labeled data in one existed (or called source) domain for sentiment classification in target domain. To address this problem, we propose a two-stage framework for cross-domain sentiment classification. At the “building a bridge” stage, we build a bridge between the source domain and the target domain to get some most confidently labeled documents in the target domain; at the “following the structure” stage, we exploit the intrinsic structure, revealed by these most confidently labeled documents, to label the target-domain data. The experimental results indicate that the proposed approach could improve the performance of cross-domain sentiment classification dramatically.

► Propose a two-stage framework for sentiment classification. ► Build a bridge between the source and target domain. ► Exploit the intrinsic structure. ► Experimental results indicate the efficiency of proposed approach.

Related Topics
Physical Sciences and Engineering Computer Science Artificial Intelligence
Authors
, ,