Incorporating conditional random fields and active learning to improve sentiment identification

Kunpeng Zhang, Yusheng Xie*, Yi Yang, Aaron Sun, Hengchang Liu, Alok Choudhary

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

25 Scopus citations

Abstract

Many machine learning, statistical, and computational linguistic methods have been developed to identify sentiment of sentences in documents, yielding promising results. However, most of state-of-the-art methods focus on individual sentences and ignore the impact of context on the meaning of a sentence. In this paper, we propose a method based on conditional random fields to incorporate sentence structure and context information in addition to syntactic information for improving sentiment identification. We also investigate how human interaction affects the accuracy of sentiment labeling using limited training data. We propose and evaluate two different active learning strategies for labeling sentiment data. Our experiments with the proposed approach demonstrate a 5%-15% improvement in accuracy on Amazon customer reviews compared to existing supervised learning and rule-based methods.

Original languageEnglish (US)
Pages (from-to)60-67
Number of pages8
JournalNeural Networks
Volume58
DOIs
StatePublished - Oct 2014

Keywords

  • Active learning
  • Conditional random fields
  • Customer reviews
  • Sentiment analysis

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Incorporating conditional random fields and active learning to improve sentiment identification'. Together they form a unique fingerprint.

Cite this