Lifelong Learning for Sentiment Classification
Authors:
Preprint
Abstract
This paper proposes a novel lifelong learning (LL) approach to sentiment classification. LL mimics the human continuous learning process, i.e., retaining the knowledge learned from past tasks and use it to help future learning. In this paper, we first discuss LL in general and then LL for sentiment classification in particular. The proposed LL approach adopts a Bayesian optimization framework based on stochastic gradient descent. Our experimental results show that the proposed method outperforms baseline methods significantly, which demonstrates that lifelong learning is a promising research direction.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Sentiment Analysis and Opinion MiningSynthesis Lectures on Human Language Technologies, 2012
- Integrating low-rank and group-sparse structures for robust multi-task learning2011
- Transfer Learning for Multiple-Domain Sentiment Analysis — Identifying Domain Dependent/Independent Word PolarityProceedings of the AAAI Conference on Artificial Intelligence, 2011
- Toward an Architecture for Never-Ending Language LearningProceedings of the AAAI Conference on Artificial Intelligence, 2010
- Using morphological and syntactic structures for Chinese opinion analysis2009
- Opinion Mining and Sentiment Analysis2008
- A novel scheme for domain-transfer problem in the context of sentiment analysis2007
- Learning and evaluating classifiers under sample selection bias2004
- Improving predictive inference under covariate shift by weighting the log-likelihood functionJournal of Statistical Planning and Inference, 2000