Sixing Wu

A hybrid unsupervised method for aspect term and opinion target extraction

Abstract Aspect term extraction (ATE) and opinion target extraction (OTE) are two important tasks in fine-grained sentiment analysis field. Existing approaches to ATE and OTE are mainly based on rules or machine learning methods. Rule-based methods are usually unsupervised, but they can’t make use of high level features. Although supervised learning approaches usually outperform the rule-based ones, they need a large number of labeled samples to train their models, which are expensive and time-consuming to annotate. In this paper, we propose a hybrid unsupervised method which can combine rules and machine learning methods to address ATE and OTE tasks. First, we use chunk-level linguistic rules to extract nominal phrase chunks and regard them as candidate opinion targets and aspects. Then we propose to filter irrelevant candidates based on domain correlation. Finally, we use these texts with extracted chunks as pseudo labeled data to train a deep gated recurrent unit (GRU) network for aspect term extraction and opinion target extraction. The experiments on benchmark datasets validate the effectiveness of our approach in extracting opinion targets and aspects with minimal manual annotation.

Sentiment Domain Adaptation with Multi-Level Contextual Sentiment Knowledge

Sentiment domain adaptation is widely studied to tackle the domain-dependence problem in sentiment analysis field. Existing domain adaptation methods usually train a sentiment classifier in a source domain and adapt it to the target domain using transfer learning techniques. However, when the sentiment feature distributions of the source and target domains are significantly different, the adaptation performance will heavily decline. In this paper, we propose a new sentiment domain adaptation approach by adapting the sentiment knowledge in general-purpose sentiment lexicons to a specific domain. Since the general sentiment words of general-purpose sentiment lexicons usually convey consistent sentiments in different domains, they have better generalization performance than the sentiment classifier trained in a source domain. In addition, we propose to extract various kinds of contextual sentiment knowledge from massive unlabeled samples in target domain and formulate them as sentiment relations among sentiment expressions. It can propagate the sentiment information in general sentiment words to massive domain-specific sentiment expressions. Besides, we propose a unified framework to incorporate these different kinds of sentiment knowledge and learn an accurate domain-specific sentiment classifier for target domain. Moreover, we propose an efficient optimization algorithm to solve the model of our approach. Extensive experiments on benchmark datasets validate the effectiveness and efficiency of our approach.

Automatic construction of target-specific sentiment lexicon

Abstract Sentiment lexicon plays an important role in sentiment analysis system. In most existing sentiment lexica, each sentiment word or phrase is given a sentiment label or score. However, a sentiment word may express different sentiment orientations describing different targets. It’s beneficial but challenging to incorporate knowledge of opinion targets into sentiment lexicon. In this paper we propose an automatic approach to construct a target-specific sentiment lexicon, in which each term is an opinion pair consisting of an opinion target and an opinion word. The approach solves two principle problems in construction process, namely, opinion target extraction and opinion pair sentiment classification. An unsupervised algorithm is proposed to extract opinion pairs in high quality. Both semantic feature and syntactic feature are incorporated in the algorithm, to extract opinion pairs containing correct opinion targets. A group of opinion pairs are generated and a framework is proposed to classify their sentiment polarities. Knowledge of available resources including general-purpose sentiment lexicon and thesaurus, and context knowledge including syntactic relations and sentiment information in sentences, are extracted and integrated in a unified framework to calculate sentiment scores of opinion pairs. Experimental results on product reviews datasets in different domains prove the effectiveness of our method in target-specific sentiment lexicon construction, which can improve performances of opinion target extraction and opinion pair sentiment classification. In addition, our lexicon also achieves better performance in target-level sentiment classification compared with several general-purpose sentiment lexicons.

Domain attention model for multi-domain sentiment classification

Abstract Sentiment classification is widely known as a domain-dependent problem. In order to learn an accurate domain-specific sentiment classifier, a large number of labeled samples are needed, which are expensive and time-consuming to annotate. Multi-domain sentiment analysis based on multi-task learning can leverage labeled samples in each single domain, which can alleviate the need for large amount of labeled data in all domains. In this paper, we propose a domain attention model for multi-domain sentiment analysis. In our approach, the domain representation is used as attention to select the most domain-related features in each domain. The domain representation is obtained through an auxiliary domain classification task, which works as domain regularizer. In this way, both shared and domain-specific features for sentiment classification are extracted simultaneously. In contrast with existing multi-domain sentiment classification methods, our approach can extract the most discriminative features from a shared hidden layer in a more compact way. Experimental results on two multi-domain sentiment datasets validate the effectiveness of our approach.