Conference Paper

Aspect and sentiment unification model for online review analysis

DOI: 10.1145/1935826.1935932 Conference: Proceedings of the Forth International Conference on Web Search and Web Data Mining, WSDM 2011, Hong Kong, China, February 9-12, 2011
Source: DBLP


User-generated reviews on the Web contain sentiments about detailed aspects of products and services. However, most of the reviews are plain text and thus require much effort to obtain information about relevant details. In this paper, we tackle the problem of automatically discovering what aspects are evaluated in reviews and how sentiments for different aspects are expressed. We first propose Sentence-LDA (SLDA), a probabilistic generative model that assumes all words in a single sentence are generated from one aspect. We then extend SLDA to Aspect and Sentiment Unification Model (ASUM), which incorporates aspect and sentiment together to model sentiments toward different aspects. ASUM discovers pairs of {aspect, sentiment} which we call senti-aspects. We applied SLDA and ASUM to reviews of electronic devices and restaurants. The results show that the aspects discovered by SLDA match evaluative details of the reviews, and the senti-aspects found by ASUM capture important aspects that are closely coupled with a sentiment. The results of sentiment classification show that ASUM outperforms other generative models and comes close to supervised classification methods. One important advantage of ASUM is that it does not require any sentiment labels of the reviews, which are often expensive to obtain.

Download full-text


Available from: Alice Oh, Oct 31, 2014
  • Source
    • "Li et al. [14] presented a sentiment-LDA model for sentiment classification with global topics and local dependency. Jo and Oh [15] proposed two models, Sentence-LDA (SLDA) and Aspect and Sentiment Unification Model (ASUM) to tackle the problem of automatically discovering what aspects are evaluated in reviews and how sentiments for different aspects are expressed. Although LDA has been applied to sentiment classification for many years, there is little effort done to explore the order relationships among topics. "

    Preview · Article · Jan 2016
  • Source
    • "After extracting all aspect expressions, additional efforts are required to categorize domain synonyms into the same aspect. Another line of related work applies variants of standard topic modeling such as LDA (Titov and McDonald, 2008; Christina et al., 2011; Brody and Elhadad, 2010; Zhao et al., 2010; Jo and Oh, 2011; Moghaddam and Ester, 2012; Chen et al., 2014; Mukherjee and Liu, 2012; Kim et al., 2013; Sauper and Barzilay, 2013). Topic modeling deals with implicit aspects to some degree, and simulta- Figure 2. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper considers Aspect-based Opinion Summarization (AOS) of reviews on particular products. To enable real applications, an AOS system needs to address two core subtasks, aspect extraction and sentiment classification. Most existing approaches to aspect extraction, which use linguistic analysis or topic modeling, are general across different products but not precise enough or suitable for particular products. Instead we take a less general but more precise scheme, directly mapping each review sentence into pre-defined aspects. To tackle aspect mapping and sentiment classification, we propose two Convolutional Neural Network (CNN) based methods, cascaded CNN and multitask CNN. Cascaded CNN contains two levels of convolutional networks. Multiple CNNs at level 1 deal with aspect mapping task, and a single CNN at level 2 deals with sentiment classification. Multitask CNN also contains multiple aspect CNNs and a sentiment CNN, but different networks share the same word embeddings. Experimental results indicate that both cascaded and multitask CNNs outperform SVM-based methods by large margins. Multitask CNN generally performs better than cascaded CNN.
    Preview · Article · Nov 2015
  • Source
    • "Topic Modeling in Reviews Data: Another emerging body of work applies probabilistic topic models on reviews data to extract appraisal aspects and the corresponding specific sentiment lexicon. These kinds of models are usually referred to as joint sentiment/aspect topic models (Jo and Oh, 2011; Titov and McDonald, 2008; Zhao, Jiang, Yan and Li, 2010). Lin and He (2009) propose the Joint Sentiment Topic Model (JST) to model the dependency between sentiment and topics. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This work proposes an unsupervised method intended to enhance the quality of opinion mining in contentious text. It presents a Joint Topic Viewpoint (JTV) probabilistic model to analyze the underlying divergent arguing expressions that may be present in a collection of contentious documents. It extends the original Latent Dirichlet Allocation, which makes it domain and thesaurus independent, e.g., does not rely on WordNet coverage. The conceived JTV has the potential of automatically carrying the tasks of extracting associated terms denoting an arguing expression, according to the hidden topics it discusses and the embedded viewpoint it voices. Furthermore, JTV’s structure enables the unsupervised grouping of obtained arguing expressions according to their viewpoints, using a constrained clustering approach. Experiments are conducted on three types of contentious documents: polls, online debates and editorials. The qualitative and quantitative analyses of the experimental results show the effectiveness of our model to handle six different contentious issues when compared to a state-of-the-art method. Moreover, the ability to automatically generate distinctive and informative patterns of arguing expressions is demonstrated. Furthermore, the coherence of these arguing expressions is proved to be of a high quality when evaluated on the basis of recently introduced automatic coherence measure.
    Full-text · Article · Oct 2015 · Knowledge and Information Systems
Show more