An Unsupervised Aspect-Sentiment Model for Online Reviews

By Samuel Brody, Noémie Elhadad. North American Chapter of the Association for Computational Linguistics, 2010

562 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b1eb39722b3577c46e41572099dcaad74ce43753

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. B. Liu
2. Hu Xu
3. Bing Liu
4. Lei Shu
5. Saif M. Mohammad
6. Julian McAuley
7. Erik Cambria
8. Jure Leskovec

Citations in the corpus

• Improving the quality of predictions using textual information in online user reviews (2013, methodology): “In [6], the authors present an unsupervised text classification technique for the Citysearch restaurant reviews data set used in this paper.”
• Using Summarization to Discover Argument Facets in Online Idealogical Dialog (2017, background): “There appears to be similarity between FACET induction and aspect learning in sentiment analysis (Brody and Elhadad, 2010), but FACETS are propositional abstract objects, while aspects can usually be described as nouns or properties.”
• Mining Aspect-Specific Opinion using a Holistic Lifelong Topic Model (2016, unknown): “There are also many topic models that have been used for the task of aspect extraction and categorization in, for example, [4, 11, 24, 28, 49, 27, 32, 33, 43, 10, 5, 14, 22, 23, 30, 45, 46].”
• An Unsupervised Neural Attention Model for Aspect Extraction (2017, methodology): “Following (Brody and Elhadad, 2010; Zhao et al., 2010), we set the number of aspects for the restaurant corpus to 14.”
• Lifelong Learning CRF for Supervised Aspect Extraction (2017, background): “, 2014), topic modeling (Mei et al., 2007; Titov and McDonald, 2008; Li et al., 2010; Brody and Elhadad, 2010; Wang et al., 2010; Moghaddam and Ester, 2011; Mukherjee and Liu, 2012; Lin and He, 2009; Zhao et al., 2010; Jo and Oh, 2011; Fang and Huang, 2012; Wang et al., 2016), word alignment (Liu et”
• Exploiting Topic based Twitter Sentiment for Stock Prediction (2013, background): “…in its extended forms in sentiment analysis and many other tasks (Mei et al., 2007; Branavan et al., 2008; Lin and He, 2009; Zhao et al., 2010; Wang et al., 2010; Brody and Elhadad, 2010; Jo and Oh, 2011; Moghaddam and Ester, 2011; Sauper et al., 2011; Mukherjee and Liu, 2012; He et al., 2012).”
• Inferring Networks of Substitutable and Complementary Products (2015, background): “A variety of works have used topic models within recommender systems ( e.g. [6, 10, 11, 22, 23, 28, 31, 32]), though generally with the goal of predicting user ratings (or opinions) rather than learning relationships between products as we do here.”
• Hidden factors and hidden topics: understanding rating dimensions with review text (2013, background): “Furthermore, although related to our work, the goal of such studies is typically summarization [5, 13, 18], or feature discovery [23], rather than rating prediction per se.”
• SemEval-2014 Task 4: Aspect Based Sentiment Analysis (2014, background): “Previous publicly available ABSA benchmark datasets adopt different annotation schemes within different tasks.”
• Simultaneously Discovering and Quantifying Risk Types from Textual Risk Disclosures (2014, methodology): “Despite its simplicity, this method, called local-LDA (Brody and Elhadad 2010), has been demonstrated to be effective in discovering meaningful topics while summarizing consumer reviews.”
• Aspect Extraction through Semi-Supervised Modeling (2012, background): “…(i.e., discovering positive and negative aspect words and/or sentiments for each aspect without separating aspect and sentiment terms) (Lin and He, 2009; Brody and Elhadad, 2010, Jo and Oh, 2011) and separately discovering both aspects and sentiments (e.g., Mei et al., 2007; Zhao et al., 2010).”
• Jointly Modeling Aspects and Opinions with a MaxEnt-LDA Hybrid (2010, methodology): “Brody and Elhadad (2010) also only used these three aspects for quantitative evaluation.”
• SemEval-2015 Task 12: Aspect Based Sentiment Analysis (2015, methodology): “Typically, most methods treat aspect extraction and sentiment classification separately (Brody and Elhadad, 2010), but there are also approaches that model the two problems jointly (Jo and Oh, 2011).”
• Learning Attitudes and Attributes from Multi-aspect Reviews (2012, methodology): “We assume that each sentence in a review discusses a single aspect; alternately we could model one aspect per word or per paragraph , though one aspect per sentence matches what appears in existing work [5], [12], [30].”
• Survey on Aspect-Level Sentiment Analysis (2016, background): “(2010) [76] restaurant [77] & ternary + aspect identification avg.”
• A Survey of Opinion Mining and Sentiment Analysis (2012, background): “Brody and Elhadad [10] proposed to first identify aspects using topic models and then identify aspect-specific opinion words by considering adjectives only.”