Knowledge empowered prominent aspect extraction from product reviews

Abstract Many existing systems for analyzing and summarizing customer reviews about products or service are based on a number of prominent review aspects. Conventionally, the prominent review aspects of a product type are determined manually. This costly approach cannot scale to large and cross-domain services such as Amazon.com, Taobao.com or Yelp.com where there are a large number of product types and new products emerge almost everyday. In this paper, we propose a novel method empowered by knowledge sources such as Probase and WordNet, for extracting the most prominent aspects of a given product type from textual reviews. The proposed method, ExtRA (Extraction of Prominent Review Aspects), (i) extracts the aspect candidates from text reviews based on a data-driven approach, (ii) builds an aspect graph utilizing the Probase to narrow the aspect space, (iii) separates the space into reasonable aspect clusters by employing a set ofproposed algorithms and finally (iv) generates K most prominent aspect terms or phrases which do not overlap semantically automatically without supervision from those aspect clusters. ExtRA extracts high-quality prominent aspects as well as aspect clusters with little semantic overlap by exploring knowledge sources. ExtRA can extract not only words but also phrases as prominent aspects. Furthermore, it is general-purpose and can be applied to almost any type of product and service. Extensive experiments show that ExtRA is effective and achieves the state-of-the-art performance on a dataset consisting of different product types.

[1]  P. Deepa Shenoy,et al.  Aspect term extraction for sentiment analysis in large movie reviews using Gini Index feature selection method and SVM classifier , 2016, World Wide Web.

[2]  Mohammad Tubishat,et al.  Implicit aspect extraction in sentiment analysis: Review, taxonomy, oppportunities, and open challenges , 2018, Inf. Process. Manag..

[3]  Andi Rexha,et al.  An unsupervised aspect extraction strategy for monitoring real-time reviews stream , 2019, Inf. Process. Manag..

[4]  Qian Liu,et al.  Improving Opinion Aspect Extraction Using Semantic Similarity and Aspect Associations , 2016, AAAI.

[5]  Quang-Phuoc Nguyen,et al.  Automatic Knowledge Extraction for Aspect-based Sentiment Analysis of Customer Reviews , 2018, ICCMS 2018.

[6]  Amélie Marian,et al.  Beyond the Stars: Improving Rating Predictions using Review Text Content , 2009, WebDB.

[7]  Timothy Baldwin,et al.  Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-Based Sentiment Analysis , 2018, NAACL.

[8]  Noémie Elhadad,et al.  An Unsupervised Aspect-Sentiment Model for Online Reviews , 2010, NAACL.

[9]  Xiaokui Xiao,et al.  Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis , 2016, EMNLP.

[10]  ChengXiang Zhai,et al.  Learning online discussion structures by conditional random fields , 2011, SIGIR.

[11]  Ming Zhou,et al.  Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification , 2014, ACL.

[12]  Oren Etzioni,et al.  Extracting Product Features and Opinions from Reviews , 2005, HLT.

[13]  Yu-N Cheah,et al.  A two-fold rule-based model for aspect extraction , 2017, Expert Syst. Appl..

[14]  Martin Ester,et al.  On the design of LDA models for aspect-based opinion mining , 2012, CIKM.

[15]  Thomas Hofmann,et al.  Probabilistic Latent Semantic Indexing , 1999, SIGIR Forum.

[16]  Chen Gui,et al.  A Rule-Based Approach to Aspect Extraction from Product Reviews , 2014, SocialNLP@COLING.

[17]  Hongfei Yan,et al.  Jointly Modeling Aspects and Opinions with a MaxEnt-LDA Hybrid , 2010, EMNLP.

[18]  Haixun Wang,et al.  Probase: a probabilistic taxonomy for text understanding , 2012, SIGMOD Conference.

[19]  Ahmad Baraani-Dastjerdi,et al.  Enriched LDA (ELDA): Combination of latent Dirichlet allocation with word co-occurrence analysis for aspect extraction , 2017, Expert Syst. Appl..

[20]  Yu-N Cheah,et al.  Improving Aspect Extraction Using Aspect Frequency and Semantic Similarity-Based Approach for Aspect-Based Sentiment Analysis , 2017, IC2IT.

[21]  Yue Lu,et al.  Latent aspect rating analysis without aspect keyword supervision , 2011, KDD.

[22]  Chun Chen,et al.  Opinion Word Expansion and Target Extraction through Double Propagation , 2011, CL.

[23]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[24]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[25]  Chuhan Wu,et al.  A hybrid unsupervised method for aspect term and opinion target extraction , 2018, Knowl. Based Syst..

[26]  Ivan Titov,et al.  Modeling online reviews with multi-grain topic models , 2008, WWW.

[27]  John Pavlopoulos,et al.  Aspect Term Extraction for Sentiment Analysis: New Datasets, New Evaluation Measures and an Improved Unsupervised Method , 2014 .

[28]  Yue Lu,et al.  Latent aspect rating analysis on review text data: a rating regression approach , 2010, KDD.

[29]  Xinying Xu,et al.  Hidden sentiment association in chinese web opinion mining , 2008, WWW.

[30]  Xiaocheng Feng,et al.  Effective LSTMs for Target-Dependent Sentiment Classification , 2015, COLING.

[31]  Jiafeng Guo,et al.  BTM: Topic Modeling over Short Texts , 2014, IEEE Transactions on Knowledge and Data Engineering.

[32]  Erik Cambria,et al.  Aspect extraction for opinion mining with a deep convolutional neural network , 2016, Knowl. Based Syst..

[33]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[34]  Qian Liu,et al.  Automated Rule Selection for Aspect Extraction in Opinion Mining , 2015, IJCAI.

[35]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[36]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[37]  Yulan He,et al.  Joint sentiment/topic model for sentiment analysis , 2009, CIKM.

[38]  Gerard de Melo,et al.  Sentiment-Aspect Extraction based on Restricted Boltzmann Machines , 2015, ACL.

[39]  Himabindu Lakkaraju,et al.  Exploiting Coherence for the Simultaneous Discovery of Latent Facets and associated Sentiments , 2011, SDM.

[40]  Erik Cambria,et al.  Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM , 2018, AAAI.

[41]  Arno Scharl,et al.  Rule-based opinion target and aspect extraction to acquire affective knowledge , 2013, WWW '13 Companion.

[42]  Fang Li,et al.  A Classification-Based Approach for Implicit Feature Identification , 2013, CCL.

[43]  Martin Ester,et al.  ILDA: interdependent LDA model for learning latent aspects and their ratings from online product reviews , 2011, SIGIR.

[44]  Philip S. Yu,et al.  A holistic lexicon-based approach to opinion mining , 2008, WSDM '08.

[45]  Xiaokui Xiao,et al.  Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms , 2017, AAAI.