Domain-Specific Aspect-Sentiment Pair Extraction Using Rules and Compound Noun Lexicon for Customer Reviews

Online reviews are an important source of opinion to measure products’ quality. Hence, automated opinion mining is used to extract important features (aspect) and related comments (sentiment). Extraction of correct aspect-sentiment pairs is critical for overall outcome of opinion mining; however, current works still have limitations in terms of identifying special compound noun and parent-child relationship aspects in the extraction process. To address these problems, an aspect-sentiment pair extraction using the rules and compound noun lexicon (ASPERC) model is proposed. The model consists of three main phases, such as compound noun lexicon generation, aspect-sentiment pair rule generation, and aspect-sentiment pair extraction. The combined approach of rules generated from training sentences and domain specific compound noun lexicon enable extraction of more aspects by firstly identifying special compound noun and parent-child aspects, which eventually contribute to more aspect-sentiment pair extraction. The experiment is conducted with the SemEval 2014 dataset to compare proposed and baseline models. Both ASPERC and its variant, ASPER, result higher in recall (28.58% and 22.55% each) compared to baseline and satisfactorily extract more aspect sentiment pairs. Lastly, the reasonable outcome of ASPER indicates applicability of rules to various domains.

[1]  James R. Hurford.  Grammar: A Student's Guide , 1994 .

[2]  Lukasz Golab,et al.  Is the grass greener?: mining electric vehicle opinions , 2014, e-Energy.

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

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

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

[6]  L. Anthony,et al.  AntConc: design and development of a freeware corpus analysis toolkit for the technical writing classroom , 2005, IPCC 2005. Proceedings. International Professional Communication Conference, 2005..

[7]  Alice H. Oh,et al.  A Hierarchical Aspect-Sentiment Model for Online Reviews , 2013, AAAI.

[8]  Pierre André Ménard,et al.  Multiword noun compound bracketing using Wikipedia , 2014 .

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

[10]  Shibily Joseph,et al.  A syntactic approach for aspect based opinion mining , 2015, Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015).

[11]  Ales Tamchyna,et al.  ÚFAL: Using Hand-crafted Rules in Aspect Based Sentiment Analysis on Parsed Data , 2014, SemEval@COLING.

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

[13]  Jürgen Broß,et al.  Automatic construction of domain and aspect specific sentiment lexicons for customer review mining , 2013, CIKM.

[14]  Kim Schouten,et al.  Survey on Aspect-Level Sentiment Analysis , 2016, IEEE Transactions on Knowledge and Data Engineering.

[15]  ChengXiang Zhai,et al.  Comprehensive Review of Opinion Summarization , 2011 .

[16]  Hui Wang,et al.  Confidence Estimation and Reputation Analysis in Aspect Extraction , 2014, 2014 22nd International Conference on Pattern Recognition.

[17]  H. P. Luhn.  Key word‐in‐context index for technical literature (kwic index) , 1960 .

[18]  Ioannis Hatzilygeroudis,et al.  Aspect based sentiment analysis in social media with classifier ensembles , 2017, 2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS).

[19]  James H. Martin,et al.  Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition , 2000 .

[20]  Bing Liu,et al.  Sentiment Analysis and Opinion Mining , 2012, Synthesis Lectures on Human Language Technologies.

[21]  K. Raghuveer,et al.  Web User Opinion Analysis for Product Features Extraction and Opinion Summarization , 2012 .

[22]  Peng Xu,et al.  Using a Dependency Parser to Improve SMT for Subject-Object-Verb Languages , 2009, NAACL.

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

[24]  Jesse Davis,et al.  Automatically Detecting and Rating Product Aspects from Textual Customer Reviews , 2014, DMNLP@PKDD/ECML.

[25]  Pin Lv,et al.  A Bootstrapping Based Refinement Framework for Mining Opinion Words and Targets , 2014, CIKM.

[26]  Suresh Manandhar,et al.  SemEval-2014 Task 4: Aspect Based Sentiment Analysis , 2014, *SEMEVAL.