Appraisal expression extraction based on semantic and dependency parsing
Authors: 
Longmao Hu, Bingwu Fang, Xuegang HuAuthors Info & Claims
Longmao Hu, Bingwu Fang, Xuegang HuAuthors Info & ClaimsArticle No.: 66, Pages 1 - 8
Abstract
Fine-grained sentiment analysis of online product reviews is important to both potential consumers and sellers. Automatically extracting appraisal expressions from online reviews is one of the key issues in fine-grained sentiment analysis. The existing method of using conditional random fields (CRF) extraction has achieved good results, but the mining of semantic features is not deep enough. On the basis of in-depth analysis of the semantic information of online reviews, we propose four semantic features, which are related word, distance from the beginning of sentence, forward-pointed turning word and backward-pointed adverb. CRF model with our features and traditional features is used to extract the appraisal expressions, then dependency parsing rules are used to supplement opinion phrases corresponding to isolated opinion targets. Experimental results on the mobile phone reviews corpus show that the accuracy of the proposed method is greatly improved compared with the baseline method 1. Compared with the baseline method 2, the accuracy of the method is not improved obviously, but the cost of manually marking the corpus is saved.
References
[1]
H Nie, T Li, H He, M Liu and H Shou (2018). Automatic acquisition of business competition intelligence based on online reviews. Journal of Intelligence, 37(10), 167--173+188.
[2]
K Dave, S Lawrence and D M Pennock (2003). Mining the Peanut gallery: opinion extraction and semantic classification of product reviews. Journal of Biological Chemistry, 289(51), 35326--40.
[3]
M Hu and B Liu (2004). Mining and summarizing customer reviews. In Proc of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, pages 168--177.
[4]
N Jakob and I Gurevych (2010). Extracting Opinion Targets in a Single- and Cross-Domain Setting with Conditional. In EMNLP, pages 1035--1045.
[5]
A M Popescu and O Etzioni (2005). Extracting product features and opinions from reviews. In Proceedings of the Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 339--346.
[6]
K Bloom, N Garg and S Argamon (2007). Extracting appraisal expressions. In The Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 308--315.
[7]
C Liu, L Han and D Li (2017). Research of product feature-opinion extraction and sentiment analysis based on Chinese chunk parsing. Application Research of Computers, 34(10), 2942--2945.
[8]
Y Meng and H Wang (2016). Extracting Product Feature and User Opinion from Chinese Reviews. New Technology of Library and Information Service, 32(02), 16--24.
[9]
X Tang and Y Liu (2018). Cross-lingual Fine-grained Sentiment Analysis Based on Dependency Parsing. Information Studies: Theory & Application, 41(06), 124--129.
[10]
T Jiang, C Wan, D Liu, X Liu and G Liao (2017). Extracting Target-Opinion Pairs Based on Semantic Analysis. Chinese Journal of Computers, 40(03), 617--633.
[11]
Y He and S He (2018). Sentiment Mining of Online Product Reviews Based on Domain Ontology. Data Analysis and Knowledge Discovery, 2(08), 60--68.
[12]
Y Jo and A H Oh (2011). Aspect and sentiment unification model for online review analysis. In Proceedings of the 4th ACM International Conference on Web Search and Data Mining, pages 815--824.
[13]
Y Peng, C Wan, T Jiang, D Liu and G Liao (2017). Extracting Product Aspects and User Opinions Based on Semantic Constrained LDA Model. Journal of Software, 28(3), 676--693.
[14]
W Wang, S Pan, D Dahlmeier and X Xiao (2016). Recursive neural conditional random fields for aspect-based sentiment analysis. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 616--626.
[15]
Y Shen, X Huang and J Cao (2018). Joint Extraction of Opinion Targets and Opinion Words Based on LSTM. Journal of Chinese Information Processing, 32(2), 110--119.
[16]
C Liao, C Feng, S Yang and H Huang (2016). A Hybrid Method of Domain Lexicon Construction for Opinion Targets Extraction Using Syntax and Semantics. Journal of Computer Science and Technology, 31(3), 595--603.
[17]
Z Zhang and Y Zhao (2018). Opinion Target Extraction Based on Semantic and Syntactic Dependency. Journal of Chinese Information Processing, 32(06), 80--87+97.
[18]
X Sun and C Tang (2015). Fine-Grained Emotional Elements Extraction and Affection Analysis Based on Cascaded Model. Pattern Recognition and Artificial Intelligence, 28(06), 513--520.
[19]
L Liu, Y Wang and H Wei (2015). Fine-grained sentiment analysis oriented to product comment. Computer Applications, 35(12), 3481--3486+3505.
[20]
X Ma, S Jin and S Yang (2015). Opinion Mining of Chinese E-commerce Platform Products Comments---Empirical Research Based On Conditional Random Field. Journal of Systems Science and Complexity, 35(11), 1327--1346.
[21]
Z Li, M Wang and P Zhao (2017). Study on the Extraction of 'Opinion Feature-Opinion Word' Based on Conditional Random Fields Model. Journal of the China Society for Scientific and Technical Information, 36(04), 411--421.
[22]
W Wang, H Wang and X Sheng (2017). Extracting product features and opinions from Chinese online reviews: A comparative study on multi-domains. Journal of Industrial Engineering and Engineering Management, 31(04), 52--62.
[23]
J Tian and W Zhao (2010). Words Similarity Algorithm Based on Tongyici Cilin in Semantic Adaptive Web Learning System. Journal of Jilin University (Information Science Edition), 28(02), 602--608.
[24]
H Chen, F Fei, X Zhu and R Ma (2016). A Path and Depth---Based Approach to Word Semantic Similarity Calcalation in CiLin. Journal of Chinese Information Processing, 20(05), 80--88.
[25]
L Liu, X Zhao, H Wang, X Nie and W Song (2015). Constructing Domain Affective Ontology Based on Product Features. Journal of Beijing Institute of Technology, 25(5), 538--544.
[26]
H Zhou, M Hou, P Yan, Y Zhang, M Hou and Y Teng (2014). Function of Semantic Features in Opinion Target Extraction and Its Polarity Identification. Acta Scientiarum Naturalium Universitatis Pekinensis, 50(1), 93--99.
[27]
Universal Dependencies contributors, "Universal Dependency Relations," [Online]. Available: http://universaldependencies.org/u/dep/index.html. [Accessed Aug. 23, 2019].
Index Terms
- Appraisal expression extraction based on semantic and dependency parsing
Recommendations
CoreNLP dependency parsing and pattern identification for enhanced opinion mining in aspect-based sentiment analysis
AbstractAspect-Based Sentiment Analysis (ABSA) aims to identify the sentiment expressed towards a specific feature or aspect of a given text. Although certain ABSA techniques employ syntactic information to capture the connection between the opinion ...
Highlights- The ABSA method leverages syntax, semantics, and CoreNLP’s parsing to gauge aspect sentiment.
- Captures the aspect polarity by identifying patterns and extracting critical relations.
- The method outperforms ABSA approaches using ...
Extraction of Chinese "Opinion target - Opinion word" Pairs Based on Part-of-speech Rules and Semantic Dependency Parsing
ICBIM '18: Proceedings of the 2nd International Conference on Business and Information ManagementDue to the non-standardization of online comments, it is difficult to extract the "opinion target - opinion word" pairs. This paper proposes a method of extracting the "opinion target - opinion word" pairs based on part-of-speech rules and semantic ...
A Study on Semantic Features of Antonymous Verbs Based on Lexical Knowledge System
Chinese Lexical SemanticsAbstractExtraction of lexical semantic features is a key issue in lexical knowledge research. Based on the connectionism theory, this paper adopts the corpus and statistical approach to analyze the semantic features of antonymous verbs and construct their ...
Comments
Information & Contributors
Information
Published In
December 2019
464 pages
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
- ASciE: Association for Science and Engineering
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 19 December 2019
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Key Project of Natural Science Fund of Anhui Higher Education Institutions
Conference
AIIPCC '19
Sponsor:
- ASciE
AIIPCC '19: 2019 International Conference on Artificial Intelligence, Information Processing and Cloud Computing
December 19 - 21, 2019
Sanya, China
Acceptance Rates
AIIPCC '19 Paper Acceptance Rate 78 of 211 submissions, 37%;
Overall Acceptance Rate 78 of 211 submissions, 37%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 47Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 28 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in