A Knowledge-Driven Approach for Automatic Semantic Aspect Term Extraction Using the Semantic Power of Linked Open Data
Source abstract
Abstract
Aspect-Based Sentiment Analysis (ABSA) is a crucial process for assessing customer feedback and gauging satisfaction with products or services. It typically consists of three stages: Aspect Term Extraction (ATE), Aspect Categorization Extraction (ACE), and Sentiment Analysis (SA). Various techniques have been proposed for ATE, including unsupervised, supervised, and hybrid methods. However, many studies face challenges in detecting aspect terms due to reliance on training data, which may not cover all multiple aspect terms and relate semantic aspect terms effectively. This study presents a knowledge-driven approach to automatic semantic aspect term extraction from customer feedback using Linked Open Data (LOD) to enrich aspect extraction outcomes in the training dataset. Additionally, it utilizes the N-gram model to capture complex text patterns and relationships, facilitating accurate classification and analysis of multiple-word terms for each aspect. To assess the effectiveness of the proposed model, experiments were conducted on three benchmark datasets: SemEval 2014, 2015, and 2016. Comparative evaluations with contemporary unsupervised, supervised, and hybrid methods on these datasets yielded F-measures of 0.80, 0.76, and 0.77, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sentiment Analysis and Opinion Mining · Advanced Text Analysis Techniques · Text and Document Classification Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Applied Intelligence and Data Analytics (AIDA) Laboratory, College of Computing, Khon Kaen University, Khon Kaen 40002, Thailand
References (64)
Show source-provided references
1. Fleisher, C.S., and Bensoussan, B.E. (2003). Strategic and Competitive Analysis: Methods and Techniques for Analyzing Business Competition, Prentice Hall.
2. Price competition and store competition: Store brands vs. national brand10.1016/j.ejor.2012.07.016 ↗
3. Salinca, A. (2015, January 21–24). Business reviews classification using sentiment analysis. Proceedings of the 2015 17th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), Timisoara, Romania.10.1109/SYNASC.2015.46 ↗
4. Hu, M., and Liu, B. (2004, January 22–25). Mining and summarizing customer reviews. Proceedings of the tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, WA, USA.10.1145/1014052.1014073 ↗
5. Liu, B. (2020). Sentiment Analysis: Mining Opinions, Sentiments, and Emotions, Cambridge University Press. Studies in Natural Language Processing.10.1017/9781108639286 ↗
6. Vajjala, S., Majumder, B., Gupta, A., and Surana, H. (2020). Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems, O’Reilly Media.
7. Toh, Z., and Wang, W. (2014, January 23–24). Dlirec: Aspect term extraction and term polarity classification system. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), Dublin, Ireland.10.3115/v1/S14-2038 ↗
8. Shelke, P.P., and Wagh, K.P. (2021, January 17–19). Review on aspect based sentiment analysis on social data. Proceedings of the 2021 8th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India.
9. Nguyen, M.H., Nguyen, T.M., Van Thin, D., and Nguyen, N.L.T. (2019, January 24–26). A corpus for aspect-based sentiment analysis in Vietnamese. Proceedings of the 2019 11th International Conference on Knowledge and Systems Engineering (KSE), Da Nang, Vietnam.10.1109/KSE.2019.8919448 ↗
10. A Semi-Supervised Approach for Aspect Category Detection and Aspect Term Extraction from Opinionated Text
11. Dependency Structure-Based Rules Using Root Node Technique for Explicit Aspect Extraction From Online Reviews10.1109/ACCESS.2023.3287830 ↗
12. Xue, W., Zhou, W., Li, T., and Wang, Q. (2017, January 1). MTNA: A neural multi-task model for aspect category classification and aspect term extraction on restaurant reviews. Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), Taipei, Taiwan.
13. Global inference for aspect and opinion terms co-extraction based on multi-task neural networks10.1109/TASLP.2018.2875170 ↗
14. Language independent sequence labelling for opinion target extraction10.1016/j.artint.2018.12.002 ↗
15. Improving aspect term extraction with bidirectional dependency tree representation10.1109/TASLP.2019.2913094 ↗
16. Multi-task learning for aspect term extraction and aspect sentiment classification10.1016/j.neucom.2020.02.093 ↗
17. Aspect term extraction via information-augmented neural network10.1007/s40747-022-00818-2 ↗
18. Piao, Y., and Zhang, J.X. (2024). Text Triplet Extraction Algorithm with Fused Graph Neural Networks and Improved Biaffine Attention Mechanism. Appl. Sci., 14.10.3390/app14083524 ↗
19. A multi-task learning model for chinese-oriented aspect polarity classification and aspect term extraction10.1016/j.neucom.2020.08.001 ↗
20. Hu, M., and Liu, B. (2004). Mining Opinion Features in Customer Reviews, AAAI.
21. Anwer, N., Rashid, A., and Hassan, S. (2010, January 16–18). Feature based opinion mining of online free format customer reviews using frequency distribution and Bayesian statistics. Proceedings of the 6th International Conference on Networked Computing and Advanced Information Management, Seoul, Republic of Korea.
22. A two-fold rule-based model for aspect extraction10.1016/j.eswa.2017.07.047 ↗
23. Zhao, Y., Qin, B., Hu, S., and Liu, T. (2010, January 2–4). Generalizing syntactic structures for product attribute candidate extraction. Proceedings of the Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Angeles, CA, USA.
24. Aspect extraction in customer reviews using syntactic pattern10.1016/j.procs.2015.07.545 ↗
25. Shafie, A.S., Sharef, N.M., Murad, M.A.A., and Azman, A. (2018, January 26–28). Aspect extraction performance with pos tag pattern of dependency relation in aspect-based sentiment analysis. Proceedings of the 2018 Fourth International Conference on Information Retrieval and Knowledge Management (CAMP), Kota Kinabalu, Malaysia.10.1109/INFRKM.2018.8464692 ↗
26. An unsupervised aspect extraction strategy for monitoring real-time reviews stream10.1016/j.ipm.2018.04.010 ↗
27. Huang, J., Cui, Y., and Wang, S. (2023). Adaptive Local Context and Syntactic Feature Modeling for Aspect-Based Sentiment Analysis. Appl. Sci., 13.10.3390/app13010603 ↗
28. Titov, I., and McDonald, R. (2008, January 21–25). Modeling online reviews with multi-grain topic models. Proceedings of the 17th International Conference on World Wide Web, Beijing, China.10.1145/1367497.1367513 ↗
29. Brody, S., and Elhadad, N. (2010, January 2–4). An unsupervised aspect-sentiment model for online reviews. Proceedings of the Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Los Angeles, CA, USA.
30. Concept over time: The combination of probabilistic topic model with wikipedia knowledge10.1016/j.eswa.2016.04.014 ↗
31. Enriched LDA (ELDA): Combination of latent Dirichlet allocation with word co-occurrence analysis for aspect extraction10.1016/j.eswa.2017.02.038 ↗
32. Opinion mining on Mandalika hotel reviews using latent dirichlet allocation10.1016/j.procs.2019.11.178 ↗
33. A new topic modeling based approach for aspect extraction in aspect based sentiment analysis: SS-LDA10.1016/j.eswa.2020.114231 ↗
34. An enhanced guided LDA model augmented with BERT based semantic strength for aspect term extraction in sentiment analysis10.1016/j.knosys.2022.108668 ↗
35. A hybrid unsupervised method for aspect term and opinion target extraction10.1016/j.knosys.2018.01.019 ↗
36. A two-step hybrid unsupervised model with attention mechanism for aspect extraction10.1016/j.eswa.2020.113673 ↗
37. Chen, M., Hua, Q., Mao, Y., and Wu, J. (2023). An Interactive Learning Network That Maintains Sentiment Consistency in End-to-End Aspect-Based Sentiment Analysis. Appl. Sci., 13.10.3390/app13169327 ↗
38. Span-based dependency-enhanced graph convolutional network for aspect sentiment triplet extraction10.1016/j.neucom.2023.126966 ↗
39. Graph Convolutional Network with Syntactic Dependency for Aspect-Based Sentiment Analysis10.1007/s44196-024-00419-6 ↗
40. Mu, Y., and Shi, S. (2024). Dependency-Type Weighted Graph Convolutional Network on End-to-End Aspect-Based Sentiment Analysis. International Conference on Intelligent Information Processing, Springer.10.1007/978-3-031-57919-6_4 ↗
41. Ensemble BiLSTM: A Novel Approach for Aspect Extraction From Online Text10.1109/ACCESS.2023.3349203 ↗
42. Knowledge-enabled BERT for aspect-based sentiment analysis10.1016/j.knosys.2021.107220 ↗
43. Label-semantics enhanced multi-layer heterogeneous graph convolutional network for Aspect Sentiment Quadruplet Extraction10.1016/j.eswa.2024.124523 ↗
44. Aspect-based sentiment analysis using smart government review data10.1016/j.aci.2019.11.003 ↗
45. Cavnar, W.B., and Trenkle, J.M. (1994, January 11–13). N-gram-based text categorization. Proceedings of the SDAIR-94, 3rd Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, NV, USA.
46. Auer, S., Bryl, V., and Tramp, S. (2014). Linked Open Data—Creating Knowledge Out of Interlinked Data: Results of the LOD2 Project, Springer International Publishing. Lecture Notes in Computer Science.10.1007/978-3-319-09846-3 ↗
47. Bauer, F., and Kaltenböck, M. (2011). Linked Open Data: The Essentials, Edition Mono/Monochrom.
48. Dbpedia—A large-scale, multilingual knowledge base extracted from wikipedia10.3233/SW-140134 ↗
49. Boyd, M. (2024, February 08). Thesaurus Synonyms API. Available online: https://api-ninjas.com/api/thesaurus/.
50. Latent dirichlet allocation
51. Latent Dirichlet allocation (LDA) and topic modeling: Models, applications, a survey10.1007/s11042-018-6894-4 ↗
52. Biomedical and clinical English model packages for the Stanza Python NLP library10.1093/jamia/ocab090 ↗
53. Bird, S. (2006, January 18). NLTK: The natural language toolkit. Proceedings of the COLING/ACL 2006 Interactive Presentation Sessions, Sydney, Australia.10.3115/1225403.1225421 ↗
54. Barrus, T. (2023, August 12). Pyspellchecker. Available online: https://pypi.org/project/pyspellchecker/.
55. Dependency grammar and dependency parsing
56. textblob Documentation
57. Baccianella, S., Esuli, A., and Sebastiani, F. (2010, January 17–23). Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. Proceedings of the Lrec, Valletta, Malta.
58. Han, H., Zhang, Y., Zhang, J., Yang, J., and Zou, X. (2018). Improving the performance of lexicon-based review sentiment analysis method by reducing additional introduced sentiment bias. PloS ONE, 13.10.1371/journal.pone.0202523 ↗
59. Agirre, E., Bos, J., Diab, M., Manandhar, S., Marton, Y., and Yuret, D. (2012). *SEM 2012: The First Joint Conference on Lexical and Computational Semantics—Volume 1: Proceedings of the Main Conference and the Shared Task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (semEval 2012), Montreal, Canada, 7–8 June 2021, Omnipress, Inc.
60. Aspect based sentiment analysis semeval-2014 task 4
61. Papageorgiou, H., Androutsopoulos, I., Galanis, D., Pontiki, M., and Manandhar, S. (2015, January 4–5). SemEval-2015 Task 12: Aspect Based Sentiment Analysis. Proceedings of the 9th International Workshop on Semantic Evaluation, Denver, CO, USA.
62. Pontiki, M., Galanis, D., Papageorgiou, H., Androutsopoulos, I., Manandhar, S., AL-Smadi, M., Al-Ayyoub, M., Zhao, Y., Qin, B., and De Clercq, O. (2016, January 16–17). Semeval-2016 task 5: Aspect based sentiment analysis. Proceedings of the ProWorkshop on Semantic Evaluation (SemEval-2016), Association for Computational Linguistics, San Diego, CA, USA.10.18653/v1/S16-1002 ↗
63. Schwaiger, J.M., Lang, M., Ritter, C., and Johannsen, F. (2016, January 12–15). Assessing the accuracy of sentiment analysis of social media posts at small and medium-sized enterprises in Southern Germany. Proceedings of the Twenty-Fourth European Conference on Information Systems (ECIS), Istanbul, Turkey.
64. Dbpedia-a crystallization point for the web of data10.1016/j.websem.2009.07.002 ↗