Hostname: page-component-78c5997874-t5tsf Total loading time: 0 Render date: 2024-11-18T08:08:27.930Z Has data issue: false hasContentIssue false
  • English
  • Français

EXTRACTING LATENT NEEDS FROM ONLINE REVIEWS THROUGH DEEP LEARNING BASED LANGUAGE MODEL

Published online by Cambridge University Press:  19 June 2023

Yi Han ,
Ryan Bruggeman ,
Joseph Peper ,
Estefania Ciliotta Chehade ,
Tucker Marion ,
Paolo Ciuccarelli  and
Mohsen Moghaddam
Yi Han*
Affiliation:
Northeastern university;
Ryan Bruggeman
Affiliation:
Northeastern university;
Joseph Peper
Affiliation:
The University of Michigan
Estefania Ciliotta Chehade
Affiliation:
Northeastern university;
Tucker Marion
Affiliation:
Northeastern university;
Paolo Ciuccarelli
Affiliation:
Northeastern university;
Mohsen Moghaddam
Affiliation:
Northeastern university;
*
Han, Yi, northeastern university, United States of America, han.yi1@northeastern.edu

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Aspect-based sentiment analysis (ABSA) provides an opportunity to systematically generate user's opinions of specific aspects to enrich the idea creation process in the early stage of product/service design process. Yet, the current ABSA task has two major limitations. First, existing research mostly focusing on the subsets of ABSA task, e.g. aspect-sentiment extraction, extract aspect, opinion, and sentiment in a unified model is still an open problem. Second, the implicit opinion and sentiment are ignored in the current ABSA task. This article tackles these gaps by (1) creating a new annotated dataset comprised of five types of labels, including aspect, category, opinion, sentiment, and implicit indicator (ACOSI) and (2) developing a unified model which could extract all five types of labels simultaneously in a generative manner. Numerical experiments conducted on the manually labeled dataset originally scraped from three major e-Commerce retail stores for apparel and footwear products indicate the performance, scalability, and potentials of the framework developed. Several directions are provided for future exploration in the area of automated aspect-based sentiment analysis for user-centered design.

Keywords

Latent needs findingNatural language processingArtificial intelligenceMachine learningBig data
Type
Article
Information
Proceedings of the Design Society , Volume 3: ICED23 , July 2023 , pp. 1855 - 1864
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2023. Published by Cambridge University Press

References

(2022), “c4 | TensorFlow Datasets”, [Online; accessed 18. Nov. 2022]. https://www.tensorflow.org/datasets/catalog/c4Google Scholar
(2022), Constructing Grounded Theory, SAGE Publications Ltd, Thousand Oaks, CA, USA. https://uk.sagepub.com/en-gb/eur/constructing-grounded-theory/book235960Google Scholar
(2022), “Know Your Customers'” Jobs to Be Done””, [Online; accessed 30. Nov. 2022]. https://hbr.org/2016/09/know-your-customers-jobs-to-be-doneGoogle Scholar
(2022), “T5”, [Online; accessed 20. Nov. 2022]. https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5TokenizerGoogle Scholar
(2022), “The Jobs-to-be-Done Growth Strategy Matrix”, [Online; accessed 30. Nov. 2022]. https://strategyn.com/lp/the-jobs-to-be-done-growth-strategy-matrixGoogle Scholar
Ahmed, M., Chen, Q., Wang, Y., Nafa, Y., Li, Z. and Duan, T. (2021), “DNN-driven Gradual Machine Learning for Aspect-term Sentiment Analysis”, ACL Anthology, pp. 488–497, http://doi.org/10.18653/v1/2021.findings-acl.43.CrossRefGoogle Scholar
Andersen, S. (1983), “Need assessment: a way of improving the value of new products”, Design Studies, Vol. 4 No. 3, pp. 183–187, http://doi.org/10.1016/0142-694X(83)90028-5.CrossRefGoogle Scholar
Cai, H., Xia, R. and Yu, J. (2021), “Aspect-Category-Opinion-Sentiment Quadruple Extraction with Implicit Aspects and Opinions”, ACL Anthology, pp. 340–350, http://doi.org/10.18653/v1/2021.acl-long.29.CrossRefGoogle Scholar
Charmaz, K. (2014), Constructing grounded theory, sage.Google Scholar
Cooper, R.G., Edgett, S.J. and Kleinschmidt, E.J. (2004), “Benchmarking best NPD practices - III”, http://doi.org/10.1080/08956308.2004.11671662.CrossRefGoogle Scholar
Cramer-Petersen, C.L., Christensen, B.T. and Ahmed-Kristensen, S. (2018), “Empirically analysing design reasoning patterns: Abductive-deductive reasoning patterns dominate design idea generation”, Design Studies, Vol. 60, http://doi.org/10.1016/jj.destud.2018.10.001.Google Scholar
Devlin, J., Chang, M.W., Lee, K. and Toutanova, K. (2018), “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding”,. https://github.com/tensorflow/tensor2tensorGoogle Scholar
Et al., H.W. (2022), “Target-Aspect-Sentiment Joint Detection for Aspect-Based Sentiment Analysis | EndNote Click”, [Online; accessed 17. Nov. 2022].Google Scholar
Felfernig, A. (2007), “Standardized Configuration Knowledge Representations as Technological Foundation for Mass Customization”, IEEE Transactions on Engineering Management, Vol. 54 No. 1, pp. 41–56, http://doi.org/10.1109/TEM.2006.889066. http://ieeexplore.ieee.org/document/4077230/CrossRefGoogle Scholar
Fogliatto, F.S., Da Silveira, G.J. and Borenstein, D. (2012), “The mass customization decade: An updated review of the literature”, International Journal of Production Economics, Vol. 138 No. 1, pp. 14–25, http://doi.org/10.1016/j.ijpe.2012.03.002.CrossRefGoogle Scholar
Fogliatto, F.S. and da Silveira, G.J. (2008), “Mass customization: A method for market segmentation and choice menu design”, International Journal of Production Economics, Vol. 111 No. 2, pp. 606–622, http://doi.org/10.1016/j.ijpe.2007.02.034. https://linkinghub.elsevier.com/retrieve/pii/S092552730700103XCrossRefGoogle Scholar
Franke, N., Keinz, P. and Steger, C.J. (2009), “Testing the Value of Customization: When Do Customers Really Prefer Products Tailored to Their Preferences?”, Journal of Marketing, Vol. 73 No. 5, pp. 103–121, http://doi.org/10.1509/jmkg.73.5.103. http://journals.sagepub.com/doi/10.1509/jmkg.73.5.103CrossRefGoogle Scholar
Fullerton, L. (2017), “Online reviews impact purchasing decisions for over 93% of consumers”,. https://www.thedrum.com/news/2017/03/27/online-reviews-impact-purchasing-decisions-over-93-consumers-report-suggestsGoogle Scholar
Fuller, J. and Matzler, K. (2007), “Virtual product experience and customer participation—A chance for customer-centred, really new products”, Technovation, Vol. 27 No. 6, pp. 378–387, http://doi.org/10.1016/j.technovation.2006.09.005.CrossRefGoogle Scholar
Gero, J.S. (2000), “Computational Models of Innovative and Creative Design Processes”, Technol. Forecasting Social Change, Vol. 64 No. 2, pp. 183–196, http://doi.org/10.1016/S0040-1625(99)00105-5.CrossRefGoogle Scholar
Guenther, A., Eisenbart, B. and Dong, A. (2017), Creativity as a way to innovate successfully.Google Scholar
Han, Y. and Moghaddam, M. (2019), “Analysis of Sentiment Expressions for Customer-Centric Design”, Expert Systems With Applications (under review: ESWA-S-19-07664), Vol. 1 No. 617.Google Scholar
Han, Y. and Moghaddam, M. (2021a), “Analysis of sentiment expressions for user-centered design”, Expert Syst. Appl., Vol. 171, p. 114604, http://doi.org/10.1016/jj.eswa.2021.114604.CrossRefGoogle Scholar
Han, Y. and Moghaddam, M. (2021b), “Eliciting Attribute-Level User Needs From Online Reviews With Deep Language Models and Information Extraction”, J. Mech. Des., Vol. 143 No. 6, http://doi.org/10.1115/1.4048819.CrossRefGoogle Scholar
Kolko, J. (2010), “Abductive Thinking and Sensemaking: The Drivers of Design Synthesis”, Des. Issues, Vol. 26 No. 1, pp. 15–28, http://doi.org/10.1162/desi.2010.26.L15.CrossRefGoogle Scholar
Lee, J.S. and Taxman, F.S. (2020), “Using latent class analysis to identify the complex needs of youth on probation”, Children and Youth Services Review, Vol. 115, p. 105087, http://doi.org/10.1016/jj.childyouth.2020.105087.CrossRefGoogle ScholarPubMed
Li, X., Bing, L., Li, P., Lam, W. and Yang, Z. (2018), “Aspect term extraction with history attention and selective transformation”, IJCAI International Joint Conference on Artificial Intelligence, Vol. 2018-July, pp. 4194— 4200, http://doi.org/10.24963/ijcai.2018/583.Google Scholar
Lord, C.G., Ross, L. and Lepper, M.R. (1979), “Biased assimilation and attitude polarization: The effects of prior theories on subsequently considered evidence”, Journal of Personality and Social Psychology, Vol. 37 No. 11, pp. 2098–2109, http://doi.org/10.1037/0022-3514.37.11.2098.CrossRefGoogle Scholar
Marion, T.J. and Fixson, S.K. (2018), The innovation navigator: Transforming your organization in the era of digital design and collaborative culture, University of Toronto Press.CrossRefGoogle Scholar
Peper, J.J. and Wang, L. (2022), “Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure”, arXiv, http://doi.org/10.48550/arXiv.2211.07743.CrossRefGoogle Scholar
Pitman, J. (2022), “Local Consumer Review Survey 2022: Customer Reviews and Behavior”, BrightLocal. https://www.brightlocal.com/research/local-consumer-review-surveyGoogle Scholar
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W. and Liu, P.J. (2019), “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer”, arXiv. https://arxiv.org/abs/1910.10683v3Google Scholar
Ravi, K. and Ravi, V. (2015), “A survey on opinion mining and sentiment analysis: Tasks, approaches and applications”, Knowledge-Based Systems, Vol. 89, pp. 14–46, http://doi.org/10.1016Zj.knosys.2015.06.015.Google Scholar
Roy, A. (2021), “Recent Trends in Named Entity Recognition (NER)”, arXiv, http://doi.org/10.48550/arXiv.2101.11420.CrossRefGoogle Scholar
Schaffhausen, C.R. and Kowalewski, T.M. (2015), “Large-scale needfinding: Methods of increasing user- generated needs from large populations”, Journal of Mechanical Design, Transactions of theASME, Vol. 137 No. 7, pp. 1–11, http://doi.org/10.1115/L4030161.Google Scholar
Stacey, Mcfadzean and Sketch, J.. (, 1997), Managing effec-tive communication in knitwear design, Technical Report 3.Google Scholar
Tang, H., Tan, S. and Cheng, X. (2009), “A survey on sentiment detection of reviews”, Expert Systems with Applications, Vol. 36 No. 7, pp. 10760–10773, http://doi.org/10.1016/j.eswa.2009.02.063.CrossRefGoogle Scholar
Timoshenko, A. and Hauser, J.R. (2019), “Identifying Customer Needs from User-Generated Content”, Marketing Science. https://pubsonline.informs.org/doi/abs/10.1287/mksc.2018.1123?journalCode=mkscCrossRefGoogle Scholar
Ulwick, A. (2005), What customers want, Vol. 8, McGraw-Hill Professional Publishing New York, NY.Google Scholar
Umeda, Y., Ishii, M., Yoshioka, M., Shimomura, Y. and Tomiyama, T. (1996), “Supporting conceptual design based on the function-behavior-state modeler”, AI EDAM, Vol. 10 No. 4, pp. 275–288, http://doi.org/10.1017/S0890060400001621.Google Scholar
Vaswani, A. (2017), “Attention Is All You Need”, No. Nips.Google Scholar
Wang, K., Shen, W., Yang, Y., Quan, X. and Wang, R. (2020), “Relational Graph Attention Network for Aspect- based Sentiment Analysis”, arXiv. https://arxiv.org/abs/2004.12362v1CrossRefGoogle Scholar
Yadav, V. and Bethard, S. (2018), A Survey on Recent Advances in Named Entity Recognition from Deep Learning models, Technical report. http://2016.bionlp-st.org/tasks/bb2Google Scholar
Yi Han, Moghaddam, M. (2021), “Analysis of sentiment expressions for user-centered design”, undefined. https://www.semanticscholar.org/paper/Analysis-of-sentiment-expressions-for-user-centered-Han-Moghaddam/aba9b15d95a2fce3e76048860d5dd238e07fe90cGoogle Scholar
Yuan, C., Marion, T. and Moghaddam, M. (2022), “Leveraging End-User Data for Enhanced Design Concept Evaluation: A Multimodal Deep Regression Model”, J. Mech. Des., Vol. 144 No. 2, http://doi.org/10.1115/1.4052366.Google Scholar
Zhou, F., Jianxin Jiao, R. and Linsey, J.S. (2015), “Latent Customer Needs Elicitation by Use Case Analogical Reasoning From Sentiment Analysis of Online Product Reviews”, J. Mech. Des., Vol. 137 No. 7, http://doi.org/10.1115/1.4030159.CrossRefGoogle Scholar