Hostname: page-component-76fb5796d-vfjqv Total loading time: 0 Render date: 2024-04-25T11:27:54.725Z Has data issue: false hasContentIssue false
  • English
  • Français

Design change prediction based on social media sentiment analysis

Published online by Cambridge University Press:  27 July 2022

Edwin C.Y. Koh Open the ORCID record for Edwin C.Y. Koh [Opens in a new window]
Edwin C.Y. Koh*
Affiliation:
Design and Artificial Intelligence Programme & Engineering Product Development Pillar, Singapore University of Technology and Design, Singapore, Singapore
*
Author for correspondence: Edwin C.Y. Koh, E-mail: edwin_koh@sutd.edu.sg
Get access Rights & Permissions [Opens in a new window]

Abstract

The use of artificial intelligence (AI) techniques to uncover customer sentiment is not uncommon. However, the integration of sentiment analysis with research in design change prediction remains an untapped potential. This paper presents a method that uses social media sentiment analysis to identify opportunities for design change and the set of product components affected by the change. The method builds on natural language processing to determine change candidates from textual data and uses dependency modeling to reveal direct and indirect change propagation paths arising from the change candidates. The method was applied in a case example where 3665 YouTube comments on a diesel engine were analyzed. Based on the results, two engine components were recommended for design change with six others predicted as likely to be affected through change propagation. The findings suggest that the method can be used to aid decision quality in product planning through a better understanding of the change impact associated with the opportunities identified.

Keywords

BERTdependency modelingdesign changenatural language processingsocial media
Type
Research Article
Information
AI EDAM , Volume 36 , 2022 , e24
Check for updates
Copyright
Copyright © The Author(s), 2022. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Agrawal, R, Imieliński, T and Swami, A (1993) Mining association rules between sets of items in large databases. Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, pp. 207–216.10.1145/170035.170072CrossRefGoogle Scholar
Ahmad, N, Wynn, DC and Clarkson, PJ (2013) Change impact on a product and its redesign process: a tool for knowledge capture and reuse. Research in Engineering Design 24, 219–244.10.1007/s00163-012-0139-8CrossRefGoogle Scholar
Archak, N, Ghose, A and Ipeirotis, PG (2011) Deriving the pricing power of product features by mining consumer reviews. Management Science 57, 1485–1509.10.1287/mnsc.1110.1370CrossRefGoogle Scholar
Barbieri, F, Camacho-Collados, J, Neves, L and Espinosa-Anke, L (2020) Tweeteval: Unified benchmark and comparative evaluation for tweet classification. arXiv preprint. arXiv:2010.12421.10.18653/v1/2020.findings-emnlp.148CrossRefGoogle Scholar
BBC News (2009) Design changes cause Boeing loss. Available at http://news.bbc.co.uk/1/hi/business/8318519.stmGoogle Scholar
Blei, DM, Ng, AY and Jordan, MI (2003) Latent Dirichlet allocation. Journal of Machine Learning Research 3, 993–1022.Google Scholar
Cardin, M-A, Kolfschoten, GL, Frey, DD, de Neufville, R, de Weck, OL and Geltner, DM (2013) Empirical evaluation of procedures to generate flexibility in engineering systems and improve lifecycle performance. Research in Engineering Design 24, 277–295.10.1007/s00163-012-0145-xCrossRefGoogle Scholar
Chang, D and Lee, C (2018) A product affective properties identification approach based on web mining in a crowdsourcing environment. Journal of Engineering Design 29, 449–483.10.1080/09544828.2018.1463514CrossRefGoogle Scholar
Chen, L, Zheng, Y, Xi, J and Li, S (2020) An analysis method for change propagation based on product feature network. Research in Engineering Design 31, 491–503.10.1007/s00163-020-00344-7CrossRefGoogle Scholar
Clarkson, PJ, Simons, C and Eckert, CM (2004) Predicting change propagation in complex design. Journal of Mechanical Design 126, 765–797.10.1115/1.1765117CrossRefGoogle Scholar
Devlin, J, Chang, M-W, Lee, K and Toutanova, K (2018) BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint. arXiv:1810.04805.Google Scholar
Duran-Novoa, R, Weigl, JD, Henz, M and Koh, ECY (2018) Designing in young organisations: engineering change propagation in a university design project. Research in Engineering Design 29, 489–506.10.1007/s00163-018-0292-9CrossRefGoogle Scholar
Eckert, CM, Clarkson, PJ and Zanker, W (2004) Change and customisation in complex engineering domains. Research in Engineering Design 15, 1–21.10.1007/s00163-003-0031-7CrossRefGoogle Scholar
Einwiller, SA and Steilen, S (2015) Handling complaints on social network sites – an analysis of complaints and complaint responses on Facebook and twitter pages of large US companies. Public Relations Review 41, 195–204.10.1016/j.pubrev.2014.11.012CrossRefGoogle Scholar
Eppinger, SD and Browning, TR (2012) Design Structure Matrix Methods and Applications. Cambridge, MA: MIT Press.10.7551/mitpress/8896.001.0001CrossRefGoogle Scholar
Fernandes, J, Henriques, E, Silva, A and Moss, MA (2015) Requirements change in complex technical systems: an empirical study of root causes. Research in Engineering Design 26, 37–55.10.1007/s00163-014-0183-7CrossRefGoogle Scholar
Giffin, M, de Weck, O, Buonova, G, Keller, R, Eckert, CM and Clarkson, PJ (2009) Change propagation analysis in complex technical systems. Journal of Mechanical Design 131, 081001, 1–14.10.1115/1.3149847CrossRefGoogle Scholar
Grégoire, Y, Salle, A and Tripp, TM (2015) Managing social media crises with your customers: the good, the bad, and the ugly. Business Horizons 58, 173–182.10.1016/j.bushor.2014.11.001CrossRefGoogle Scholar
Hamraz, B and Clarkson, PJ (2015) Industrial evaluation of FBS linkage – a method to support engineering change management. Journal of Engineering Design 26, 24–47.10.1080/09544828.2015.1015783CrossRefGoogle Scholar
Hamraz, B, Hisarciklilar, O, Rahmani, K, Wynn, DC, Thomson, V and Clarkson, PJ (2013) Change prediction using interface data. Concurrent Engineering 21, 141–154.10.1177/1063293X13482473CrossRefGoogle Scholar
Hutto, C and Gilbert, E (2014) Vader: A parsimonious rule-based model for sentiment analysis of social media text. Proceedings of the International AAAI Conference on Web and Social Media, Vol. 8, No. 1, pp. 216–225.Google Scholar
Jarratt, TAW, Eckert, CM, Caldwell, NHM and Clarkson, PJ (2011) Engineering change: an overview and perspective on the literature. Research in Engineering Design 22, 103–124.10.1007/s00163-010-0097-yCrossRefGoogle Scholar
Javornik, A, Filieri, R and Gumann, R (2020) “Don't forget that others are watching, too!” The effect of conversational human voice and reply length on observers’ perceptions of complaint handling in social media. Journal of Interactive Marketing 50, 100–119.10.1016/j.intmar.2020.02.002CrossRefGoogle Scholar
Jiang, H, Kwong, CK and Yung, KL (2017) Predicting future importance of product features based on online customer reviews, Journal of Mechanical Design 139, 111413, 1–10.10.1115/1.4037348CrossRefGoogle Scholar
Jin, J, Liu, Y, Ji, P and Liu, H (2016) Understanding big consumer opinion data for market-driven product design. International Journal of Production Research 54, 3019–3041.10.1080/00207543.2016.1154208CrossRefGoogle Scholar
Kang, SW and Tucker, CS (2016) An automated approach to quantifying functional interactions by mining large-scale product specification data. Journal of Engineering Design 27, 1–24.10.1080/09544828.2015.1083539CrossRefGoogle Scholar
Kasperek, D, Schenk, D, Kreimeyer, M, Maurer, M and Lindemann, U (2016) Structure-based system dynamics analysis of engineering design processes. Systems Engineering 19, 278–298.10.1002/sys.21353CrossRefGoogle Scholar
Keller, R (2007) Predicting Change Propagation: Algorithms, Representations, Software Tools (PhD thesis). Department of Engineering, University of Cambridge, UK.Google Scholar
Koh, ECY (2017) A study on the requirements to support the accurate prediction of engineering change propagation. Systems Engineering 20, 147–157.10.1002/sys.21385CrossRefGoogle Scholar
Koh, ECY, Caldwell, NHM and Clarkson, PJ (2012) A method to assess the effects of engineering change propagation. Research in Engineering Design 23, 329–351.10.1007/s00163-012-0131-3CrossRefGoogle Scholar
Koh, ECY, Caldwell, NHM and Clarkson, PJ (2013) A technique to assess the changeability of complex engineering systems. Journal of Engineering Design 24, 477–498.10.1080/09544828.2013.769207CrossRefGoogle Scholar
Koh, ECY, Forg, A, Kreimeyer, M and Lienkamp, M (2015) Using engineering change forecast to prioritise component modularisation. Research in Engineering Design 26, 337–353.10.1007/s00163-015-0200-5CrossRefGoogle Scholar
Kreimeyer, M (2016) Implementing product architecture in industry: impact of engineering design research. In Chakrabarti, A and Lindemann, U (eds), Impact of Design Research on Industrial Practice. Cham: Springer, pp. 383–398.Google Scholar
Kreimeyer, M and Lindemann, U (2011) Complexity Metrics in Engineering Design - Managing the Structure of Design Processes. Berlin, Heidelberg: Springer.10.1007/978-3-642-20963-5CrossRefGoogle Scholar
Laufer, D and Coombs, WT (2006) How should a company respond to a product harm crisis? The role of corporate reputation and consumer-based cues. Business Horizons 49, 379–385.10.1016/j.bushor.2006.01.002CrossRefGoogle Scholar
Lee, J and Hong, YS (2017) Bayesian network approach to change propagation analysis. Research in Engineering Design 28, 437–455.10.1007/s00163-017-0252-9CrossRefGoogle Scholar
Lim, S and Tucker, CS (2016) A Bayesian sampling method for product feature extraction from large scale textual data. Journal of Mechanical Design 138, 061403, 1–9.10.1115/1.4033238CrossRefGoogle Scholar
Lim, S, Conrad, S and Tucker, CS (2017) Mitigating online product rating biases through the discovery of optimistic, pessimistic, and realistic reviewers. Journal of Mechanical Design 139, 111409, 1–11.10.1115/1.4037612CrossRefGoogle Scholar
Lindemann, U, Maurer, M and Braun, T (2009) Structural Complexity Management – An Approach for the Field of Product Design. Berlin, Heidelberg: Springer.10.1007/978-3-540-87889-6CrossRefGoogle Scholar
Liu, Y, Jin, J, Ji, P, Harding, JA and Fung, RYK (2013) Identifying helpful online reviews: a product designer's perspective. Computer-Aided Design 45, 180–194.10.1016/j.cad.2012.07.008CrossRefGoogle Scholar
Liu, Y, Ott, M, Goyal, N, Du, J, Joshi, M, Chen, D, Levy, O, Lewis, M, Zettlemoyer, L and Stoyanov, V (2019) RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint. arXiv:1907.11692.Google Scholar
Long, M, Erickson, M and MacDonald, EF (2019) Consideration-constrained engineering design for strategic insights. Journal of Mechanical Design 141, 064501, 1–8.10.1115/1.4041916CrossRefGoogle Scholar
Maier, JF, Eckert, CM and Clarkson, PJ (2017) Model granularity in engineering design – concepts and framework. Design Science 3, 1–29.10.1017/dsj.2016.16CrossRefGoogle Scholar
Pratama, MO, Satyawan, W, Jannati, R, Pamungkas, B, Raspiani, , Syahputra, ME and Neforawati, I (2019) The sentiment analysis of Indonesia commuter line using machine learning based on Twitter data. Journal of Physics: Conference Series 1193, 1–6.Google Scholar
Roth, M, Wolf, M and Lindemann, U (2015) Integrated matrix-based fault tree generation and evaluation. Procedia Computer Science 44, 599–608.10.1016/j.procs.2015.03.027CrossRefGoogle Scholar
Sarica, S, Luo, J and Wood, K (2020) Technet: technology semantic network based on patent data. Expert Systems with Applications 142, 112995.10.1016/j.eswa.2019.112995CrossRefGoogle Scholar
Sha, Z, Saeger, V, Wang, M, Fu, Y and Chen, W (2017) Analyzing customer preference to product optional features in supporting product configuration. SAE International Journal of Materials and Manufacturing 10, 320–332.10.4271/2017-01-0243CrossRefGoogle Scholar
Shankar, P, Morkos, B and Summers, JD (2012) Reasons for change propagation: a case study in an automotive OEM. Research in Engineering Design 23, 291–303.10.1007/s00163-012-0132-2CrossRefGoogle Scholar
Siddharth, L and Sarkar, P (2017) A methodology for predicting the effect of engineering design changes. Procedia CIRP 60, 452–457.10.1016/j.procir.2017.03.071CrossRefGoogle Scholar
Song, B, Luo, J and Wood, K (2019) Data-driven platform design: patent data and function network analysis. Journal of Mechanical Design 141, 021101, 1–10.10.1115/1.4042083CrossRefGoogle Scholar
Suh, ES, de Weck, O and Chang, D (2007) Flexible product platforms: framework and case study. Research in Engineering Design 18, 67–89.10.1007/s00163-007-0032-zCrossRefGoogle Scholar
Sun, H, Guo, W, Shao, H and Rong, B (2020) Dynamical mining of ever-changing user requirements: a product design and improvement perspective. Advanced Engineering Informatics 46, 1–11.10.1016/j.aei.2020.101174CrossRefGoogle Scholar
Suryadi, D and Kim, H (2018) A systematic methodology based on word embedding for identifying the relation between online customer reviews and sales rank. Journal of Mechanical Design 140, 121403, 1–12.10.1115/1.4040913CrossRefGoogle Scholar
Tang, D, Yin, L, Wang, Q, Ullah, I, Zhu, H and Leng, S (2016) Workload-based change propagation analysis in engineering design. Concurrent Engineering 24, 17–34.10.1177/1063293X15608510CrossRefGoogle Scholar
Tang, M, Jin, J, Liu, Y, Li, C and Zhang, W (2019) Integrating topic, sentiment, and syntax for modeling online reviews: a topic model approach. Journal of Computing and Information Science in Engineering 19, 011001, 1–12.10.1115/1.4041475CrossRefGoogle Scholar
Tuarob, S and Tucker, CS (2015 a) Automated discovery of lead users and latent product features by mining large scale social media networks. Journal of Mechanical Design 137, 071402, 1–11.10.1115/1.4030049CrossRefGoogle Scholar
Tuarob, S and Tucker, CS (2015 b) Quantifying product favorability and extracting notable product features using large scale social media data. Journal of Computing and Information Science in Engineering 15, 031003, 1–12.10.1115/1.4029562CrossRefGoogle Scholar
Tuarob, S, Lim, S, Conrad, S and Tucker, CS (2018) Automated discovery of product feature inferences within large-scale implicit social media data. Journal of Computing and Information Science in Engineering 18, 021017, 1–14.10.1115/1.4039432CrossRefGoogle Scholar
Tucker, CS and Kim, HM (2009) Data-driven decision tree classification for product portfolio design optimization. Journal of Computing and Information Science in Engineering 9, 041004, 1–14.10.1115/1.3243634CrossRefGoogle Scholar
Tucker, CS and Kim, HM (2011) Trend mining for predictive product design. Journal of Mechanical Design 133, 111008, 1–11.10.1115/1.4004987CrossRefGoogle Scholar
Ullah, I, Tang, D, Yin, L, Hussain, I and Wang, Q (2018) Cost-effective propagation paths for multiple change requirements in the product design. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science 232, 1572–1585.Google Scholar
Vaswani, A, Shazeer, N, Parmar, N, Uszkoreit, J, Jones, L, Gomez, AN, Kaiser, L and Polosukhin, I (2017) Attention is all you need. arXiv preprint. arXiv:1706.03762.Google Scholar
Wang, M, Sha, Z, Huang, Y, Contractor, N, Fu, Y and Chen, W (2018) Predicting product co-consideration and market competitions for technology-driven product design: a network-based approach. Design Science 4, 1–34.10.1017/dsj.2018.4CrossRefGoogle Scholar
Wang, WM, Tian, ZG, Li, Z, Wang, JW, Barenji, AV and Cheng, MN (2019) Supporting the construction of affective product taxonomies from online customer reviews: an affective-semantic approach. Journal of Engineering Design 30, 445–476.10.1080/09544828.2019.1642460CrossRefGoogle Scholar
Wickel, MC and Lindemann, U (2015) How to build up an engineering change dependency model based on past change data? Proceedings of the 17th International Dependency and Structure Modelling Conference, Texas, pp. 221–231.Google Scholar
Xie, Y and Ma, Y (2016) Well-controlled engineering change propagation via a dynamic inter-feature association map. Research in Engineering Design 27, 311–329.10.1007/s00163-016-0220-9CrossRefGoogle Scholar
Xie, J, Bi, Y, Sha, Z, Wang, M, Fu, Y, Contractor, N, Gong, L and Chen, W (2020) Data-driven dynamic network modeling for analyzing the evolution of product competitions. Journal of Mechanical Design 142, 031112, 1–14.10.1115/1.4045687CrossRefGoogle Scholar
Yassine, AA and Khoury, WG (2021) Optimizing module upgrade decisions to maximize profits. Research in Engineering Design 32, 49–70.10.1007/s00163-020-00350-9CrossRefGoogle Scholar
Yin, L, Tang, D, Wang, Q, Ullah, I and Zhang, H (2017) Engineering change management of product design using model-based definition technology. Journal of Computing and Information Science in Engineering 17, 041006, 1–19.10.1115/1.4036121CrossRefGoogle Scholar
Yin, L, Sun, Q, Xu, Y, Shao, L and Tang, D (2021) Risk analysis of engineering change for distributed product design. Journal of Computing and Information Science in Engineering 21, 041003, 1–11.10.1115/1.4048812CrossRefGoogle Scholar
Zhan, J, Loh, HT and Liu, Y (2009) Gather customer concerns from online product reviews – a text summarization approach. Expert Systems with Applications 36, 2107–2115.10.1016/j.eswa.2007.12.039CrossRefGoogle Scholar
Zhou, F, Jiao, R and Linsey, JS (2015) Latent customer needs elicitation by use case analogical reasoning from sentiment analysis of online product reviews. Journal of Mechanical Design 137, 071401, 1–12.10.1115/1.4030159CrossRefGoogle Scholar
Zhou, F, Ayoub, J, Xu, Q and Yang, XJ (2020) A machine learning approach to customer needs analysis for product ecosystems. Journal of Mechanical Design 142, 011101, 1–13.10.1115/1.4044435CrossRefGoogle Scholar