nach oben

The International Journal of Advanced Manufacturing Technology

Erschienen in:

19.02.2024 | ORIGINAL ARTICLE

A novel approach to voice of customer extraction using GPT-3.5 Turbo: linking advanced NLP and Lean Six Sigma 4.0

verfasst von: Mohammad Shahin, F. Frank Chen, Ali Hosseinzadeh, Mazdak Maghanaki, Ayda Eghbalian

Erschienen in: The International Journal of Advanced Manufacturing Technology | Ausgabe 7-8/2024

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

This research breaks new ground by utilizing the advanced natural language processing (NLP) capabilities of OpenAI’s GPT-3.5 Turbo model for the extraction of voice of customer (VoC) data from online customer support interactions on Twitter. Traditional methods of VoC extraction have typically fallen short in capturing the richness and nuance of customer sentiment. Contemporary machine learning (ML) approaches, while improved, still struggle to interpret the contextual subtleties of digital customer communications effectively. This study showcases the innovative deployment of GPT-3.5 Turbo, demonstrating its superior performance in extracting VoC through a deeper understanding of conversational context and a more intuitive, chat-based data processing. Furthermore, the large-scale, multilingual processing capabilities of this model offer a more comprehensive and inclusive analysis of VoC. The study ties these advancements to Lean Six Sigma 4.0, illustrating how the integration of GPT-3.5 Turbo’s transformative capabilities can elevate the customer-centric approach of Lean Six Sigma in the era of Industry 4.0. This innovative exploration points to a significant evolution in VoC analysis, offering potential for more insightful, real-time data–driven customer service strategies and a more substantial foundation for decision-making in product development and process improvement. Future research is encouraged to validate these preliminary findings and to investigate ethical considerations associated with the use of such advanced NLP models.

Vorheriger Artikel An efficient and precise stability analysis method for milling process

Nächster Artikel Optimization of forward pulsed currents for combining the precision shaping and polishing of nickel micro mould tools to reduce demoulding defects

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Zhou Q, He L (2019) Research on customer satisfaction evaluation method for individualized customized products. Int J Adv Manuf Technol 104:3229–3238. https://doi.org/10.1007/s00170-017-1192-2CrossRef

Mastrogiacomo L, Barravecchia F, Franceschini F, Marimon F (2021) Mining quality determinants of product-service systems from user-generated contents. Qual Eng 33:425–442. https://doi.org/10.1080/08982112.2021.1877305CrossRef

Sony M, Antony J, Douglas JA (2020) Essential ingredients for the implementation of Quality 4.0: a narrative review of literature and future directions for research. TQM J 32:779–793. https://doi.org/10.1108/TQM-12-2019-0275CrossRef

Elg M, Birch-Jensen A, Gremyr I et al (2021) Digitalisation and quality management: problems and prospects. Prod Plan CONTROL 32:990–1003. https://doi.org/10.1080/09537287.2020.1780509CrossRef

Kaplan AM, Haenlein M (2010) Users of the world, unite! The challenges and opportunities of Social Media. Bus Horiz 53:59–68. https://doi.org/10.1016/j.bushor.2009.09.003CrossRef

Tirunillai S, Tellis GJ (2014) Mining marketing meaning from online chatter: strategic brand analysis of big data using latent Dirichlet allocation. J Mark Res JMR 51:463–479. https://doi.org/10.1509/jmr.12.0106CrossRef

Özdağoğlu G, Kapucugil-İkiz A, Çelik AF (2018) Topic modelling-based decision framework for analysing digital voice of the customer. Total Qual Manag Bus Excell 29:1545–1562. https://doi.org/10.1080/14783363.2016.1273106CrossRef

Stentoft J, Adsboll Wickstrom K, Philipsen K, Haug A (2021) Drivers and barriers for Industry 4.0 readiness and practice: empirical evidence from small and medium-sized manufacturers. Prod Plan CONTROL 32:811–828. https://doi.org/10.1080/09537287.2020.1768318CrossRef

Koodiani HK, Jafari E, Majlesi A et al (2024) Machine learning tools to improve nonlinear modeling parameters of RC columns. J Build Eng 108492. https://doi.org/10.1016/j.jobe.2024.108492

10.

Shahin M, Chen FF, Hosseinzadeh A et al (2022) A deep hybrid learning model for detection of cyber attacks in industrial IoT devices. Int J Adv Manuf Technol 123:1973–1983. https://doi.org/10.1007/s00170-022-10329-6CrossRef

11.

Shahin M, Chen FF, Bouzary H et al (2022) A novel fully convolutional neural network approach for detection and classification of attacks on industrial IoT devices in smart manufacturing systems. Int J Adv Manuf Technol 1–13. https://doi.org/10.1007/s00170-022-10259-3

12.

Patel L, Lean AI (2020) How innovative startups use artificial intelligence to grow. O’Reilly Media, Inc

13.

Song X, Wu N, Song S, Stojanovic V (2023) Switching-like event-triggered state estimation for reaction–diffusion neural networks against DoS attacks. Neural Process Lett:1–22

14.

Khodadadi Koodiani H, Erfanian N, Majlesi A et al (2023) Calibrating equations to predict the compressive strength of FRP-confined columns using optimized neural network model. Structures 56:105060. https://doi.org/10.1016/j.istruc.2023.105060CrossRef

15.

Song X, Wu N, Song S, Zhang Y, Stojanovic V (2023) Bipartite synchronization for cooperative-competitive neural networks with reaction–diffusion terms via dual event-triggered mechanism. Neurocomputing 126498

16.

Thomas T, Sharma P, Gupta DK (2023) Sustainable application of ML/AI methods in DCW understanding & screening. Mater Today Proc. https://doi.org/10.1016/j.matpr.2023.06.010CrossRef

17.

Barravecchia F, Mastrogiacomo L, Franceschini F (2022) Digital voice-of-customer processing by topic modelling algorithms: insights to validate empirical results. Int J Qual Reliab Manag 39:1453–1470. https://doi.org/10.1108/IJQRM-07-2021-0217CrossRef

18.

Mastrogiacomo L, Barravecchia F, Franceschini F (2019) A worldwide survey on manufacturing servitization. Int J Adv Manuf Technol 103:3927–3942. https://doi.org/10.1007/s00170-019-03740-zCrossRef

19.

Yang Z, Dai Z, Yang Y, Carbonell J, Salakhutdinov RR, Le QV (2019) Xlnet: Generalized autoregressive pretraining for language understanding. Adv Neural Inf Process Syst:32

20.

Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805

21.

Murdoch WJ, Singh C, Kumbier K et al (2019) Definitions, methods, and applications in interpretable machine learning. Proc Natl Acad Sci 116:22071–22080. https://doi.org/10.1073/pnas.1900654116MathSciNetCrossRef

22.

Raghavan VA, Yoon S, Srihari K (2014) Lean transformation in a high mix low volume electronics assembly environment. Int J Lean Six Sigma 5:342–360. https://doi.org/10.1108/IJLSS-07-2013-0042CrossRef

23.

Virmani N, Saha R, Sahai R (2018) Leagile manufacturing: a review paper. Int J Product Qual Manag 23:385. https://doi.org/10.1504/IJPQM.2018.089807CrossRef

24.

Virmani N, Sharma S, Kumar A, Luthra S (2023) Adoption of industry 4.0 evidence in emerging economy: behavioral reasoning theory perspective. Technol Forecast Soc Change 188 https://doi.org/10.1016/j.techfore.2023.122317

25.

Shahin M, Chen FF, Bouzary H, Krishnaiyer K (2020) Integration of Lean practices and Industry 4.0 technologies: smart manufacturing for next-generation enterprises. Int J Adv Manuf Technol 107:2927–2936. https://doi.org/10.1007/s00170-020-05124-0CrossRef

26.

Virmani N, Saha R, Sahai R (2017) Understanding the barriers in implementing leagile manufacturing system. Int J Product Qual Manag 22:499. https://doi.org/10.1504/IJPQM.2017.087866CrossRef

27.

Shahin M, Chen FF, Hosseinzadeh A, Zand N (2023) Using machine learning and deep learning algorithms for downtime minimization in manufacturing systems: an early failure detection diagnostic service. Int J Adv Manuf Technol 128:3857–3883. https://doi.org/10.1007/s00170-023-12020-wCrossRef

28.

Shahin M, Chen F, Bouzary H et al (2023) Classification and detection of malicious attacks in industrial IoT devices via machine learning. In: Kim K-Y, Monplaisir L, Rickli J (eds) Flexible Automation and Intelligent Manufacturing: The Human-Data-Technology Nexus. Springer International Publishing, Cham, pp 99–106CrossRef

29.

Shahin M, Chen FF, Bouzary H, Zarreh A (2020) Frameworks proposed to address the threat of cyber-physical attacks to Lean 4.0 systems. Procedia Manuf 51:1184–1191. https://doi.org/10.1016/j.promfg.2020.10.166CrossRef

30.

Virmani N, Sharma V (2019) Prioritisation and assessment of leagile manufacturing enablers using interpretive structural modelling approach. Eur J Ind Eng 13:701–722. https://doi.org/10.1504/EJIE.2019.104293CrossRef

31.

Virmani N, Salve UR (2021) Significance of human factors and ergonomics (HFE): mediating its role between Industry 4.0 implementation and operational excellence. IEEE Trans Eng Manag. https://doi.org/10.1109/TEM.2021.3091398

32.

Kumar M, Rodrigues VS (2020) Synergetic effect of lean and green on innovation: a resource-based perspective. Int J Prod Econ 219:469–479. https://doi.org/10.1016/j.ijpe.2018.04.007CrossRef

33.

Mohammad S, Chen FF, Hosseinzadeh A, Maghanaki M (2023) Waste reduction via computer vision based inspection: towards lean systems in metal production

34.

Ganjavi N, Fazlollahtabar H (2023) Integrated sustainable production value measurement model based on Lean and Six Sigma in Industry 4.0 Context. IEEE Trans IEEE Trans Eng Manage 70:2320–2333. https://doi.org/10.1109/TEM.2021.3078169CrossRef

35.

Tronvoll B (2012) A dynamic model of customer complaining behaviour from the perspective of service-dominant logic. Eur J Mark 46:284–305. https://doi.org/10.1108/03090561211189338CrossRef

36.

Orsingher C, Valentini S, de Angelis M (2010) A meta-analysis of satisfaction with complaint handling in services. J Acad Mark Sci 38:169–186. https://doi.org/10.1007/s11747-009-0155-zCrossRef

37.

Levesque T, McDougall G (1996) Customer dissatisfaction: the relationship between types of problems and customer response. Rev Can Sci Adm-Can J Adm Sci 13:264–276CrossRef

38.

Womack JP, Jones DT (1997) Lean thinking—banish waste and create wealth in your corporation. J Oper Res Soc 48(11):1148–1148

39.

Found P, Harrison R (2012) Understanding the lean voice of the customer. Int J Lean Six Sigma 3:251–267. https://doi.org/10.1108/20401461211282736CrossRef

40.

Kovacs M, Buryakov D, Kryssanov V (2021) An unsupervised approach for customer need assessment in E-commerce: a case study of Japanese customer reviews. 2021 6th Int Conf Cloud Comput Internet Things 41–48. https://doi.org/10.1145/3493287.3493294

41.

Six sigma certifications. Int Six Sigma Inst. https://www.sixsigmainstitute.org/Six_Sigma_DMAIC_Process_Define_Phase_Capturing_Voice_Of_Customer_VOC.php. Accessed 6 May 2023

42.

Zhang M, Sun L, Wang GA et al (2022) Using neutral sentiment reviews to improve customer requirement identification and product design strategies. Int J Prod Econ 254. https://doi.org/10.1016/j.ijpe.2022.108641

43.

Barravecchia F, Mastrogiacomo L, Franceschini F (2022) KA-VoC map: classifying product key-attributes from digital voice-of-customer. Qual Eng 34:344–358. https://doi.org/10.1080/08982112.2022.2057805CrossRef

44.

Ohlig J, Poetters P, Leyendecker B (2021) The impact of digitalization on the define phase of the six sigma methodology. In: Proceedings of the International Conference on Industrial Engineering and Operations Management, pp 232–242

45.

Zonnenshain A, Kenett RS (2020) Quality 4.0—the challenging future of quality engineering. Qual Eng 32:614–626. https://doi.org/10.1080/08982112.2019.1706744CrossRef

46.

DeVellis RF, Thorpe CT (2021) Scale development: theory and applications. Sage Publicationshttps://doi.org/10.1111/peps.12499

47.

Groves RM (2006) Nonresponse rates and nonresponse bias in household surveys. Public Opin Q 70:646–675CrossRef

48.

CheshmehSohrabi M, Mashhadi A (2022) Using data mining, text mining, and bibliometric techniques to the research trends and gaps in the field of language and linguistics. J Psycholinguist Res 1–24. https://doi.org/10.1007/s10936-022-09911-6

49.

Bi J-W, Liu Y, Fan Z-P, Cambria E (2019) Modelling customer satisfaction from online reviews using ensemble neural network and effect-based Kano model. Int J Prod Res 57:7068–7088. https://doi.org/10.1080/00207543.2019.1574989CrossRef

50.

Sanchez-Nunez P, Cobo MJ, Heras-Pedrosa CDL et al (2020) Opinion mining, sentiment analysis and emotion understanding in advertising: a bibliometric analysis. IEEE Access Access IEEE 8:134563–134576. https://doi.org/10.1109/ACCESS.2020.3009482CrossRef

51.

Ozkaya I (2023) Application of large language models to software engineering tasks: opportunities, risks, and implications. IEEE Softw Softw IEEE IEEE Softw 40:4–8. https://doi.org/10.1109/MS.2023.3248401CrossRef

52.

Strobelt H, Webson A, Sanh V et al (2023) Interactive and visual prompt engineering for ad-hoc task adaptation with large language models. IEEE Trans Vis Comput Graph Vis Comput Graph 29:1146–1156. https://doi.org/10.1109/TVCG.2022.3209479CrossRef

53.

Kovalev AK, Panov AI (2023) Application of pretrained large language models in embodied artificial intelligence. Dokl Math 1–6. https://doi.org/10.1134/s1064562422060138

54.

Veres C (2022) Large language models are not models of natural language: they are corpus models. IEEE Access Access IEEE 10:61970–61979. https://doi.org/10.1109/ACCESS.2022.3182505CrossRef

55.

Leippold M (2023) Thus spoke GPT-3: interviewing a large-language model on climate finance. Finance Res Lett 53. https://doi.org/10.1016/j.frl.2022.103617

56.

Contreras Kallens P, Kristensen-McLachlan RD, Christiansen MH (2023) Large language models demonstrate the potential of statistical learning in language. Cogn Sci 47:1–6. https://doi.org/10.1111/cogs.13256CrossRef

57.

Ahmad Z (2023) Megatron NLG, ERNIE, and BLOOM: a look at GPT-3-like large language models. The Indian Express https://indianexpress.com/article/technology/gpt-3-like-llm-large-language-models-ernie-bloom-megatron-8396267/. Accessed 6 May 2023

58.

Walsh T (2022) Everyone’s having a field day with ChatGPT – but nobody knows how it actually works. In: The Conversation. http://theconversation.com/everyones-having-a-field-day-with-chatgpt-but-nobody-knows-how-it-actually-works-196378. Accessed 6 May 2023

59.

Shams R (2014) Semi-supervised classification for natural language processing. arXiv preprint arXiv:14097612

60.

Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Proces Syst 30

61.

Radford A, Narasimhan K, Salimans T, Sutskever I (2018) Improving language understanding by generative pretraining

62.

Gedeon T, Wong KW, Lee M (eds) (2019) Neural Information Processing: 26th International Conference, ICONIP 2019, Sydney, NSW, Australia, December 12–15, 2019, Proceedings, Part III (Vol. 11955). Springer Nature

63.

OpenAI R (2023) Gpt-4 technical report. Arxiv 2303.08774. View in Article 2:13

64.

De Angelis L, Baglivo F, Arzilli G, Privitera GP, Ferragina P, Tozzi AE, Rizzo C (2023) ChatGPT and the rise of large language models: the new AI-driven infodemic threat in public health. Front Public Health 11:1166120. https://doi.org/10.3389/fpubh.2023.1166120

65.

Customer Support on Twitter. https://www.kaggle.com/datasets/thoughtvector/customer-support-on-twitter. Accessed 7 May 2023

66.

Huang Y (2023) It’s time to create a private ChatGPT for yourself today. Medium https://levelup.gitconnected.com/itstime-to-create-a-private-chatgpt-for-yourself-today-6503649e7bb6. Accessed 7 May 2023

67.

Lo LS (2023) The CLEAR path: a framework for enhancing information literacy through prompt engineering. J Acad Librariansh 49(4):102720

Titel: A novel approach to voice of customer extraction using GPT-3.5 Turbo: linking advanced NLP and Lean Six Sigma 4.0
verfasst von: Mohammad Shahin
F. Frank Chen
Ali Hosseinzadeh
Mazdak Maghanaki
Ayda Eghbalian
Publikationsdatum: 19.02.2024
Verlag: Springer London
Erschienen in: The International Journal of Advanced Manufacturing Technology / Ausgabe 7-8/2024
Print ISSN: 0268-3768
Elektronische ISSN: 1433-3015
DOI: https://doi.org/10.1007/s00170-024-13167-w

Premium Partner

Marktübersichten

Die im Laufe eines Jahres in der „adhäsion“ veröffentlichten Marktübersichten helfen Anwendern verschiedenster Branchen, sich einen gezielten Überblick über Lieferantenangebote zu verschaffen.

Zur Marktübersicht

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Weitere Artikel der Ausgabe 7-8/2024

Research on the thermal forming limit diagram (TFLD) with the M-K model for Ti-6Al-4V alloy

An integrated framework for a multi-material surface roughness prediction model in CNC turning using theoretical and machine learning methods

Understanding the stress corrosion cracking resistance of laser shock surface patterned austenitic stainless-steel weld joints

Effect of magnesium addition consolidated by the thixoforming process on the wear properties of A319 alloy

Working end wear of 3D-laminated microelectrode in reverse-polarity PMEDM with Gr and Cu powders

Geometric error compensation method using the Laser R-test

Premium Partner

Marktübersichten