IDEAS home Printed from https://ideas.repec.org/a/eee/joreco/v81y2024ics0969698924002716.html
   My bibliography  Save this article

Crafting clarity: Leveraging large language models to decode consumer reviews

Author

Listed:
  • Praveen, S.V.
  • Gajjar, Pranshav
  • Ray, Rajeev Kumar
  • Dutt, Ashutosh

Abstract

Large Language Models (LLMs) have emerged as powerful tools for understanding consumer perceptions and extracting insights from unstructured textual data. This study investigates the effectiveness of LLMs in comprehending consumer opinions, particularly in service industries. We fine-tuned four prominent LLMs—Falcon-7B, MPT-7B, GPT-2, and BERT—using 1,031,478 consumer reviews and assessed their ability to identify topics, emotions, and sentiments. Our results indicate that Falcon-7B excels in accuracy and reliability for complex tasks. This study is the first, to our knowledge, to fine-tune Large Language Models (LLMs) specifically for consumer data, showcasing the efficacy of attention mechanisms in extracting valuable insights. Our findings offer strategic decision-making insights for the service industry and underscore the transformative potential of LLMs in business intelligence from consumer feedback.

Suggested Citation

  • Praveen, S.V. & Gajjar, Pranshav & Ray, Rajeev Kumar & Dutt, Ashutosh, 2024. "Crafting clarity: Leveraging large language models to decode consumer reviews," Journal of Retailing and Consumer Services, Elsevier, vol. 81(C).
    • Handle: RePEc:eee:joreco:v:81:y:2024:i:c:s0969698924002716
    DOI: 10.1016/j.jretconser.2024.103975
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0969698924002716
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.jretconser.2024.103975?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Mike Thelwall & Kevan Buckley & Georgios Paltoglou & Di Cai & Arvid Kappas, 2010. "Sentiment strength detection in short informal text," Journal of the American Society for Information Science and Technology, Association for Information Science & Technology, vol. 61(12), pages 2544-2558, December.
    2. Basu, Bibaswan & Sebastian, M.P. & Kar, Arpan Kumar, 2024. "What affects the promoting intention of mobile banking services? Insights from mining consumer reviews," Journal of Retailing and Consumer Services, Elsevier, vol. 77(C).
    3. Kim, Da Yeon & Kim, Sang Yong, 2023. "Investigating the effect of customer-generated content on performance in online platform-based experience goods market," Journal of Retailing and Consumer Services, Elsevier, vol. 74(C).
    4. Mike Thelwall & Kevan Buckley & Georgios Paltoglou & Di Cai & Arvid Kappas, 2010. "Sentiment strength detection in short informal text," Journal of the Association for Information Science & Technology, Association for Information Science & Technology, vol. 61(12), pages 2544-2558, December.
    5. Margaret Roberts & Brandon Stewart & Tingley, Dustin & Edoardo Airoldi, 2013. "The structural topic model and applied social science," Working Paper 132666, Harvard University OpenScholar.
    6. Bharati Sanjay Ainapure & Reshma Nitin Pise & Prathiba Reddy & Bhargav Appasani & Avireni Srinivasulu & Mohammad S. Khan & Nicu Bizon, 2023. "Sentiment Analysis of COVID-19 Tweets Using Deep Learning and Lexicon-Based Approaches," Sustainability, MDPI, vol. 15(3), pages 1-21, January.
    7. Wu, Jia-Jhou & Chang, Sue-Ting, 2020. "Exploring customer sentiment regarding online retail services: A topic-based approach," Journal of Retailing and Consumer Services, Elsevier, vol. 55(C).
    8. Kumar, Avinash & Chakraborty, Shibashish & Bala, Pradip Kumar, 2023. "Text mining approach to explore determinants of grocery mobile app satisfaction using online customer reviews," Journal of Retailing and Consumer Services, Elsevier, vol. 73(C).
    9. Filieri, Raffaele, 2015. "What makes online reviews helpful? A diagnosticity-adoption framework to explain informational and normative influences in e-WOM," Journal of Business Research, Elsevier, vol. 68(6), pages 1261-1270.
    10. Sánchez-Franco, Manuel J. & Arenas-Márquez, Francisco J. & Alonso-Dos-Santos, Manuel, 2021. "Using structural topic modelling to predict users’ sentiment towards intelligent personal agents. An application for Amazon’s echo and Google Home," Journal of Retailing and Consumer Services, Elsevier, vol. 63(C).
    11. Yue Kang & Zhao Cai & Chee-Wee Tan & Qian Huang & Hefu Liu, 2020. "Natural language processing (NLP) in management research: A literature review," Journal of Management Analytics, Taylor & Francis Journals, vol. 7(2), pages 139-172, April.
    12. Luong, Van Ha & Tarquini, Annalisa & Anadol, Yaprak & Klaus, Phil & Manthiou, Aikaterini, 2024. "Is digital fashion the future of the metaverse? Insights from YouTube comments," Journal of Retailing and Consumer Services, Elsevier, vol. 79(C).
    13. Sparks, Beverley A. & Browning, Victoria, 2011. "The impact of online reviews on hotel booking intentions and perception of trust," Tourism Management, Elsevier, vol. 32(6), pages 1310-1323.
    14. Stanca, Liana & Dabija, Dan-Cristian & Câmpian, Veronica, 2023. "Qualitative analysis of customer behavior in the retail industry during the COVID-19 pandemic: A word-cloud and sentiment analysis approach," Journal of Retailing and Consumer Services, Elsevier, vol. 75(C).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Mustak, Mekhail & Hallikainen, Heli & Laukkanen, Tommi & Plé, Loïc & Hollebeek, Linda D. & Aleem, Majid, 2024. "Using machine learning to develop customer insights from user-generated content," Journal of Retailing and Consumer Services, Elsevier, vol. 81(C).
    2. Michal Maj & Damian Pliszczuk & Patryk Marek & Weronika Wilczewska & Bartosz Przysucha & Tomasz Rymarczyk, 2024. "Optimizing Customer Support Using Text2SQL to Query Natural Language Databases," European Research Studies Journal, European Research Studies Journal, vol. 0(Special B), pages 426-438.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Kumari, Vandana & Bala, Pradip Kumar & Chakraborty, Shibashish, 2024. "A text mining approach to explore factors influencing consumer intention to use metaverse platform services: Insights from online customer reviews," Journal of Retailing and Consumer Services, Elsevier, vol. 81(C).
    2. Bellary, Sreevatsa & Bala, Pradip Kumar & Chakraborty, Shibashish, 2024. "Exploring cognitive-behavioral drivers impacting consumer continuance intention of fitness apps using a hybrid approach of text mining, SEM, and ANN," Journal of Retailing and Consumer Services, Elsevier, vol. 81(C).
    3. Desiraju, Kanti & Mishra, Arindra Nath & Sengupta, Pooja, 2024. "Customer perceptions on open banking apps: Insights using Structural topic modeling," Journal of Retailing and Consumer Services, Elsevier, vol. 81(C).
    4. Kumar, Anand & Bala, Pradip Kumar & Chakraborty, Shibashish & Behera, Rajat Kumar, 2024. "Exploring antecedents impacting user satisfaction with voice assistant app: A text mining-based analysis on Alexa services," Journal of Retailing and Consumer Services, Elsevier, vol. 76(C).
    5. Shobhit Kakaria & Aline Simonetti & Enrique Bigne, 2024. "Interaction between extrinsic and intrinsic online review cues: perspectives from cue utilization theory," Electronic Commerce Research, Springer, vol. 24(4), pages 2469-2497, December.
    6. Ma, Jie & Tse, Ying Kei & Wang, Xiaojun & Zhang, Minhao, 2019. "Examining customer perception and behaviour through social media research – An empirical study of the United Airlines overbooking crisis," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 127(C), pages 192-205.
    7. Book, Laura A. & Tanford, Sarah & Chang, Wen, 2018. "Customer reviews are not always informative: The impact of effortful versus heuristic processing," Journal of Retailing and Consumer Services, Elsevier, vol. 41(C), pages 272-280.
    8. Kübler, Raoul V. & Manke, Kai & Pauwels, Koen, 2025. "I like, I share, I vote: Mapping the dynamic system of political marketing," Journal of Business Research, Elsevier, vol. 186(C).
    9. Moradi, Masoud & Dass, Mayukh & Kumar, Piyush, 2023. "Differential effects of analytical versus emotional rhetorical style on review helpfulness," Journal of Business Research, Elsevier, vol. 154(C).
    10. Müller-Hansen, Finn & Lee, Yuan Ting & Callaghan, Max & Jankin, Slava & Minx, Jan C., 2022. "The German coal debate on Twitter: Reactions to a corporate policy process," Energy Policy, Elsevier, vol. 169(C).
    11. Elvira Ismagilova & Emma L. Slade & Nripendra P. Rana & Yogesh K. Dwivedi, 2020. "The Effect of Electronic Word of Mouth Communications on Intention to Buy: A Meta-Analysis," Information Systems Frontiers, Springer, vol. 22(5), pages 1203-1226, October.
    12. Lipizzi, Carlo & Iandoli, Luca & Ramirez Marquez, José Emmanuel, 2015. "Extracting and evaluating conversational patterns in social media: A socio-semantic analysis of customers’ reactions to the launch of new products using Twitter streams," International Journal of Information Management, Elsevier, vol. 35(4), pages 490-503.
    13. Martin Haselmayer & Marcelo Jenny, 2017. "Sentiment analysis of political communication: combining a dictionary approach with crowdcoding," Quality & Quantity: International Journal of Methodology, Springer, vol. 51(6), pages 2623-2646, November.
    14. Daesik Kim & Chung Joo Chung & Kihong Eom, 2022. "Measuring Online Public Opinion for Decision Making: Application of Deep Learning on Political Context," Sustainability, MDPI, vol. 14(7), pages 1-16, March.
    15. David M. Goldberg & Nohel Zaman & Arin Brahma & Mariano Aloiso, 2022. "Are mortgage loan closing delay risks predictable? A predictive analysis using text mining on discussion threads," Journal of the Association for Information Science & Technology, Association for Information Science & Technology, vol. 73(3), pages 419-437, March.
    16. Gabriele Ranco & Ilaria Bordino & Giacomo Bormetti & Guido Caldarelli & Fabrizio Lillo & Michele Treccani, 2014. "Coupling news sentiment with web browsing data improves prediction of intra-day price dynamics," Papers 1412.3948, arXiv.org, revised Dec 2015.
    17. Tadić, Bosiljka & Mitrović Dankulov, Marija & Melnik, Roderick, 2023. "Evolving cycles and self-organised criticality in social dynamics," Chaos, Solitons & Fractals, Elsevier, vol. 171(C).
    18. Meek, Stephanie & Wilk, Violetta & Lambert, Claire, 2021. "A big data exploration of the informational and normative influences on the helpfulness of online restaurant reviews," Journal of Business Research, Elsevier, vol. 125(C), pages 354-367.
    19. Ping-Yu Hsu & Hong-Tsuen Lei & Shih-Hsiang Huang & Teng Hao Liao & Yao-Chung Lo & Chin-Chun Lo, 2019. "Effects of sentiment on recommendations in social network," Electronic Markets, Springer;IIM University of St. Gallen, vol. 29(2), pages 253-262, June.
    20. Yi Feng & Yunqiang Yin & Dujuan Wang & Lalitha Dhamotharan & Joshua Ignatius & Ajay Kumar, 2023. "Diabetic patient review helpfulness: unpacking online drug treatment reviews by text analytics and design science approach," Annals of Operations Research, Springer, vol. 328(1), pages 387-418, September.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:joreco:v:81:y:2024:i:c:s0969698924002716. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: https://www.journals.elsevier.com/journal-of-retailing-and-consumer-services .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.