{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:48:20Z","timestamp":1782755300066,"version":"3.54.5"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Northeastern University USA"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>LLarge language models (LLMs) demonstrate strong natural language processing capabilities but come with significant computational costs, raising questions about their practical utility compared to small language models (SLMs). This study systematically compares SLMs (DistilBERT, ELECTRA) and LLMs (Flan-T5, Flan-UL2) on two customer review analysis tasks: sentiment polarity classification and product correlation analysis. Our results show that while LLMs outperform in sentiment classification, they do so at a much higher computational cost, whereas fine-tuned SLMs excel in domain-specific correlation analysis with greater efficiency. To balance accuracy and cost, we propose a context-enhanced hybrid (CE-Hybrid) model, which refines traditional hybrid methods by enriching LLM input with SLM-generated insights, reducing redundant computation while maintaining accuracy. Our findings quantify the trade-offs between model performance and resource efficiency, offering actionable insights for businesses to optimize AI deployment. These results have significant implications for real-world applications such as e-commerce, customer service automation, and business analytics.<\/jats:p>","DOI":"10.1007\/s10462-025-11308-5","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T04:33:32Z","timestamp":1754627612000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Do you actually need an LLM? Rethinking language models for customer reviews analysis"],"prefix":"10.1007","volume":"58","author":[{"given":"Yang","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunke","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoyujie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hayden","family":"Barker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan","family":"Rad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,8]]},"reference":[{"key":"11308_CR1","unstructured":"Statista (2023) Generative AI - Worldwide. Accessed: 2024-02-12. https:\/\/www.statista.com\/outlook\/tmo\/artificial-intelligence\/generative-ai\/worldwide"},{"key":"11308_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"key":"11308_CR3","unstructured":"Bubeck S, Chandrasekaran V, Eldan R, Gehrke J, Horvitz E, Kamar E, Lee P, Lee YT, Li Y, Lundberg S, Nori H, Palangi H, Ribeiro MT, Zhang Y (2023) Sparks of Artificial General Intelligence: Early experiments with GPT-4"},{"key":"11308_CR4","unstructured":"Touvron H, Martin L, Stone K et al (2023) Llama 2: open foundation and fine-tuned chat models"},{"key":"11308_CR5","doi-asserted-by":"publisher","first-page":"3457","DOI":"10.1109\/TCSS.2023.3334306","volume":"11","author":"X Zheng","year":"2024","unstructured":"Zheng X, Li J, Lu M, Wang F-Y (2024) New paradigm for economic and financial research with generative ai: impact and perspective. IEEE Trans Comput Soc Syst 11:3457","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"11308_CR6","unstructured":"Yan Q, Seraj R, He J, Meng L, Sylvain T (2023) Autocast++: Enhancing world event prediction with zero-shot ranking-based context retrieval. arXiv preprint arXiv:2310.01880"},{"key":"11308_CR7","unstructured":"Halawi D, Zhang F, Yueh-Han C, Steinhardt J (2024) Approaching human-level forecasting with language models. arXiv preprint arXiv:2402.18563"},{"issue":"1","key":"11308_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/1500000011","volume":"2","author":"B Pang","year":"2008","unstructured":"Pang B, Lee L et al (2008) Opinion mining and sentiment analysis. Found Trends Inf Retr 2(1):1\u2013135","journal-title":"Found Trends Inf Retr"},{"key":"11308_CR9","doi-asserted-by":"crossref","unstructured":"Zhang W, Deng Y, Liu B, Pan SJ, Bing L (2023) Sentiment analysis in the era of large language models: A reality check. arXiv preprint arXiv:2305.15005","DOI":"10.18653\/v1\/2024.findings-naacl.246"},{"key":"11308_CR10","doi-asserted-by":"publisher","unstructured":"Chien AA, Lin L, Nguyen H, Rao V, Sharma T, Wijayawardana R (2023) Reducing the carbon impact of generative ai inference (today and in 2035). In: Proceedings of the 2nd workshop on sustainable computer systems. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3604930.3605705","DOI":"10.1145\/3604930.3605705"},{"issue":"1","key":"11308_CR11","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13040-023-00339-9","volume":"16","author":"JG Meyer","year":"2023","unstructured":"Meyer JG, Urbanowicz RJ, Martin PC, Connor O (2023) Chatgpt and large language models in academia: opportunities and challenges. BioData Min 16(1):20","journal-title":"BioData Min"},{"key":"11308_CR12","doi-asserted-by":"publisher","unstructured":"Keung P, Lu Y, Szarvas G, Smith NA (2020) The multilingual Amazon reviews corpus. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), pp. 4563\u20134568. Association for Computational Linguistics, Online. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.369. https:\/\/aclanthology.org\/2020.emnlp-main.369","DOI":"10.18653\/v1\/2020.emnlp-main.369"},{"issue":"7","key":"11308_CR13","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1080\/10941665.2012.708351","volume":"18","author":"QY Huiying Li","year":"2013","unstructured":"Huiying Li QY, Law R (2013) Determinants of customer satisfaction in the hotel industry: an application of online review analysis. Asia Pac J Tour Res 18(7):784\u2013802. https:\/\/doi.org\/10.1080\/10941665.2012.708351","journal-title":"Asia Pac J Tour Res"},{"key":"11308_CR14","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1007\/978-3-7091-1142-0_40","volume-title":"Information and communication technologies in tourism 2012","author":"D Gr\u00e4bner","year":"2012","unstructured":"Gr\u00e4bner D, Zanker M, Fliedl G, Fuchs M (2012) Classification of customer reviews based on sentiment analysis. Information and communication technologies in tourism 2012. Springer, Cham, pp 460\u2013470"},{"key":"11308_CR15","doi-asserted-by":"publisher","unstructured":"Kumar KLS, Desai J, Majumdar J (2016) Opinion mining and sentiment analysis on online customer review. In: 2016 IEEE international conference on computational intelligence and computing research (ICCIC), pp. 1\u20134. https:\/\/doi.org\/10.1109\/ICCIC.2016.7919584","DOI":"10.1109\/ICCIC.2016.7919584"},{"key":"11308_CR16","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5909","author":"A Onan","year":"2020","unstructured":"Onan A (2020) Sentiment analysis on product reviews based on weighted word embeddings and deep neural networks. Concurr Comput Prac Exp. https:\/\/doi.org\/10.1002\/cpe.5909","journal-title":"Concurr Comput Prac Exp"},{"key":"11308_CR17","doi-asserted-by":"publisher","first-page":"11019","DOI":"10.1109\/TKDE.2022.3230975","volume":"35","author":"W Zhang","year":"2022","unstructured":"Zhang W, Li X, Deng Y, Bing L, Lam W (2022) A survey on aspect-based sentiment analysis: tasks, methods, and challenges. IEEE Trans Knowl Data Eng 35:11019","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"11308_CR18","first-page":"1","volume":"6","author":"R Alghamdi","year":"2015","unstructured":"Alghamdi R, Alfalqi K (2015) A survey of topic modeling in text mining. Int J Adv Comput Sci Appl (IJACSA) 6:1","journal-title":"Int J Adv Comput Sci Appl (IJACSA)"},{"issue":"11","key":"11308_CR19","doi-asserted-by":"publisher","first-page":"11019","DOI":"10.1109\/TKDE.2022.3230975","volume":"35","author":"W Zhang","year":"2023","unstructured":"Zhang W, Li X, Deng Y, Bing L, Lam W (2023) A survey on aspect-based sentiment analysis: tasks, methods, and challenges. IEEE Trans Knowl Data Eng 35(11):11019\u201311038. https:\/\/doi.org\/10.1109\/TKDE.2022.3230975","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"8","key":"11308_CR20","doi-asserted-by":"publisher","first-page":"6343","DOI":"10.1007\/s10462-021-09955-5","volume":"54","author":"LDCS Subhashini","year":"2021","unstructured":"Subhashini LDCS, Li Y, Zhang J, Atukorale AS, Wu Y (2021) Mining and classifying customer reviews: a survey. Artif Intell Rev 54(8):6343\u20136389. https:\/\/doi.org\/10.1007\/s10462-021-09955-5","journal-title":"Artif Intell Rev"},{"key":"11308_CR21","unstructured":"Tay Y, Dehghani M, Tran VQ, Garcia X, Bahri D, Schuster T, Zheng HS, Houlsby N, Metzler D (2022) Unifying language learning paradigms. arXiv preprint arXiv:2205.05131"},{"key":"11308_CR22","unstructured":"Chung HW, Hou L, Longpre S, Zoph B, Tay Y, Fedus W, Li Y, Wang X, Dehghani M, Brahma S, et al (2022) Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416"},{"key":"11308_CR23","doi-asserted-by":"publisher","unstructured":"Lester B, Al-Rfou R, Constant N (2021) The power of scale for parameter-efficient prompt tuning. In: Moens, M.-F., Huang, X., Specia, L., Yih, S.W.-t. (eds.) Proceedings of the 2021 conference on empirical methods in natural language processing, pp. 3045\u20133059. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.243. https:\/\/aclanthology.org\/2021.emnlp-main.243","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"11308_CR24","first-page":"1950","volume":"35","author":"H Liu","year":"2022","unstructured":"Liu H, Tam D, Muqeeth M, Mohta J, Huang T, Bansal M, Raffel C (2022) Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Adv Neural Inf Process Syst 35:1950","journal-title":"Adv Neural Inf Process Syst"},{"key":"11308_CR25","first-page":"55006","volume":"36","author":"C Zhou","year":"2023","unstructured":"Zhou C, Liu P, Xu P, Iyer S, Sun J, Mao Y, Ma X, Efrat A, Yu P, Yu L, Zhang S, Ghosh G, Lewis M, Zettlemoyer L, Levy O (2023) LIMA: less is more for alignment. Adv Neural Inf Process Syst 36:55006","journal-title":"Adv Neural Inf Process Syst"},{"key":"11308_CR26","unstructured":"Zhong Q, Ding L, Liu J, Du B, Tao D (2023) Can chatgpt understand too? A comparative study on chatgpt and fine-tuned bert. arXiv preprint arXiv:2302.10198"},{"key":"11308_CR27","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692arXiv:1907.11692"},{"key":"11308_CR28","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2018) BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805. arXiv:1810.04805"},{"key":"11308_CR29","unstructured":"Sanh V, Debut L, Chaumond J, Wolf T (2019) Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR abs\/1910.01108arXiv:1910.01108"},{"key":"11308_CR30","unstructured":"He P, Liu X, Gao J, Chen W (2020) Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654"},{"key":"11308_CR31","unstructured":"Clark K, Luong M-T, Le QV, Manning CD (2020) ELECTRA: pre-training text encoders as discriminators rather than generators"},{"key":"11308_CR32","unstructured":"Kaggle (2024) Amazon US Customer Reviews Dataset. Kaggle Dataset. https:\/\/www.kaggle.com\/datasets\/cynthiarempel\/amazon-us-customer-reviews-dataset\/data"},{"key":"11308_CR33","unstructured":"Custom Dataset for Task 2. https:\/\/drive.google.com\/drive\/folders\/1wgGfCM5ht8HqwmdNPyvS7tA7RRuZ_DbP"},{"key":"11308_CR34","unstructured":"Zhang X, Zhao JJ, LeCun Y (2015) Character-level convolutional networks for text classification. CoRR abs\/1509.01626arXiv:1509.01626"},{"key":"11308_CR35","doi-asserted-by":"publisher","unstructured":"Stigall W, Al\u00a0Hafiz\u00a0Khan MA, Attota D, Nweke F, Pei Y (2024) Large language models performance comparison of emotion and sentiment classification. In: Proceedings of the 2024 ACM Southeast Conference. ACMSE \u201924, pp. 60\u201368. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3603287.3651183","DOI":"10.1145\/3603287.3651183"},{"key":"11308_CR36","unstructured":"Shah FA, Sabir A, Sharma R (2024) A fine-grained sentiment analysis of app reviews using large language models: an evaluation study. https:\/\/arxiv.org\/abs\/2409.07162"},{"key":"11308_CR37","unstructured":"Leviathan Y, Kalman M, Matias Y (2023) Fast inference from transformers via speculative decoding. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th international conference on machine learning. Proceedings of machine learning research, vol. 202, pp. 19274\u201319286. PMLR, New York, NY, USA. https:\/\/proceedings.mlr.press\/v202\/leviathan23a.html"},{"key":"11308_CR38","doi-asserted-by":"publisher","unstructured":"Patterson D, Gonzalez J, Le Q, Liang C, Munguia L-M, Rothchild D, Yinan D, Dicker J, Corrado G (2021) Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350https:\/\/doi.org\/10.48550\/arXiv.2104.10350","DOI":"10.48550\/arXiv.2104.10350"},{"issue":"12","key":"11308_CR39","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/3381831","volume":"63","author":"R Schwartz","year":"2020","unstructured":"Schwartz R, Dodge J, Smith NA, Etzioni O (2020) Green ai. Commun ACM 63(12):54\u201363. https:\/\/doi.org\/10.1145\/3381831","journal-title":"Commun ACM"},{"issue":"1","key":"11308_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3458754","volume":"3","author":"Y Gu","year":"2021","unstructured":"Gu Y, Tinn R, Cheng H, Lucas M, Usuyama N, Liu X, Naumann T, Gao J, Poon H (2021) Domain-specific language model pretraining for biomedical natural language processing. ACM Trans Comput Healthc 3(1):1\u201323. https:\/\/doi.org\/10.1145\/3458754","journal-title":"ACM Trans Comput Healthc"},{"key":"11308_CR41","doi-asserted-by":"publisher","unstructured":"Chalkidis I, Fergadiotis M, Malakasiotis P, Aletras N, Androutsopoulos I (2020) LEGAL-BERT: The Muppets straight out of Law School. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 2898\u20132904. Association for Computational Linguistics, Online. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.261. https:\/\/aclanthology.org\/2020.findings-emnlp.261","DOI":"10.18653\/v1\/2020.findings-emnlp.261"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11308-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-025-11308-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11308-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T18:10:15Z","timestamp":1757700615000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-025-11308-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,8]]},"references-count":41,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["11308"],"URL":"https:\/\/doi.org\/10.1007\/s10462-025-11308-5","relation":{},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,8]]},"assertion":[{"value":"16 June 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This publication contains general information only and Deloitte is not, by means of this publication, rendering accounting, business, financial, investment, legal, tax, or other professional advice or services. This publication is not a substitute for such professional advice or services, nor should it be used as a basis for any decision or action that may affect your business. Before making any decision or taking any action that may affect your business, you should consult a qualified professional advisor. Deloitte shall not be responsible for any loss sustained by any person who relies on this publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"332"}}