{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:20:07Z","timestamp":1773015607960,"version":"3.50.1"},"reference-count":47,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100002491","name":"Hansung University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002491","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>With the exponential growth of online reviews on e\u2010commerce platforms, efficiently identifying helpful reviews has become increasingly critical for supporting consumer decision\u2010making and mitigating information overload. The task of Review Helpfulness Prediction (RHP) aims to address this challenge by automatically filtering high\u2010quality and reliable content from massive volumes of user\u2010generated reviews. While earlier studies have explored this task through both feature\u2010based machine learning and deep learning models, these approaches often struggle to capture the complex linguistic nuances and contextual dependencies inherent in review texts. Although Transformer\u2010based models such as BERT have improved contextual representation learning, they rely on large\u2010scale labelled data and require extensive task\u2010specific fine\u2010tuning, which limits their adaptability and scalability in dynamic application settings. To overcome these limitations, we propose ELAS\u2010RHP, a novel instruction\u2010tuned framework grounded in Large Language Models (LLMs) that explicitly aligns model behaviour with the characteristics of the RHP task. Specifically, we reformulate review data into prompt\u2013completion pairs and apply Quantized Low\u2010Rank Adapters (QLoRA) to efficiently fine\u2010tune the LLaMA 3 model with reduced computational overhead. By incorporating a few\u2010shot learning strategy, ELAS\u2010RHP enables effective task adaptation under minimal supervision and constrained resources. Empirical evaluations conducted on real\u2010world datasets from Yelp and Amazon demonstrate that our framework consistently outperforms existing baselines across multiple evaluation scenarios. This study provides one of the first empirical investigations into instruction\u2010tuned LLMs for RHP and presents a scalable, efficient and context\u2010aware solution for enhancing review\u2010based information processing in e\u2010commerce environments.<\/jats:p>","DOI":"10.1111\/exsy.70208","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T13:44:03Z","timestamp":1768571043000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Instruction\u2010Tuned Large Language Models for Review Helpfulness Prediction: An Efficient Fine\u2010Tuning Framework for E\u2010Commerce Review Understanding"],"prefix":"10.1111","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8709-6751","authenticated-orcid":false,"given":"Xinzhe","family":"Li","sequence":"first","affiliation":[{"name":"Department of Big Data Analytics Kyung Hee University  Seoul Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-7765","authenticated-orcid":false,"given":"Qinglong","family":"Li","sequence":"additional","affiliation":[{"name":"Division of Computer Engineering Hansung University  Seoul Republic of Korea"}]},{"given":"Jaekyeong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Big Data Analytics Kyung Hee University  Seoul Republic of Korea"},{"name":"School of Management Kyung Hee University  Seoul Republic of Korea"}]}],"member":"311","published-online":{"date-parts":[[2026,1,16]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1177\/1470785318819979"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3470850"},{"key":"e_1_2_11_4_1","doi-asserted-by":"crossref","unstructured":"Bao K. J.Zhang Y.Zhang W.Wang F.Feng andX.He.2023.\u201cTallrec: An Effective and Efficient Tuning Framework to Align Large Language Model With Recommendation.\u201dProceedings of the 17th ACM Conference on Recommender Systems.","DOI":"10.1145\/3604915.3608857"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10660-022-09560-w"},{"key":"e_1_2_11_6_1","first-page":"1877","article-title":"Language Models Are Few\u2010Shot Learners","volume":"33","author":"Brown T.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_7_1","doi-asserted-by":"crossref","first-page":"10088","DOI":"10.52202\/075280-0441","article-title":"Qlora: Efficient Finetuning of Quantized Llms","volume":"36","author":"Dettmers T.","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_8_1","article-title":"Bert: Pre\u2010Training of Deep Bidirectional Transformers for Language Understanding","volume":"1810","author":"Devlin J.","year":"2018","journal-title":"arXiv"},{"key":"e_1_2_11_9_1","article-title":"The Llama 3 Herd of Models","volume":"2407","author":"Dubey A.","year":"2024","journal-title":"arXiv"},{"issue":"362","key":"e_1_2_11_10_1","first-page":"1","article-title":"Discovering Salient Neurons in Deep NLP Models","volume":"24","author":"Durrani N.","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111531"},{"key":"e_1_2_11_12_1","doi-asserted-by":"crossref","unstructured":"Hu B. Q.Sheng J.Cao et\u00a0al.2024.\u201cBad Actor Good Advisor: Exploring the Role of Large Language Models in Fake News Detection.\u201dProceedings of the AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v38i20.30214"},{"issue":"2","key":"e_1_2_11_13_1","article-title":"Lora: Low\u2010Rank Adaptation of Large Language Models","volume":"1","author":"Hu E. J.","year":"2022","journal-title":"ICLR"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2016.06.003"},{"key":"e_1_2_11_15_1","article-title":"Opt\u2010Iml: Scaling Language Model Instruction Meta Learning Through the Lens of Generalization","volume":"2212","author":"Iyer S.","year":"2022","journal-title":"arXiv"},{"key":"e_1_2_11_16_1","unstructured":"Jang J. S.Kim S.Ye et\u00a0al.2023.\u201cExploring the Benefits of Training Expert Language Models Over Instruction Tuning.\u201dInternational Conference on Machine Learning."},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40547-024-00143-4"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1108\/IJCHM-06-2020-0587"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3348778"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1108\/JHTT-09-2023-0255"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2023.2166226"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-06100-x"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128576"},{"key":"e_1_2_11_24_1","article-title":"Few\u2010Shot Learning With Multilingual Language Models","volume":"2112","author":"Lin X. V.","year":"2021","journal-title":"arXiv"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.12.036"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3294636"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2017.09.004"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102434"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102538"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-025-00959-9"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.11.029"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116787"},{"key":"e_1_2_11_33_1","first-page":"27730","article-title":"Training Language Models to Follow Instructions With Human Feedback","volume":"35","author":"Ouyang L.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_34_1","article-title":"Instruction Tuning With Gpt\u20104","volume":"2304","author":"Peng B.","year":"2023","journal-title":"arXiv"},{"key":"e_1_2_11_35_1","article-title":"When Does In\u2010Context Learning Fall Short and Why? A Study on Specification\u2010Heavy Tasks","volume":"2311","author":"Peng H.","year":"2023","journal-title":"arXiv"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103573"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120344"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbusres.2016.08.008"},{"key":"e_1_2_11_39_1","article-title":"Llama: Open and Efficient Foundation Language Models","volume":"2302","author":"Touvron H.","year":"2023","journal-title":"arXiv"},{"key":"e_1_2_11_40_1","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_41_1","article-title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","volume":"2412","author":"Warner B.","year":"2024","journal-title":"arXiv"},{"key":"e_1_2_11_42_1","article-title":"Finetuned Language Models Are Zero\u2010Shot Learners","volume":"2109","author":"Wei J.","year":"2021","journal-title":"arXiv"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118138"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121878"},{"key":"e_1_2_11_45_1","article-title":"Instruction Tuning for Large Language Models: A Survey","volume":"2308","author":"Zhang S.","year":"2023","journal-title":"arXiv"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.elerap.2017.10.008"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhm.2023.103579"},{"key":"e_1_2_11_48_1","first-page":"1","article-title":"A Comprehensive Survey on Pretrained Foundation Models: A History From Bert to Chatgpt","volume":"16","author":"Zhou C.","year":"2024","journal-title":"International Journal of Machine Learning and Cybernetics"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70208","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70208","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T23:21:50Z","timestamp":1773012110000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1111\/exsy.70208"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70208","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,16]]},"assertion":[{"value":"2025-07-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70208"}}