{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:34:58Z","timestamp":1777336498756,"version":"3.51.4"},"reference-count":64,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>\n                    The exponential growth of the mobile app market underscores the importance of constant innovation and rapid response to user demands. As user satisfaction is paramount to the success of a mobile application (app), developers typically rely on user reviews, which represent user feedback that includes ratings and comments to identify areas for improvement. However, the sheer volume of user reviews poses challenges in manual analysis, necessitating automated approaches. Existing automated approaches either analyze only the target app\u2019s reviews, neglecting the comparison of similar features to competitors or fail to provide suggestions for feature enhancement. To address these gaps, we propose a\n                    <jats:italic toggle=\"yes\">Large Language Model (LLM)-based Competitive User Review Analysis for Feature Enhancement)<\/jats:italic>\n                    (\n                    <jats:italic toggle=\"yes\">LLM-Cure<\/jats:italic>\n                    ), an approach powered by LLMs to automatically generate suggestions for mobile app feature improvements. More specifically,\n                    <jats:italic toggle=\"yes\">LLM-Cure<\/jats:italic>\n                    identifies and categorizes features within reviews by applying LLMs. When provided with a complaint in a user review,\n                    <jats:italic toggle=\"yes\">LLM-Cure<\/jats:italic>\n                    curates highly rated (4 and 5 stars) reviews in competing apps related to the complaint and proposes potential improvements tailored to the target application. We evaluate\n                    <jats:italic toggle=\"yes\">LLM-Cure<\/jats:italic>\n                    on 1,056,739 reviews of 70 popular Android apps. Our evaluation demonstrates that\n                    <jats:italic toggle=\"yes\">LLM-Cure<\/jats:italic>\n                    significantly outperforms the state-of-the-art approaches in assigning features to reviews by up to 13% in F1-score, 16% in recall, and 11% in precision. Additionally,\n                    <jats:italic toggle=\"yes\">LLM-Cure<\/jats:italic>\n                    demonstrates its capability to provide suggestions for resolving user complaints. We verify the suggestions using the release notes that reflect the changes of features in the target mobile app.\n                    <jats:italic toggle=\"yes\">LLM-Cure<\/jats:italic>\n                    achieves a promising average of 73% of the implementation of the provided suggestions, demonstrating its potential for competitive feature enhancement.\n                  <\/jats:p>","DOI":"10.1145\/3744644","type":"journal-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T11:22:44Z","timestamp":1749727364000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["LLM-Cure: LLM-Based Competitor User Review Analysis for Feature Enhancement"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1274-7550","authenticated-orcid":false,"given":"Maram","family":"Assi","sequence":"first","affiliation":[{"name":"Department of Computer Science, Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7090-0475","authenticated-orcid":false,"given":"Safwat","family":"Hassan","sequence":"additional","affiliation":[{"name":"Faculty of Information, University of Toronto, Toronto, Ontario, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5335-0261","authenticated-orcid":false,"given":"Ying","family":"Zou","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Queen\u2019s University, Kingston, Ontario, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,11]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Mistral AI. 2024. Mixtral of experts. Retrieved from https:\/\/mistral.ai\/news\/mixtral-of-experts\/"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2891715"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3152494.3152500"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICARC61713.2024.10499727"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593802"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-09988-y"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944966"},{"key":"e_1_3_2_9_2","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. arXiv:2005.14165. Retrieved from https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_10_2","unstructured":"Published by Laura Ceci and Mar 4. 2024. Messaging apps: Most popular by global downloads 2024. Retrieved from https:\/\/www.statista.com\/statistics\/1263360\/most-popular-messenger-apps-worldwide-by-monthly-downloads\/"},{"key":"e_1_3_2_11_2","unstructured":"Laura Ceci. 2024. Number of mobile app downloads worldwide from 2016 to 2023. Retrieved May 2024 from https:\/\/www.https:\/\/www.statista.com\/statistics\/271644\/worldwide-free-and-paid-mobile-app-store-downloads\/"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2568225.2568263"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-15538-4_4"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1057\/s41599-022-01190-9"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE54965.2022.00023"},{"key":"e_1_3_2_17_2","unstructured":"Qingxiu Dong Lei Li Damai Dai Ce Zheng Zhiyong Wu Baobao Chang Xu Sun Jingjing Xu Lei Li and Zhifang Sui. 2023. A survey on in-context learning. arXiv:2301.00234. Retrieved from https:\/\/arxiv.org\/abs\/2301.00234"},{"key":"e_1_3_2_18_2","unstructured":"Yihong Dong Xue Jiang Zhi Jin and Ge Li .2023. Self-collaboration code generation via ChatGPT. arXiv:2304.07590. Retrieved from https:\/\/arxiv.org\/abs\/2304.07590"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3638067.3638081"},{"key":"e_1_3_2_20_2","unstructured":"Zhiyu Fan Xiang Gao Abhik Roychoudhury and Shin Hwei Tan. 2022. Improving automatically generated code from Codex via automated program repair. arXiv:2205.10583. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:248986410"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488202"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2022.3217566"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00040"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1002\/smr.2257"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00107"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1036"},{"key":"e_1_3_2_27_2","unstructured":"Xinyi Hou Yanjie Zhao Yue Liu Zhou Yang Kailong Wang Li Li Xiapu Luo David Lo John Grundy and Haoyu Wang. 2024. Large language models for software engineering: A systematic literature review. arXiv:2308.10620. Retrieved from https:\/\/arxiv.org\/abs\/2308.10620"},{"key":"e_1_3_2_28_2","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-rank adaptation of large language models. arXiv:2106.09685. Retrieved from https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_29_2","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin et al. 2023. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. arXiv:2311.05232. Retrieved from https:\/\/arxiv.org\/abs\/2311.05232"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.5555\/2487085.2487094"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2017.71"},{"issue":"1","key":"e_1_3_2_32_2","first-page":"75:1","article-title":"Mining user reviews for mobile app comparisons","author":"Li Yuanchun","year":"2017","unstructured":"Yuanchun Li, Baoxiong Jia, Yao Guo, and Xiangqun Chen. 2017. Mining user reviews for mobile app comparisons. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 1, 3 (Sep. 2017), 75:1\u201375:15.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Vitor Lima Jacson Barbosa and Ricardo Marcacini. 2023. Learning risk factors from app reviews: A large language model approach for risk matrix construction (Version 1). Research Square. \u00a0DOI: 10.21203\/rs.3.rs-3182322\/v1]","DOI":"10.21203\/rs.3.rs-3182322\/v1]"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.08.050"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639118"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2015.7320414"},{"key":"e_1_3_2_37_2","unstructured":"Gr\u00e9goire Mialon Roberto Dess\u00ec Maria Lomeli Christoforos Nalmpantis Ram Pasunuru Roberta Raileanu Baptiste Rozi\u00e8re Timo Schick Jane Dwivedi-Yu Asli Celikyilmaz et al. 2023. Augmented language models: A survey. arXiv:2302.07842. Retrieved from https:\/\/arxiv.org\/abs\/2302.07842"},{"key":"e_1_3_2_38_2","unstructured":"Shervin Minaee Tomas Mikolov Narjes Nikzad Meysam Chenaghlu Richard Socher Xavier Amatriain and Jianfeng Gao. 2024. Large language models: A survey. arXiv:2402.06196. Retrieved from https:\/\/arxiv.org\/abs\/2402.06196"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.4103\/aca.ACA_94_19"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-57327-9_16"},{"key":"e_1_3_2_41_2","unstructured":"Kate O\u2019Flaherty. 2020. Zoom beats Microsoft Teams Google Meet with game-changing new features. Retrieved from https:\/\/www.forbes.com\/sites\/kateoflahertyuk\/2020\/10\/14\/zoom-beats-microsoft-teams-google-meet-with-game-changing-new-features\/"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2013.6636712"},{"key":"e_1_3_2_43_2","first-page":"1","volume-title":"Proceedings of the 1st instructional Conference on Machine Learning (iCML \u201903)","author":"Ramos Juan","year":"2003","unstructured":"Juan Ramos. 2003. Using TF-IDF to determine word relevance in document queries. In Proceedings of the 1st instructional Conference on Machine Learning (iCML \u201903), 1\u20134."},{"key":"e_1_3_2_44_2","unstructured":"Christian Rigg and Nikshep Myle. 2021. Zoom video conferencing service review. Retrieved from https:\/\/www.techradar.com\/reviews\/zoom#section-zoom-features"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2024.100056"},{"key":"e_1_3_2_46_2","first-page":"1114","volume-title":"Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC \u201916)","author":"S\u00e4nger Mario","year":"2016","unstructured":"Mario S\u00e4nger, Ulf Leser, Steffen Kemmerer, Peter Adolphs, and Roman Klinger. 2016. SCARE \u2015 The sentiment corpus of app reviews with fine-grained annotations in German. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC \u201916). Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, and Stelios Piperidis (Eds.), European Language Resources Association (ELRA), Portoro\u017e, Slovenia, 1114\u20131121. Retrieved from https:\/\/aclanthology.org\/L16-1178"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2017.2759112"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/2993259.2993267"},{"key":"e_1_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Faiz Ali Shah Kairit Sirts and Dietmar Pfahl. 2018. The impact of annotation guidelines and annotated data on extracting app features from app reviews. arXiv:1810.05187. Retrieved from https:\/\/arxiv.org\/abs\/1810.05187","DOI":"10.31219\/osf.io\/wazhf"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-15538-4_2"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340496.3342756"},{"key":"e_1_3_2_52_2","unstructured":"Chris Stokel-Walker. 2020. How Skype lost its crown to Zoom. Retrieved from https:\/\/www.wired.com\/story\/skype-coronavirus-pandemic\/"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3209479"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSN48538.2019.00070"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510201"},{"key":"e_1_3_2_56_2","first-page":"749","volume-title":"Proceedings of the 30th IEEE\/ACM International Conference on Automated Software Engineering (ASE \u201915)","author":"5","year":"2015","unstructured":"[55] Phong Minh Vu, Tam The Nguyen, Hung Viet Pham, and Tung Thanh Nguyen. 2015. Mining user opinions in mobile app reviews: A keyword-based approach (T). In Proceedings of the 30th IEEE\/ACM International Conference on Automated Software Engineering (ASE \u201915), 749\u2013759."},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111435"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118095"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE57278.2023.00062"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI59109.2023.00135"},{"key":"e_1_3_2_61_2","unstructured":"Xiancai Xu Jia-Dong Zhang Rongchang Xiao and Lei Xiong. 2023. The limits of ChatGPT in extracting aspect-category-opinion-sentiment quadruples: A comparative analysis. arXiv:2310.06502. Retrieved from https:\/\/arxiv.org\/abs\/2310.06502"},{"key":"e_1_3_2_62_2","unstructured":"Pengyu Xue Linhao Wu Zhongxing Yu Zhi Jin Zhen Yang Xinyi Li Zhenyu Yang and Yue Tan. 2024. Automated commit message generation with large language models: An empirical study and beyond. arXiv:2404.14824. Retrieved from https:\/\/arxiv.org\/abs\/2404.14824"},{"key":"e_1_3_2_63_2","unstructured":"Wenxuan Zhang Yue Deng Bing Liu Sinno Jialin Pan and Lidong Bing. 2023. Sentiment analysis in the era of large language models: A reality check. arXiv:2305.15005. Retrieved from https:\/\/arxiv.org\/abs\/2305.15005"},{"key":"e_1_3_2_64_2","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv:2303.18223. Retrieved from https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"e_1_3_2_65_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Zhou Yongchao","year":"2023","unstructured":"Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. 2023. Large language models are human-level prompt engineers. In Proceedings of the 11th International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=92gvk82DE-"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3744644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:27:25Z","timestamp":1773246445000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3744644"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":64,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3744644"],"URL":"https:\/\/doi.org\/10.1145\/3744644","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,11]]},"assertion":[{"value":"2024-09-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}