{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T10:59:45Z","timestamp":1768215585477,"version":"3.49.0"},"reference-count":77,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Digital lending, also known as alternative lending, refers to fintech platforms that offer quick and easy loans through digital channels, bypassing many of the limitations of traditional banking. Since the mid-2000s, digital lending has become a major fintech innovation, with rapid growth in India driven by financial inclusion measures. However, the sector continues to face challenges, including fraud, transparency issues, and consumer dissatisfaction. The primary objective of this study was to understand how consumers perceive and assess India\u2019s RBI-approved P2P digital lending apps by analyzing a large dataset of customer feedback to identify strengths, weaknesses, and overall satisfaction levels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The study analyzed a final dataset of 15,408 user reviews collected from seven RBI-approved digital lending platforms: 5Paisa, Faircent, i2iFunding, LenDenClub, CashKumar, Lendbox, and IndiaMoneyMart derived from an initial 15,537 reviews. The cleaned data was then examined using natural language processing, topic modeling, and supervised machine learning and deep learning models to identify key themes and evaluate predictive performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Topic modeling identified 11 recurring topics. Sentiment analysis revealed that 55% of evaluations were positive, 41% were negative, and 4% were neutral. Strengths included loan disbursement, withdrawals, and EMI payments, while weaknesses involved interface design, transparency around rejections, and login functionality. Comparative data revealed that IndiaMoneyMart and i2iFunding received the highest user satisfaction, while 5Paisa and Lendbox trailed due to recurring complaints about transparency, accessibility, and overall user experience. In terms of modeling, the deep learning model VGG16 and ensemble machine learning techniques (XGBoost, CatBoost, and LightGBM) consistently achieved the highest predictive accuracy (up to 0.88), outperforming simpler models such as decision trees and ResNets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The findings indicate that digital lending platforms support financial inclusion but require improvements in user interface and user experience, better transparency in loan decisions, and stronger customer support. Addressing these areas can help strengthen trust and promote long term adoption of digital lending services.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1708080","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T07:51:42Z","timestamp":1768204302000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["User perceptions of RBI-approved P2P digital lending apps: an NLP, machine learning, and deep learning approach"],"prefix":"10.3389","volume":"8","author":[{"given":"Kunchakara Raja","family":"Sekhar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaiku Shahida","family":"Saheb","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.3390\/joitmc8030120","volume-title":"Continued intention to use of M-banking in Jordan by integrating UTAUT, TPB, TAM and service quality with ML","author":"Abu-taieh","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"760","DOI":"10.51594\/estj.v5i3.871","article-title":"Data-driven sustainability: how fintech innovations are supporting green finance","volume":"5","author":"Addy","year":"2024","journal-title":"Eng. Sci. Technol. J."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/j.procs.2019.05.008","article-title":"The impact of features extraction on the sentiment analysis","volume":"152","author":"Ahuja","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s10588-018-9266-8","article-title":"The impact of preprocessing steps on the accuracy of machine learning algorithms in sentiment analysis","volume":"25","author":"Alam","year":"2019","journal-title":"Comput. Math. Organ. Theory"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.3390\/electronics14112125","article-title":"Sentiment analysis of digital banking reviews using machine learning and large language models","volume":"14","author":"Alawaji","year":"2025","journal-title":"Electronics"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"90","DOI":"10.3390\/ijfs11030090","article-title":"Building Trust in Fintech: an analysis of ethical and privacy considerations in the intersection of big data, AI, and customer trust","volume":"11","author":"Aldboush","year":"2023","journal-title":"Int. J. Financ. Stud."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"102132","DOI":"10.1016\/j.ijinfomgt.2020.102132","article-title":"A comparative assessment of sentiment analysis and star ratings for consumer reviews","volume":"54","author":"Al-Natour","year":"2020","journal-title":"Int. J. Inf. Manag."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"240","DOI":"10.22452\/mjcs.vol33no3.5","article-title":"Senti2vec: an effective feature extraction technique for sentiment analysis based on word2vec","volume":"33","author":"Alshari","year":"2020","journal-title":"Malays. J. Comput. Sci."},{"key":"ref9","first-page":"1","article-title":"Analysis of Google play store\u2019s sentiment review on Indonesia\u2019s P2P Fintech platform","author":"Amrie","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/jrfm15070287","article-title":"Fintech innovations in the financial service industry","volume":"15","author":"Anifa","year":"2022","journal-title":"J. Risk Financ. Manag."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1007\/s10796-023-10423-4","article-title":"Throwing good money after bad: risk mitigation strategies in the P2P lending platforms","volume":"26","author":"Bao","year":"2024","journal-title":"Inf. Syst. Front."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e1948","DOI":"10.1002\/pa.1948","article-title":"Analyzing the progress and prospects of financial inclusion in India","volume":"19","author":"Barik","year":"2019","journal-title":"J. Public Aff."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1108\/09564230610656962","article-title":"Beyond technology acceptance: understanding consumer practice","volume":"17","author":"Baron","year":"2006","journal-title":"Int. J. Serv. Ind. Manag."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5089\/9781498314428.001","article-title":"FinTech in financial inclusion: machine learning applications in assessing credit risk","volume":"2019","author":"Bazarbash","year":"2019","journal-title":"IMF Work. Pap."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/s12232-024-00449-8","article-title":"The dark side of the moon? Fintech and financial stability","volume":"71","author":"Cevik","year":"2024","journal-title":"Int. Rev. Econ."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s10799-014-0187-z","article-title":"A trust model for online peer-to-peer lending: a lender\u2019s perspective","volume":"15","author":"Chen","year":"2014","journal-title":"Inf. Technol. Manag."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.inoche.2016.03.015","article-title":"Unusual formations of superoxo heptaoxomolybdates from peroxo molybdates","volume":"67","author":"Chen","year":"2016","journal-title":"Inorg. Chem. Commun."},{"key":"ref9002","doi-asserted-by":"crossref","first-page":"319","DOI":"10.2307\/249008","article-title":"Perceived usefulness, perceived ease of use, and user acceptance of information technology","author":"Davis","year":"1989","journal-title":"MIS quarterly."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"2710","DOI":"10.30574\/wjarr.2024.23.1.2272","article-title":"The evolution of green fintech: leveraging AI and IoT for sustainable financial services and smart contract implementation","volume":"23","author":"Elias","year":"2024","journal-title":"World J. Adv. Res. Rev."},{"key":"ref20","volume-title":"Book reviews","author":"Feldman","year":"2007"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1080\/13563467.2017.1259298","article-title":"The digital revolution in financial inclusion: international development in the fintech era","volume":"22","author":"Gabor","year":"2017","journal-title":"New Polit. Econ."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1080\/2157930X.2020.1850012","article-title":"Determinants of digital finance in India","volume":"12","author":"Ghosh","year":"2022","journal-title":"Innov. Dev."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"e239","DOI":"10.2196\/jmir.2721","article-title":"Use of sentiment analysis for capturing patient experience from free-text comments posted online","volume":"15","author":"Greaves","year":"2013","journal-title":"J. Med. Internet Res."},{"key":"ref24","first-page":"97","article-title":"User sentiment analysis of Cashkumar peer-to-peer (P2P) lending platform: based on Google reviews","author":"Gupta","year":"2023"},{"key":"ref25","first-page":"50","article-title":"Probabilistic latent semantic indexing","author":"Hofmann","year":"1999"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/S0167-9236(03)00086-1","article-title":"Credit rating analysis with support vector machines and neural networks: A market comparative study","volume":"37","author":"Huang","year":"2004","journal-title":"Decis. Support. Syst."},{"key":"ref27","first-page":"25","article-title":"Measuring service quality: SERVQUAL vs. SERVPERF scales","author":"Jain","year":"2004"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"507","DOI":"10.3390\/jtaer19010027","article-title":"Public perception of online P2P lending applications","volume":"19","author":"Khan","year":"2024","journal-title":"J. Theor. Appl. Electron. Commer. Res."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.13140\/RG.2.2.35247.25765","article-title":"An overview of the peer to peer lending industry of India","author":"Khatri","year":"2019","journal-title":"Int. J. Bus. Manag. Invent. ISSN"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/e24060801","article-title":"P2P lending default prediction based on AI and statistical models","volume":"24","author":"Ko","year":"2022","journal-title":"Entropy"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"100598","DOI":"10.1016\/j.rico.2025.100598","article-title":"Customer satisfaction in peer-to-peer lending platforms: a text mining and sentiment analysis approach","volume":"20","author":"Kumari","year":"2025","journal-title":"Results Control Optim."},{"key":"ref32","first-page":"143","article-title":"Neurocomputing improving convolutional neural network for text classification by recursive data pruning.","volume-title":"Neurocomputing,","author":"Li","year":"2020"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/9781108639286","volume-title":"Sentiment analysis: mining opinions, sentiments, and emotions","author":"Liu","year":"2020"},{"key":"ref35","first-page":"1","article-title":"Research on personal loan default assessment based on machine learning","author":"Liu","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1852","DOI":"10.1002\/asi","article-title":"Full-text citation analysis: a new method to enhance","volume":"64","author":"Liu","year":"2013","journal-title":"J. Am. Soc. Inf. Sci. Technol."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/laws13060070","article-title":"Understanding the nature of the transnational scam-related fraud: challenges and solutions from Vietnam\u2019s perspective","volume":"13","author":"Luong","year":"2024","journal-title":"Laws"},{"key":"ref37","first-page":"52","article-title":"Different model for hand gesture recognition with a novel line feature extraction","author":"Mahmood","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.32388\/dkjluj.2","article-title":"An empirical analysis of loan repayment behavior and default rates on digital lending platforms: evidence from an emerging market","volume":"7","author":"Mallinguh","year":"2025","journal-title":"Qeios"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"3793","DOI":"10.58968\/bs.v2i2.379","article-title":"Sentiment analysis of peer-to-peer (P2P) lending: a study of scientific publications","volume":"2","author":"Maulida","year":"2024","journal-title":"Bus. Suatain."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.54105\/ijef.a2542.053123","article-title":"Digital lending laws in India and beyond: scrutinizing the regulatory blind spot","volume":"3","author":"Modi","year":"2023","journal-title":"Indian J. Econ. Finance"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1016\/j.eswa.2012.07.059","article-title":"Document-level sentiment classification: an empirical comparison between SVM and ANN","volume":"40","author":"Moraes","year":"2013","journal-title":"Expert Syst. Appl."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"3293","DOI":"10.3390\/SU12083293","article-title":"Lender trust on the P2P lending: analysis based on sentiment analysis of comment text","volume":"12","author":"Niu","year":"2020","journal-title":"Sustainability"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1080\/08839514.2021.1922843","article-title":"Classification of customer reviews using machine learning algorithms","volume":"35","author":"Noori","year":"2021","journal-title":"Appl. Artif. Intell."},{"key":"ref44","first-page":"12","volume-title":"DigitalCommons @ Kennesaw state university Fintech use, digital divide and financial inclusion Fintech use, digital divide and financial inclusion","author":"Odei-appiah","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"673","DOI":"10.30574\/ijsra.2024.13.2.2183","article-title":"The intersection of digital safety and financial literacy: mitigating financial risks in the digital economy","volume":"13","author":"Ogunola","year":"2024","journal-title":"Int. J. Sci. Res. Arch."},{"key":"ref46","first-page":"90","article-title":"Integrating fintech and innovation in microfinance: transforming credit accessibility for small businesses","volume":"3","author":"Omowole","year":"2024","journal-title":"Int. J. Front. Res. Rev."},{"key":"ref47","first-page":"1345","article-title":"Sentiment analysis of twitter data for predicting stock market movements","author":"Pagolu","year":"2016"},{"key":"ref48","first-page":"37","volume-title":"Topic identification and classification of GooglePlay store reviews","author":"Pamplona","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/9776138","article-title":"System dynamics models of online lending platform based on Vensim simulation technology and analysis of interest rate evolution trend","volume":"2022","author":"Pang","year":"2022","journal-title":"Comput. Intell. Neurosci."},{"key":"ref50","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s40854-023-00496-0","article-title":"Exploring the determinants of the user experience in P2P payment systems in Spain: a text mining approach","volume":"10","author":"Perea-Khalifi","year":"2024","journal-title":"Financ. Innov."},{"key":"ref51","first-page":"17","article-title":"Borrower sentiment on P2P lending in Indonesia based on Google playstore reviews","author":"Pohan","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.dss.2009.12.009","article-title":"Borrower decision aid for people-to-people lending","volume":"49","author":"Puro","year":"2010","journal-title":"Decis. Support. Syst."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"3078","DOI":"10.3390\/jtaer16070168","article-title":"Blockchain technology adoption in supply chain finance","volume":"16","author":"Rijanto","year":"2021","journal-title":"J. Theor. Appl. Electron. Commer. Res."},{"key":"ref54","article-title":"Decoding the diversity: a review of the Indic AI research landscape","author":"Sankalp","year":"2024"},{"key":"ref55","first-page":"159","article-title":"Digital lending high level system architecture in Indonesia","author":"Sarungu","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1080\/13600869955134","article-title":"Counteracting identity fraud in the information age: the identity theft and assumption deterrence act","volume":"13","author":"Saunders","year":"1999","journal-title":"Int. Rev. Law Comput. Technol."},{"key":"ref57","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1111\/sdi.12160","article-title":"Briefly noted","volume":"27","author":"Sherman","year":"2014","journal-title":"Semin. Dial."},{"key":"ref58","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.dss.2018.01.002","article-title":"Disentangling consumer recommendations: explaining and predicting airline recommendations based on online reviews","volume":"107","author":"Siering","year":"2018","journal-title":"Decis. Support. Syst."},{"key":"ref60","doi-asserted-by":"publisher","first-page":"2565","DOI":"10.1007\/s10115-022-01734-0","article-title":"Learning to hash: a comprehensive survey of deep learning-based hashing methods","volume":"64","author":"Singh","year":"2022","journal-title":"Knowl. Inf. Syst."},{"key":"ref59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3127\/ajis.v24i0.2695","article-title":"An integrated model combining the ECM and the UTAUT to explain users\u2019 post-adoption behaviour towards mobile payment systems","volume":"24","author":"Singh","year":"2020","journal-title":"Australas. J. Inf. Syst."},{"key":"ref61","volume-title":"Mobile money: d\u00e9cryptage d Une succes story africaine perceived usefulness, perceived ease of use, and user acceptance of information technology","author":"Sylvie","year":"2021"},{"key":"ref62","first-page":"2544","article-title":"Sentiment strength detection in short informal text 1","author":"Thelwall","year":"2010"},{"key":"ref63","first-page":"81","article-title":"An application of naive Bayes classification for credit scoring in e-lending platform","author":"Vedala","year":"2012"},{"key":"ref64","doi-asserted-by":"publisher","first-page":"425","DOI":"10.2307\/30036540","article-title":"User acceptance of information technology: toward A unified View1","volume":"27","author":"Venkatesh","year":"2019","journal-title":"Quarterly"},{"key":"ref9001","volume-title":"Predicting Yelp Star Ratings Based on Text Analysis of User Reviews","author":"Wang","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","first-page":"41","DOI":"10.32604\/jbd.2022.027717","article-title":"Chinese news text classification based on convolutional neural network","volume":"4","author":"Wang","year":"2022","journal-title":"J. Big Data"},{"key":"ref68","doi-asserted-by":"publisher","first-page":"3591","DOI":"10.1080\/0144929X.2021.2005679","article-title":"Posts and reviews in P2P online lending platforms: a sentiment analysis and cross-culture comparison","volume":"41","author":"Wang","year":"2022","journal-title":"Behav. Inf. Technol."},{"key":"ref67","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1108\/INTR-05-2019-0183","article-title":"Why do borrowers default on online loans? An inquiry of their psychology mechanism","volume":"30","author":"Wang","year":"2020","journal-title":"Internet Res."},{"key":"ref65","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1080\/07421222.2019.1705513","article-title":"Mining semantic soft factors for credit risk evaluation in peer-to-peer lending","volume":"37","author":"Wang","year":"2020","journal-title":"J. Manag. Inf. Syst."},{"key":"ref69","doi-asserted-by":"publisher","first-page":"302","DOI":"10.3390\/jrfm14070302","article-title":"Machine learning in finance: A metadata-based systematic review of the literature","volume":"14","author":"Warin","year":"2021","journal-title":"J. Risk Financ. Manag."},{"key":"ref71","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-0-387-34555-0","volume-title":"Text mining: predictive methods for analyzing unstructured information","author":"Weiss","year":"2005"},{"key":"ref70","first-page":"178","article-title":"LDA-based document models for ad-hoc retrieval","author":"Wei","year":"2006"},{"key":"ref72","doi-asserted-by":"publisher","first-page":"18759","DOI":"10.1038\/s41598-021-98361-6","article-title":"Loan default prediction of Chinese P2P market: a machine learning methodology","volume":"11","author":"Xu","year":"2021","journal-title":"Sci. Rep."},{"key":"ref73","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1177\/22786821231211411","article-title":"Factors influencing behavioral intentions to use digital lending: an extension of TAM model","volume":"13","author":"Yadav","year":"2024","journal-title":"Jindal J. Bus. Res."},{"key":"ref74","first-page":"154","article-title":"Text classification model based on fastText","author":"Yao","year":"2020"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3018534","article-title":"Regulating a revolution: from regulatory sandboxes to smart regulation","volume":"23","author":"Zetzsche","year":"2017","journal-title":"SSRN Electron. J."},{"key":"ref76","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3185658","article-title":"A novel feature extraction approach for mechanical fault diagnosis based on ESAX and BoW model","volume":"71","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1708080\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T07:51:46Z","timestamp":1768204306000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1708080\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":77,"alternative-id":["10.3389\/frai.2025.1708080"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1708080","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"article-number":"1708080"}}