{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T13:31:36Z","timestamp":1775223096268,"version":"3.50.1"},"reference-count":37,"publisher":"Emerald","issue":"2","license":[{"start":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T00:00:00Z","timestamp":1584057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["DTA"],"published-print":{"date-parts":[[2020,3,13]]},"abstract":"Purpose<\/jats:title>The purpose of this study is to investigate the effectiveness of qualitative information extracted from firm\u2019s annual report in predicting corporate credit rating. Qualitative information represented by published reports or management interview has been known as an important source in addition to quantitative information represented by financial values in assigning corporate credit rating in practice. Nevertheless, prior studies have room for further research in that they rarely employed qualitative information in developing prediction model of corporate credit rating.<\/jats:p><\/jats:sec>Design\/methodology\/approach<\/jats:title>This study adopted three document vectorization methods, Bag-Of-Words (BOW), Word to Vector (Word2Vec) and Document to Vector (Doc2Vec), to transform an unstructured textual data into a numeric vector, so that Machine Learning (ML) algorithms accept it as an input. For the experiments, we used the corpus of Management\u2019s Discussion and Analysis (MD&A) section in 10-K financial reports as well as financial variables and corporate credit rating data.<\/jats:p><\/jats:sec>Findings<\/jats:title>Experimental results from a series of multi-class classification experiments show the predictive models trained by both financial variables and vectors extracted from MD&A data outperform the benchmark models trained only by traditional financial variables.<\/jats:p><\/jats:sec>Originality\/value<\/jats:title>This study proposed a new approach for corporate credit rating prediction by using qualitative information extracted from MD&A documents as an input to ML-based prediction models. Also, this research adopted and compared three textual vectorization methods in the domain of corporate credit rating prediction and showed that BOW mostly outperformed Word2Vec and Doc2Vec.<\/jats:p><\/jats:sec>","DOI":"10.1108\/dta-08-2019-0127","type":"journal-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T07:27:20Z","timestamp":1584084440000},"page":"151-168","source":"Crossref","is-referenced-by-count":12,"title":["Predicting corporate credit rating based on qualitative information of MD&A transformed using document vectorization techniques"],"prefix":"10.1108","volume":"54","author":[{"given":"Jinwook","family":"Choi","sequence":"first","affiliation":[]},{"given":"Yongmoo","family":"Suh","sequence":"additional","affiliation":[]},{"given":"Namchul","family":"Jung","sequence":"additional","affiliation":[]}],"member":"140","reference":[{"issue":"1","key":"key2020060208374715600_ref001","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1111\/j.1911-3846.1999.tb00575.x","article-title":"MD&A quality as measured by the SEC and analysts' earnings forecasts","volume":"16","year":"1999","journal-title":"Contemporary Accounting Research"},{"issue":"2","key":"key2020060208374715600_ref002","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1007\/s11142-017-9388-0","article-title":"The impact of narrative disclosure readability on bond ratings and the cost of debt","volume":"22","year":"2017","journal-title":"Review of Accounting Studies"},{"issue":"1","key":"key2020060208374715600_ref003","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1177\/0148558X16689653","article-title":"Soft information in loan agreements","volume":"33","year":"2018","journal-title":"Journal of Accounting, Auditing and Finance"},{"key":"key2020060208374715600_ref004","doi-asserted-by":"crossref","unstructured":"Bozanic, Z. and Kraft, P. (2014), \u201cQualitative disclosure and credit analysts' soft rating adjustments\u201d, working paper, Fisher College of Business, Ohio State University, Ohio, 1 October.","DOI":"10.1080\/09638180.2022.2038227"},{"issue":"2","key":"key2020060208374715600_ref005","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1111\/j.1475-679X.2010.00396.x","article-title":"Large\u2010sample evidence on firms\u2019 year\u2010over\u2010year MD&A modifications","volume":"49","year":"2011","journal-title":"Journal of Accounting Research"},{"issue":"3","key":"key2020060208374715600_ref006","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.eswa.2005.10.003","article-title":"A study of Taiwan's issuer credit rating systems using support vector machines","volume":"30","year":"2006","journal-title":"Expert Systems with Applications"},{"issue":"February","key":"key2020060208374715600_ref007","first-page":"224","article-title":"Hybrid models based on rough set classifiers for setting credit rating decision rules in the global banking industry","volume":"39","year":"2013","journal-title":"Knowledge-Based Systems"},{"issue":"7","key":"key2020060208374715600_ref008","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1162\/089976698300017197","article-title":"Approximate statistical tests for comparing supervised classification learning algorithms","volume":"10","year":"1998","journal-title":"Neural Computation"},{"key":"key2020060208374715600_ref009","first-page":"188","article-title":"Financial statement fraud detection using text mining: a systemic functional linguistics theory perspective","year":"2016"},{"issue":"30","key":"key2020060208374715600_ref010","first-page":"1","article-title":"An approach to the use of word embeddings in an opinion classification task","volume":"66","year":"2016","journal-title":"Expert Systems with Applications"},{"issue":"4","key":"key2020060208374715600_ref011","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1007\/s11142-009-9111-x","article-title":"Management's tone change, post earnings announcement drift and accruals","volume":"15","year":"2010","journal-title":"Review of Accounting Studies"},{"issue":"3","key":"key2020060208374715600_ref012","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1177\/0148558X0702200306","article-title":"Credit rating agencies in capital markets: a review of research evidence on selected criticisms of the agencies","volume":"22","year":"2007","journal-title":"Journal of Accounting, Auditing and Finance"},{"issue":"3","key":"key2020060208374715600_ref013","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1002\/isaf.1392","article-title":"Do sentiments matter in fraud detection? estimating semantic orientation of annual reports","volume":"23","year":"2016","journal-title":"Intelligent Systems in Accounting, Finance and Management"},{"issue":"July","key":"key2020060208374715600_ref014","first-page":"139","article-title":"Mining corporate annual reports for intelligent detection of financial statement fraud\u2013A comparative study of machine learning methods","volume":"128","year":"2017","journal-title":"Knowledge-Based Systems"},{"issue":"October","key":"key2020060208374715600_ref015","first-page":"72","article-title":"Feature selection in corporate credit rating prediction","volume":"51","year":"2013","journal-title":"Knowledge-Based Systems"},{"key":"key2020060208374715600_ref016","doi-asserted-by":"crossref","first-page":"44","DOI":"10.2307\/2490168","article-title":"The determination of long-term credit standing with financial ratios","volume":"4","year":"1966","journal-title":"Journal of Accounting Research"},{"issue":"4","key":"key2020060208374715600_ref017","doi-asserted-by":"crossref","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","year":"2004","journal-title":"Decision Support Systems"},{"issue":"3","key":"key2020060208374715600_ref018","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/j.dss.2010.08.009","article-title":"Identification of fraudulent financial statements using linguistic credibility analysis","volume":"50","year":"2011","journal-title":"Decision Support Systems"},{"issue":"2","key":"key2020060208374715600_ref019","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1086\/296045","article-title":"Statistical models of bond ratings: a methodological inquiry","volume":"52","year":"1979","journal-title":"Journal of Business"},{"issue":"March","key":"key2020060208374715600_ref020","first-page":"15","article-title":"Multi-co-training for document classification using various document representations: TF\u2013IDF, LDA, and Doc2Vec","volume":"477","year":"2019","journal-title":"Information Sciences"},{"issue":"8","key":"key2020060208374715600_ref021","doi-asserted-by":"crossref","first-page":"1800","DOI":"10.1016\/j.cor.2011.06.023","article-title":"A corporate credit rating model using multi-class support vector machines with an ordinal pairwise partitioning approach","volume":"39","year":"2012","journal-title":"Computers & Operations Research"},{"key":"key2020060208374715600_ref022","first-page":"78","article-title":"An empirical evaluation of doc2vec with practical insights into document embedding generation","year":"2016"},{"key":"key2020060208374715600_ref023","first-page":"1188","article-title":"Distributed representations of sentences and documents","year":"2014"},{"issue":"1","key":"key2020060208374715600_ref024","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.eswa.2006.04.018","article-title":"Application of support vector machines to corporate credit rating prediction","volume":"33","year":"2007","journal-title":"Expert Systems with Applications"},{"key":"key2020060208374715600_ref025","doi-asserted-by":"publisher","article-title":"Is it worth the while? The relevance of qualitative information in credit rating","year":"2003","DOI":"10.2139\/ssrn.410186"},{"issue":"5","key":"key2020060208374715600_ref026","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1111\/j.1475-679X.2010.00382.x","article-title":"The information content of forward\u2010looking statements in corporate filings\u2014a na\u00efve Bayesian machine learning approach","volume":"48","year":"2010","journal-title":"Journal of Accounting Research"},{"key":"key2020060208374715600_ref027","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/j.engappai.2016.12.002","article-title":"A deep learning approach for credit scoring using credit default swaps","volume":"65","year":"2017","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"4","key":"key2020060208374715600_ref028","doi-asserted-by":"crossref","first-page":"1621","DOI":"10.2308\/accr-50983","article-title":"MD&A disclosure and the firm's ability to continue as a going concern","volume":"90","year":"2015","journal-title":"The Accounting Review"},{"key":"key2020060208374715600_ref029","article-title":"Efficient estimation of word representations in vector space","year":"2013"},{"key":"key2020060208374715600_ref030","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","year":"2013","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"key2020060208374715600_ref031","first-page":"746","article-title":"Linguistic regularities in continuous space word representations","year":"2013"},{"issue":"5","key":"key2020060208374715600_ref032","first-page":"931","article-title":"Forward-looking MD&A disclosures and the information environment","volume":"61","year":"2014","journal-title":"Management Science"},{"key":"key2020060208374715600_ref033","unstructured":"Standard & Poor's. (2018), \u201cGuide to credit rating essentials\u201d, available at: https:\/\/www.spratings.com\/documents\/20184\/774196\/Guide_to_Credit_Rating_Essentials_Digital.pdf\/ (accessed 29 July 2019)."},{"issue":"3","key":"key2020060208374715600_ref034","first-page":"7","article-title":"Discovering finance keywords via continuous-space language models","volume":"7","year":"2016","journal-title":"ACM Transactions on Management Information Systems (TMIS)"},{"issue":"1","key":"key2020060208374715600_ref035","doi-asserted-by":"crossref","first-page":"118","DOI":"10.2307\/2674717","article-title":"An alternative approach to predicting corporate bond ratings","volume":"8","year":"1970","journal-title":"Journal of Accounting Research"},{"key":"key2020060208374715600_ref036","first-page":"1926","article-title":"Traditional Chinese medicine clinical records classification using knowledge-powered document embedding","year":"2016"},{"issue":"September","key":"key2020060208374715600_ref037","first-page":"166","article-title":"A hybrid KMV model, random forests and rough set theory approach for credit rating","volume":"33","year":"2012","journal-title":"Knowledge-Based Systems"}],"container-title":["Data Technologies and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/DTA-08-2019-0127\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/DTA-08-2019-0127\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T23:15:16Z","timestamp":1753398916000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/dta\/article\/54\/2\/151-168\/509955"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,13]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,3,13]]}},"alternative-id":["10.1108\/DTA-08-2019-0127"],"URL":"https:\/\/doi.org\/10.1108\/dta-08-2019-0127","relation":{},"ISSN":["2514-9288"],"issn-type":[{"value":"2514-9288","type":"print"}],"subject":[],"published":{"date-parts":[[2020,3,13]]}}}