[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120625-en":3,"doc-seo-120625-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120625,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Machine learning detection of manipulative environmental disclosures in corporate reports - research framework","Detecting manipulative environmental disclosures remains a critical challenge for regulators and investors. This study introduces a machine learning framework integrating financial indicators, textual sentiment, and public attention to identify manipulation risk among Chinese listed firms. A Random Forest model is trained on multi-source features from corporate reports and Baidu Index trends, achieving ROC-AUC 0.94, PR-AUC 0.78, balanced accuracy 0.86, and MCC 0.72 under severe class imbalance. SHAP interpretation highlights financial pressure, abnormal public attention, and sentiment deviation as key determinants. Results are context-specific to China’s Baidu-based indicators, requiring validation in other regulatory settings.","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nMachine learning detection of manipulative environmental disclosures in corporate reports  \nYuanzhe Li1,2,3􀀍, Junyuan Li1,3, Yutong Zheng3, Gangbing Zheng1 & Chenmeng Wu4  \nDetecting manipulative environmental disclosures remains a critical yet unresolved challenge for regulators and investors. This study proposes a machine learning framework that integrates financial indicators, textual sentiment, and public attention data to identify potential manipulation among Chinese listed firms. A Random Forest model is trained using multi-source features derived from corporate reports and Baidu Index trends. The optimized model demonstrates strong discriminatory ability under severe class imbalance (ROC-AUC = 0.94, PR-AUC= 0.78, Balanced Accuracy = 0.86, MCC = 0.72), indicating robust and reliable performance across both majority and minority classes. Evaluation through balanced metrics further confirms the model’s genuine predictive capacity rather than overfitting to training data. SHAP-based interpretation reveals that financial pressure, abnormal public attention, and sentiment deviation are the primary determinants of manipulation risk. Overall, the framework highlights how interpretable machine learning can strengthen data-driven environmental supervision. The findings are context-specific to the Chinese market due to reliance on Baidu-based indicators, warranting validation in other regulatory contexts in future research.  \nKeywords Machine learning, Environmental information disclosure, Manipulative behavior detection, Corporate transparency, Data imbalance techniques  \nAbbreviations  \nEIDM  \nROA  \nRF  \nDT  \nLR  \nAUC  \nTP  \nTN  \nFP  \nFN  \nROC SMOTE ADASYN GRI  \nISO  \nEPS  \nBig4  \nSDGs  \nCSR  \nEnvironmental information disclosure manipulation  \nReturn on assets Random forest Decision tree Logistic regression Area under the curve True positive  \nTrue negative False positive  \nFalse negative  \nReceiver operating characteristic Synthetic minority over-sampling technique Adaptive synthetic sampling  \nGlobal reporting initiative  \nInternational organization for standardization Earnings per share  \nRefers to the big four accounting firms Sustainable development goals Corporate social responsibility  \nEnvironmental degradation, with its profound and far-reaching effects on human health, biodiversity, and economic sustainability, has emerged as a pressing global issue. The World Health Organization reports that environmental risk factors contribute to approximately 23% of all deaths worldwide. In response,“environmental  \n1Carbon Neutrality Institute, China University of Mining and Technology, Xuzhou 221116, China. 2School of Civil and Environmental Engineering, University of Auckland, Auckland 1010, New Zealand. 3College of Design and Engineering, National University of Singapore, Singapore 119076, Singapore. 4Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, Cambridge CB2 1TN, UK. 􀀍 email: [yuanzhe001@e.ntu.edu.sg](yuanzhe001@e.ntu.edu.sg)  \n[www. nature.com/scientificreports/](www. nature.com/scientificreports/)  \nprotection” has evolved from a mere conceptual framework into a vigorous, action-driven movement. As early as 1980, Neilson highlighted the growing societal concern regarding environmental degradation, a sentiment that has only intensified over the decades. Despite the increasing awareness and engagement, a persistent challenge remains in the realm of corporate environmental reporting. Studies indicate a significant discrepancy in the quality of environmental disclosures, attributing this to a blend of insufficient expertise and patchwork regulatory landscapes. Disturbingly, this gap has led some corporations to engage in the falsification of their environmental data. The role of accurate and transparent environmental reporting is pivotal. It not only links a company’s ecological efforts with public perception ","cbCaieOUjLtcRPd6","https://ap.wps.com/l/cbCaieOUjLtcRPd6","pdf",2810981,1,24,"English","en",105,"# Introduction\n## Background on environmental reporting and manipulation risk\n# Methods\n## Pressure pool index and feature construction\n## Random Forest model with imbalance handling\n# Results\n## Classification performance under severe class imbalance\n## Model interpretation with SHAP","[{\"question\":\"What problem does the study address in corporate environmental reporting?\",\"answer\":\"The study targets the unresolved challenge of detecting manipulative environmental disclosures made by some corporations despite increasing reporting and regulation.\"},{\"question\":\"What data and features are used to detect manipulation risk?\",\"answer\":\"The framework combines financial indicators, textual sentiment from disclosures, and public attention measured using Baidu Index trends, producing multi-source features for the model.\"},{\"question\":\"Why is the model considered reliable despite class imbalance?\",\"answer\":\"Performance is evaluated using balanced metrics (ROC-AUC, PR-AUC, balanced accuracy, and MCC) to confirm predictive capacity rather than relying on overfitting-prone training accuracy.\"}]","Machine learning detection of manipulative environmental disclosures in corporate reports - research framework | PDF",1785730963,60,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-detection-of-manipulative-environmental-disclosures-in-corporate-reports-research-framework","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-detection-of-manipulative-environmental-disclosures-in-corporate-reports-research-framework/120625/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in corporate environmental reporting?","Question",{"text":75,"@type":76},"The study targets the unresolved challenge of detecting manipulative environmental disclosures made by some corporations despite increasing reporting and regulation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data and features are used to detect manipulation risk?",{"text":80,"@type":76},"The framework combines financial indicators, textual sentiment from disclosures, and public attention measured using Baidu Index trends, producing multi-source features for the model.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is the model considered reliable despite class imbalance?",{"text":84,"@type":76},"Performance is evaluated using balanced metrics (ROC-AUC, PR-AUC, balanced accuracy, and MCC) to confirm predictive capacity rather than relying on overfitting-prone training accuracy.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]