Data Science and Management最新文献_第2页

A context-aware BERT framework for detecting and modeling the mental health impact of online toxic language 一个上下文感知的BERT框架，用于检测和建模在线有毒语言对心理健康的影响

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2026-01-03 DOI: 10.1016/j.dsm.2025.12.002

Ayodeji Olusegun Ibitoye, Oladosu Oyebisi Oladimeji, Isaac Olayemi Olaleye, Ozichi Nweke Emuoyibofarhe

{"title":"A context-aware BERT framework for detecting and modeling the mental health impact of online toxic language","authors":"Ayodeji Olusegun Ibitoye, Oladosu Oyebisi Oladimeji, Isaac Olayemi Olaleye, Ozichi Nweke Emuoyibofarhe","doi":"10.1016/j.dsm.2025.12.002","DOIUrl":"10.1016/j.dsm.2025.12.002","url":null,"abstract":"<div><div>Toxic language in online communities poses significant risks to mental health, often exacerbating conditions, such as anxiety, depression, and stress. While existing methods for detecting toxic language in online spaces have made progress, they struggle to understand the underlying context, emotional tone, and specific mental health topics tied to such languages. This study proposes a novel framework that leverages the power of fine-tuned bidirectional encoder representations from transformers (BERT) to detect and analyze toxic language in a contextualized manner, focusing on their impact on mental health. This study quantifies the relationship between toxic comments and mental health issues by fine-tuning BERT for both toxicity classification and sentiment analysis. The toxic language impact score (TLIS) is introduced, which combines toxicity, emotional sentiment, and the relevance of comments to mental health topics. In addition, a cumulative exposure model (CEM) is developed to track the long-term effects of repeated exposure to toxic language. The methodology analyzed a dataset of 8,200 social media comments labeled for mental health and toxicity, yielding high precision (0.87), recall (0.82), and F1-score (0.84) in detecting toxic content. The results underscore the profound impact of toxic language on well-being, offering new insights for creating targeted interventions to mitigate its effects on online communities.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 2","pages":"Article 100175"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148527437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Suspiciousness of social media accounts: Examining the role of conversational consistency using machine learning approach 社交媒体账户的怀疑：使用机器学习方法检查会话一致性的作用

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2025-09-27 DOI: 10.1016/j.dsm.2025.09.003

Kunal Rao, Gaurav Dixit

{"title":"Suspiciousness of social media accounts: Examining the role of conversational consistency using machine learning approach","authors":"Kunal Rao, Gaurav Dixit","doi":"10.1016/j.dsm.2025.09.003","DOIUrl":"10.1016/j.dsm.2025.09.003","url":null,"abstract":"<div><div>The proliferation of social media platforms has led to an upsurge in suspicious accounts that spread misinformation and manipulate public opinion. A few of these accounts with significant followings might play a prominent role in shaping people’s inclination towards social issues. Our study supports the social identity and information gap theories to conceptualize and examine the role of a novel measure, the ‘conversational consistency’ of social media accounts, in signaling the suspiciousness of social media accounts using the case of a social movement. First, we develop a novel algorithmic approach to quantify and compute topic conversational consistency on a Twitter dataset constructed using social media accounts active during Indian farmers’ protests in 2020–2021. We employ machine learning techniques, such as latent Dirichlet allocation and Jaro similarity, to compute social media accounts’ conversational consistency and suspiciousness. We leveraged semi-supervised learning to label accounts’ conversational consistency and validate the performance of our combined topic modeling and similarity approach with baseline combinations. We then performed econometric modeling to test our hypotheses. We employ two-stage least squares for the robustness tests. A key finding of our study is that social media accounts with low conversational consistency signal higher levels of suspiciousness. Other findings highlight that social media accounts’ lifetime post-sentiments, bio-length, and account creation newness are negatively associated with their suspiciousness. Our study introduces new avenues for future research on misinformation and offers novel theoretical insights and managerial implications.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 2","pages":"Article 100167"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148527433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating lean management and emerging technologies for enhanced sustainable performance: Empirical evidence based on double machine learning approach 整合精益管理和新兴技术以提高可持续绩效：基于双机器学习方法的经验证据

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2025-09-05 DOI: 10.1016/j.dsm.2025.08.004

Anna Presciuttini, Stefano Frecassetti, Matteo Ferrazzi, Alessandra Cantini, Alberto Portioli-Staudacher

{"title":"Integrating lean management and emerging technologies for enhanced sustainable performance: Empirical evidence based on double machine learning approach","authors":"Anna Presciuttini, Stefano Frecassetti, Matteo Ferrazzi, Alessandra Cantini, Alberto Portioli-Staudacher","doi":"10.1016/j.dsm.2025.08.004","DOIUrl":"10.1016/j.dsm.2025.08.004","url":null,"abstract":"<div><div>The rapid increase in sustainability has pushed manufacturing firms to rethink their production systems to make them more efficient, produce less waste, and improve their working conditions. In this landscape, many manufacturing firms that rely on traditional quality improvement methods such as lean management seek ways to improve their performance, align with market needs, and achieve zero defect production. In this sense, digital technologies seem to have promising features that can enhance manufacturing firms’ sustainable positions. However, recent studies on zero defect manufacturing have often overlooked the possible integration of existing quality improvement practices and technologies, with a major focus on the latter. Employing a survey analyzed through a double machine learning algorithm, we provide guidelines to manufacturing firms that extensively use lean management practices, showing the best technologies to significantly impact sustainable metrics. The results of this study provide guidelines for firms by demonstrating the best technologies that can be integrated with different lean management practices to advance toward zero defect production and achieve superior sustainable performance.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 2","pages":"Article 100164"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148527431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring artificial intelligence for sustainable business development: a review 探索人工智能促进可持续商业发展：综述

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2025-10-23 DOI: 10.1016/j.dsm.2025.10.001

Jintao Yu, Ximing Zhan, Giridhar Reddy Bojja

引用次数: 0

Deep learning in financial fraud detection: Innovations, challenges, and applications 金融欺诈检测中的深度学习：创新、挑战和应用

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2025-08-20 DOI: 10.1016/j.dsm.2025.08.002

Yisong Chen, Chuqing Zhao, Yixin Xu, Chuanhao Nie, Yixin Zhang

引用次数: 0

In GPT we trust: perceptions of the future of work with artificial intelligence on online forums 在GPT中，我们相信：在线论坛上对人工智能未来工作的看法

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2025-11-20 DOI: 10.1016/j.dsm.2025.11.001

Szabina Fodor, Bettina Boncz

引用次数: 0

Trust or distrust? AIGC trustworthiness and an extended analysis within nomology framework 信任还是不信任？AIGC可信度及其在法理学框架内的扩展分析

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2025-10-15 DOI: 10.1016/j.dsm.2025.09.005

Mingqian Li , Rong Du , Shizhong Ai , Richard A. Hunt , Jianing Xie

{"title":"Trust or distrust? AIGC trustworthiness and an extended analysis within nomology framework","authors":"Mingqian Li , Rong Du , Shizhong Ai , Richard A. Hunt , Jianing Xie","doi":"10.1016/j.dsm.2025.09.005","DOIUrl":"10.1016/j.dsm.2025.09.005","url":null,"abstract":"<div><div>Given the dizzying advancements in artificial intelligence (AI) applications such as ChatGPT and DeepSeek, AI-generated content (AIGC) has attracted considerable attention from scholars, practitioners, and policymakers, each of whom is grappling with fundamental issues involving individual, organizational, and even societal impacts, which are exciting and daunting. Central to the process of identifying and assessing the benefits and detriments of AIGC are critical issues involving reliability, intelligibility, desirability, and, perhaps most of all, trustworthiness. Although humans have generally accepted the reality that AI is destined to play a prominent role in our lives, we are still in the very early stages of determining how we feel about the complex relationships that emerge between people and AI. Management and organizational scholars play a key role in developing theories that demarcate and predict the evolving structure and content of these relationships. Towards that end, this study adopts a mixed-methods design to systematically examine perceptions of AIGC trustworthiness. We begin by employing grounded theory to develop a nomology framework that integrates the extroverted and introverted dimensions of human cognition. We then subject the interview corpus to text mining and sentiment analysis to distill targeted, evidence-based strategies for strengthening AIGC trustworthiness.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 2","pages":"Article 100169"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148202766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Artificial intelligence in corporate boards: a dual-dimensional framework for integration across autonomy and structural levels 公司董事会中的人工智能：跨自主性和结构层面整合的双重维度框架

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2025-12-22 DOI: 10.1016/j.dsm.2025.12.001

Manal Ahdadou, Ayoub Ahdadou, Abdellah Aajly, Mohamed Tahrouch

{"title":"Artificial intelligence in corporate boards: a dual-dimensional framework for integration across autonomy and structural levels","authors":"Manal Ahdadou, Ayoub Ahdadou, Abdellah Aajly, Mohamed Tahrouch","doi":"10.1016/j.dsm.2025.12.001","DOIUrl":"10.1016/j.dsm.2025.12.001","url":null,"abstract":"<div><div>This study examines the integration of artificial intelligence (AI) into corporate governance, with a specific focus on board-level decision-making. It critically evaluates five progressive stages of AI adoption—assisted, augmented, amplified, autonomous, and autopoietic—against the criteria of technological feasibility, legal compatibility, and ethical viability. Augmented intelligence has emerged as the most operationally and normatively sound model, enhancing decision quality while preserving human oversight and accountability. However, existing research has narrowly focused on the technical evolution of AI, neglecting the structural levels at which it is embedded within boards. To address this gap, this study introduces a two-dimensional framework that maps AI adoption along two intersecting axes: the degree of AI autonomy and governance locus of integration, spanning individual directors, board committees, and the full board. This model provides a more granular and context-sensitive lens for understanding how AI can be responsibly adopted within board structures. The paper concludes with governance-level-specific recommendations to ensure the ethical and effective deployment of augmented intelligence, contributing to both academic theory and policy design. By aligning conceptual insights with real-world dynamics, this study advances a context-sensitive roadmap for the responsible and effective integration of AI in corporate governance.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 2","pages":"Article 100174"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148527436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrative innovation of large language models in industries: technologies, applications, and challenges 工业中大型语言模型的集成创新：技术、应用和挑战

Data Science and Management Pub Date : 2026-03-01 Epub Date: 2025-07-02 DOI: 10.1016/j.dsm.2025.06.005

Shikai Wang , Yiwen Shao

引用次数: 0

Data clustering: a fundamental method in data science and management 数据聚类：数据科学和管理的基本方法

Data Science and Management Pub Date : 2026-03-01 Epub Date: 2025-08-12 DOI: 10.1016/j.dsm.2025.08.001

Tai Dinh , Hauchi Wong , Daniil Lisik , Michal Koren , Dat Tran , Philip S. Yu , Joaquín Torres-Sospedra

{"title":"Data clustering: a fundamental method in data science and management","authors":"Tai Dinh , Hauchi Wong , Daniil Lisik , Michal Koren , Dat Tran , Philip S. Yu , Joaquín Torres-Sospedra","doi":"10.1016/j.dsm.2025.08.001","DOIUrl":"10.1016/j.dsm.2025.08.001","url":null,"abstract":"<div><div>This study investigates the pivotal role of data clustering in both data science and management, focusing on core methodologies, tools, and diverse applications. It examines traditional clustering techniques such as partitional and hierarchical methods, alongside more advanced approaches, including data stream, density-based, graph-based, and model-based clustering, which are essential for processing complex and structured datasets. The study highlights fundamental principles, presents commonly adapted tools and frameworks, outlines the clustering workflow within data science, and discusses major implementation challenges. Beyond technical applications, this study emphasizes how clustering supports managerial tasks and decision-making through a comprehensive survey of recent literature. By bridging analytical techniques with real-world business needs, clustering remains an essential tool in both data science and management. The study concludes by outlining future research directions, underscoring the role of clustering in driving innovation and enabling informed strategic and operational decisions.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 1","pages":"Article 100161"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147657822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0