Virtual Seminar Series: Ahmed Abbasi, University of Notre Dame
April 23, 2021
2:00 PM - 3:30 PM
Join us for a virtual seminar this semester with Ahmed Abbasi, University of Notre Dame.
Please use the link below to join via Zoom.
Meeting ID: 975 3576 7242
Password: IDStalk21
Title: Getting Personal: A Deep Learning Artifact for Text-based Measurement of Leaders' Personalities
Abstract: Analysts, managers, and policymakers are interested in predictive analytics capable of offering better foresight. It is generally accepted that in forecasting scenarios involving organizational policies and decision-making, executives’ personal characteristics – including personality – may be an important predictor of downstream outcomes. The inclusion of personality features in forecasting models has been hindered by the fact that traditional personality measurement mechanisms are often infeasible. Text-based personality detection has garnered attention due to the public availability of executives’ digital textual traces. However, the text machine learning space has bifurcated into two branches: feature-based methods relying on manually crafted human intuition, or deep learning language models that leverage big data and compute – the main commonality being that neither branch generates accurate personality assessments, thereby making personality measures infeasible for downstream forecasting applications. In this study, we propose DeepPerson, a design artifact for text-based personality detection that bridges these two branches by leveraging concepts from relevant psycholinguistic theories in conjunction with advanced deep learning strategies. DeepPerson incorporates novel transfer learning and hierarchical attention network methods that employ psychological concepts and data augmentation in conjunction with person-level linguistic information. We evaluate the utility of the proposed artifact using an extensive design evaluation on two personality data sets, in comparison with state-of-the-art methods proposed in academia and industry. DeepPerson is able to improve detection of personality dimensions by 10 to 20 percentage points relative to the best comparison methods. Using case studies in the finance and health domains, we show that more accurate text-based leadership personality detection can translate into significant improvements in downstream applications such as forecasting future firm performance or predicting pandemic infection rates. Our findings have important implications for IS research at the intersection of design and data science, and practical implications for managers focused on enabling, producing, or consuming predictive analytics.
Bio: Ahmed Abbasi is the Giovanini Endowed Chaired Professor in the Department of IT, Analytics, and Operations in the Mendoza College of Business at the University of Notre Dame. He also serves as Co-Director of the Human-centered Analytics Lab. Prior to joining Notre Dame, he served as Associate Dean, Endowed Chair, and Director of the Center for Business Analytics at the University of Virginia. Ahmed received his PhD in Information Systems from the Artificial Intelligence (AI) Lab at the University of Arizona. He attained an MBA and BS in Information Technology from Virginia Tech.
Ahmed has over twenty years of experience pertaining to AI and predictive analytics, with applications in health, online fraud and security, text mining, and social media. Ahmed’s research has been funded by over a dozen grants from the National Science Foundation and industry partners such as AWS, Microsoft, eBay, and Oracle. He has also received the IEEE Technical Achievement Award, INFORMS Design Science Award, and IBM Faculty Award for his work at the intersection of AI and Big Data.
Ahmed has published nearly 100 articles in journals and conferences, including top-tier outlets such as MISQ, ISR, JMIS, ACM TOIS, IEEE, TKDE, IEEE Intelligent Systems, and Journal of Marketing. One of his articles was considered a top publication by the Association for Information Systems. He also won best paper awards at MISQ and WITS, and was a finalist for the Hunt/Maynard Award. Ahmed’s work has been featured in various media outlets, including the Wall Street Journal, Harvard Business Review, the Associated Press, WIRED, CBS, and Fox.
Ahmed serves as Senior Editor for Information Systems Research (ISR) and Associate Editor (AE) for ACM, TMIS and IEEE Intelligent Systems. He is presently Chair of the INFORMS College on AI and previously
served as AE at ISR and Decision Sciences Journal. Ahmed is a senior member of the IEEE, and has been on program committees for various conferences related to AI, information systems, computational linguistics, text analytics, and data mining. He has also served as co-founder or advisory board member for multiple predictive analytics-related companies.
Date posted
Apr 16, 2021
Date updated
Apr 16, 2021