News
May 20, 2025 | I’m honored to be invited to deliver a talk for the “Narratives and AI in Quantitative History: A Mandarin Workshop” organized by Professor Chicheng Ma at The University of Hong Kong. Title: AI for the Humanities. Abstract: The development of artificial intelligence is transforming the way humanities scholars conduct research. Adopting an interdisciplinary perspective, this presentation will illustrate how AI can be effectively integrated into the humanities and social sciences, including psychology, geography, and history, through three specific case studies: (1) surveying the dead minds; (2) geocoding the past world; and (3) renacting intellectual debates in history. ![]() |
---|---|
Apr 23, 2025 | Our work using LLMs for historical geography has been proudly published in International Journal of Geographical Information Science. Title: Geocoding the Past World: Unearthing Coordinates of Early China from Texts Using Generative AI. Abstract: Extracting geographic information from historical texts presents unique challenges. To address these challenges, this study leverages generative large language models (LLMs) to extract historical toponyms and their corresponding location references from texts. The coordinates of the extracted toponyms are then identified by a historical geocoder, which also calculates their maximum error distances based on the location references, indicating the degree of uncertainty. Both the extraction and geocoding processes are integrated into a novel tool named ‘His-Geo’ (https://github.com/yukiyuqichen/His-Geo). To evaluate the results, this study also curates a manually annotated dataset, the Early China Historical Geographic Corpus (CHGC-Early), filling the gap in the absence of geographic data for early China in existing gazetteers and providing a benchmark dataset for training and evaluating approaches for tasks related to geographic information extraction from premodern Chinese texts. The evaluation results show a satisfactory 0.831 F1 score for the GPT-4o model, demonstrating the remarkable capability of generative large language models in extracting geographic information from lengthy, unstructured texts that encompass diverse and sometimes conflicting views. ![]() |
Sep 18, 2024 | I’m honored to be invited to deliver a talk for the “Frontiers in Chinese Studies” series organized by Professor Song Chen at Bucknell University. Title: Historical Minds and Artificial Intelligence: How AI Helps Rediscover Ancient Minds. Abstract: Advances in AI, particularly in natural language processing, have enabled large-scale quantitative analysis of historical texts. This talk presents two cases using AI models to explore intellectual debates and cultural psychology in premodern China. ![]() |
Sep 18, 2024 | Our work has been proudly accepted by The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024). Title: Surveying the Dead Minds: Historical-Psychological Text Analysis with Contextualized Construct Representation (CCR) for Classical Chinese. ![]() |
Jul 14, 2024 | I’m honored to present my work at The Tenth Annual Symposium on Quantitative History. Title: The Waves of Social Changes: A Quantitative Analysis of Ritual Bronzes in Early China. ![]() |
Jun 12, 2024 | I’m honored to be invited to deliver a talk for the “Fu Xuancong Academic Lecture” series organized by Professor Fan Xiang at Tsinghua University. ![]() |
Jun 03, 2024 | I’m honored to be invited to deliver a talk for the School of Chinese at The University of Hong Kong. Title: Surveying the Dead Minds: Historical Text Analysis Unveilling Psychological Dynamics Within Chinese Culture Across Two Millennia. Abstract: Humans have been creating texts for thousands of years, expressing their social norms, values, composing poetry, and storytelling within them. Historical texts contain rich yet underexplored sources of psychological data, condensing the thoughts, emotions, and behaviours of people who lived in the past. By utilizing the state-of-the-art natural language processing (NLP) methods, we developed a pipeline, called contextualized construct representations (CCR), to measure psychological constructs such as collectivism, individualism, norm strength, among others, in classical Chinese corpora. The large-scale historical text analysis unveils both temporal and spatial variations of various psychological constructs and moral values in pre-modern China, demonstrating the complex influences of a variety of factors, including climate, agriculture, conflicts, Confucianism, kinship, etc., on psychology and culture. ![]() |
Apr 02, 2024 | Our work using AI methods for psychometrics in historical texts has been proudly covered by MIT Technology Review China. ![]() |
Dec 08, 2023 | I’m honored to be invited to deliver a presentation in the “GenAI and the Self-Enhancement of Humanities Scholars” Forum, organized by Professor Jing Xiang, at The 4th Tsinghua International Forum on Digital Humanities. Title: Pure Conversation with AI: Building Generative Agents for Humanities Studies. ![]() |
Nov 05, 2023 | I’m honored to be invited to deliver a talk for the “The Transformation of Humanities in the Age of Intelligence: What is the New Liberal Arts and Digital Humanities” Roundtable Lecture at Peking University. Title: From Questions to Methods: Digital Humanities and Humanities Computing. ![]() |
Nov 04, 2023 | I’m honored to be invited to deliver a presentation for the Workshop on China Biographical Database Project at Peking University. ![]() |
Oct 06, 2023 | I’m honored to be invited to deliver a presentation for a workshop on China Biographical Database Project (CBDB), hosted by Hongsu Wang and Kwok-leong Tang, at The Institute for Quantitative Social Science, Harvard University. Title: Geocoding the Past World: Unearthing Coordinates of Early China from Texts Using Large Language Models. ![]() |
Jul 25, 2022 | I’m honored to present my work at Digital Humanities Conference 2022. Title: The Great Transformation of the Clan System in Early China: A Social Network Analysis of Clan-sign Inscriptions from 1300 BC to 900 BC. ![]() |
Jun 25, 2022 | I’m honored to present my work at the Biographical Data in a Digital World 2022 (BD 2022) Workshop, co-located with the Digital Humanities Conference 2022. Title: The Hierarchical Structure of the Marriage Network of Noble Lineages in the Zhou Dynasty. ![]() |