Kanyao Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kanyao Han has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Jana Diesner
University of Illinois Urbana-Champaign, Champaign, USA
4 shared publications - Andreas Witt
Leibniz Institute for the German Language, Mannheim, Germany
2 shared publications Haotian Zhu
University of Washington
2 shared publications- Maria Becker
Leibniz Institute for the German Language, Mannheim, Germany
2 shared publications - Rezvaneh Rezapour
Drexel University, Philadelphia, USA
2 shared publications - Zhiwen You
University of Illinois Urbana-Champaign
2 shared publications
Latest Publications
- Open Access
- 28 May 2026
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 60 (3) , 50
Impact classification within and beyond academia: domain-robust annotation and the capacity of large language models
Prior analyses and assessments of the impact of scientific research has mainly relied on analyzing its scope within academia and its influence within scholarly circles. However, by not considering the broader societal, economic, and policy implications of research projects, these studies overlook the ways in which scientific discoveries contribute to technological innovation, public health improvements, environmental sustainability, and other areas of real-world application. We expand upon this prior work by developing and validating a conceptual and computational solution to automatically identify and categorize the impact of scientific research within and especially beyond academia based on text data. We first empirically develop and evaluate an annotation schema to capture and classify the impact of research projects based on research reports from different scientific domains. We then annotate a large dataset of more than 45k sentences extracted from research reports for the developed impact categories. We examine the annotated dataset for patterns in the distribution of impact categories across different scientific domains, co-occurrences of impact categories, and signal words of impact. Using the annotated texts and the novel classification schema, we investigate the performance of large language models (LLMs) for automated impact classification. Our results show that fine-tuning the models on our annotated datasets statistically significantly outperforms zero- and few-shot prompting approaches. This indicates that state-of-the-art LLMs without fine-tuning may not work well for novel classification schemas such as our impact classification schema, and in turn highlights the importance of diligent manual annotations as empirical basis in the field of computational social science.
- 28 May 2026
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 60 (3) , 50
Open AccessImpact classification within and beyond academia: domain-robust annotation and the capacity of large language models
Prior analyses and assessments of the impact of scientific research has mainly relied on analyzing its scope within academia and its influence within scholarly circles. However, by not considering the broader societal, economic, and policy implications of research projects, these studies overlook the ways in which scientific discoveries contribute to technological innovation, public health improvements, environmental sustainability, and other areas of real-world application. We expand upon this prior work by developing and validating a conceptual and computational solution to automatically identify and categorize the impact of scientific research within and especially beyond academia based on text data. We first empirically develop and evaluate an annotation schema to capture and classify the impact of research projects based on research reports from different scientific domains. We then annotate a large dataset of more than 45k sentences extracted from research reports for the developed impact categories. We examine the annotated dataset for patterns in the distribution of impact categories across different scientific domains, co-occurrences of impact categories, and signal words of impact. Using the annotated texts and the novel classification schema, we investigate the performance of large language models (LLMs) for automated impact classification. Our results show that fine-tuning the models on our annotated datasets statistically significantly outperforms zero- and few-shot prompting approaches. This indicates that state-of-the-art LLMs without fine-tuning may not work well for novel classification schemas such as our impact classification schema, and in turn highlights the importance of diligent manual annotations as empirical basis in the field of computational social science.
- Open Access
- 23 January 2025
- Published by Springer Nature in Research Square
Impact Classification within and beyond Academia: Domain-Robust Annotation and the Capacity of Large Language Models
Prior analyses and assessments of the impact of scientific research has mainly relied on analyzing its scope within academia and its influence within scholarly circles. However, by not considering the broader societal, economic, and policy implications of research projects, these studies overlook the ways in which scientific discoveries contribute to technological innovation, public health improvements, environmental sustainability, and other areas of real-world application. We expand upon this prior work by developing and validating a conceptual and computational solution to automatically identify and categorize the impact of scientific research within and especially beyond academia based on text data. We first empirically develop and evaluate an annotation schema to capture and classify the impact of research projects based on research reports from different scientific domains. We then annotate a large dataset of more than 45k sentences extracted from research reports for the developed impact categories. We examine the annotated dataset for patterns in the distribution of impact categories across different scientific domains, co-occurrences of impact categories, and signal words of impact. Using the annotated texts and the novel classification schema, we investigate the performance of large language models (LLMs) for automated impact classification. Our results show that fine-tuning the models on our annotated datasets statistically significantly outperforms zero- and fewshot prompting approaches. This indicates that state-of-the-art LLMs without fine-tuning may not work well for novel classification schemas such as our impact classification schema, and in turn highlights the importance of diligent manual annotations as empirical basis in the field of computational social science.
- 23 January 2025
- Published by Springer Nature in Research Square
Open AccessImpact Classification within and beyond Academia: Domain-Robust Annotation and the Capacity of Large Language Models
Prior analyses and assessments of the impact of scientific research has mainly relied on analyzing its scope within academia and its influence within scholarly circles. However, by not considering the broader societal, economic, and policy implications of research projects, these studies overlook the ways in which scientific discoveries contribute to technological innovation, public health improvements, environmental sustainability, and other areas of real-world application. We expand upon this prior work by developing and validating a conceptual and computational solution to automatically identify and categorize the impact of scientific research within and especially beyond academia based on text data. We first empirically develop and evaluate an annotation schema to capture and classify the impact of research projects based on research reports from different scientific domains. We then annotate a large dataset of more than 45k sentences extracted from research reports for the developed impact categories. We examine the annotated dataset for patterns in the distribution of impact categories across different scientific domains, co-occurrences of impact categories, and signal words of impact. Using the annotated texts and the novel classification schema, we investigate the performance of large language models (LLMs) for automated impact classification. Our results show that fine-tuning the models on our annotated datasets statistically significantly outperforms zero- and fewshot prompting approaches. This indicates that state-of-the-art LLMs without fine-tuning may not work well for novel classification schemas such as our impact classification schema, and in turn highlights the importance of diligent manual annotations as empirical basis in the field of computational social science.
- Open Access
SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics
Prompt-based fine-tuning has become an essential method for eliciting information encoded in pre-trained language models for a variety of tasks, including text classification. For multi-class classification tasks, prompt-based fine-tuning under low-resource scenarios has resulted in performance levels comparable to those of fully fine-tuning methods. Previous studies have used crafted prompt templates and verbalizers, mapping from the label terms space to the class space, to solve the classification problem as a masked language modeling task. However, cross-domain and fine-grained prompt-based fine-tuning with an automatically enriched verbalizer remains unexplored, mainly due to the difficulty and costs of manually selecting domain label terms for the verbalizer, which requires humans with domain expertise. To address this challenge, we introduce SciPrompt, a framework designed to automatically retrieve scientific topic-related terms for low-resource text classification tasks. To this end, we select semantically correlated and domain-specific label terms within the context of scientific literature for verbalizer augmentation. Furthermore, we propose a new verbalization strategy that uses correlation scores as additional weights to enhance the prediction performance of the language model during model tuning. Our method outperforms state-of-the-art, prompt-based fine-tuning methods on scientific text classification tasks under few and zero-shot settings, especially in classifying fine-grained and emerging scientific topics.
Open AccessSciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics
Prompt-based fine-tuning has become an essential method for eliciting information encoded in pre-trained language models for a variety of tasks, including text classification. For multi-class classification tasks, prompt-based fine-tuning under low-resource scenarios has resulted in performance levels comparable to those of fully fine-tuning methods. Previous studies have used crafted prompt templates and verbalizers, mapping from the label terms space to the class space, to solve the classification problem as a masked language modeling task. However, cross-domain and fine-grained prompt-based fine-tuning with an automatically enriched verbalizer remains unexplored, mainly due to the difficulty and costs of manually selecting domain label terms for the verbalizer, which requires humans with domain expertise. To address this challenge, we introduce SciPrompt, a framework designed to automatically retrieve scientific topic-related terms for low-resource text classification tasks. To this end, we select semantically correlated and domain-specific label terms within the context of scientific literature for verbalizer augmentation. Furthermore, we propose a new verbalization strategy that uses correlation scores as additional weights to enhance the prediction performance of the language model during model tuning. Our method outperforms state-of-the-art, prompt-based fine-tuning methods on scientific text classification tasks under few and zero-shot settings, especially in classifying fine-grained and emerging scientific topics.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 6087-6104
SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics
Zhiwen You, Kanyao Han, Haotian Zhu, Bertram Ludaescher, Jana Diesner. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 6087-6104
Open AccessSciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics
Zhiwen You, Kanyao Han, Haotian Zhu, Bertram Ludaescher, Jana Diesner. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.