Jisu Kim

Jisu Kim

Auto-generated profile, based on publicly available information

Jisu Kim

Renmin University of China School of Applied Economics Beijing

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 February 2025 in IEEE Access
Verified
Journal Article
Open access
MWMeng Wang
Meng Wang
JKJisu Kim
Jisu Kim
YYYuting Yan
Yuting Yan
Text classification is the process of categorizing sentences into predefined classes on the basis of their meanings or functions. In this context, feature words play a crucial role in representing the core meaning and key information of sentences, reflecting the main content and deep semantics of scientific literature. Optimizing text classification models using feature words is an important task in the information mining of scientific literature. To address text classification considering feature words, this study constructs a set of feature words from a linguistic perspective and quantitatively expresses the weight differences of various feature words on the basis of syntactic structure features. By embedding the weight information, absolute position, relative position, and contextual information of feature words into pre-trained models, the universal text classification models considering feature word vector weights is established. The analysis of hyperparameter space relationships reveals that the hyperparameter settings are not simple linear relationships and that their interactions are often nonlinear and complex. Employing the Bayesian optimization algorithm facilitates the model in finding the optimal hyperparameters while reducing computational costs. Based on the public dataset RCMR 280K, the experimental results demonstrate that considering feature words enables the model to capture sentence structure and features in text classification task, improving the recognition accuracy of the model. Compared with base models (BERT, SciBERT, RoBERTa and ModernBERT) and their regularized models which consider feature words, the improved ModernBERT, which is based on weighted feature word vectors, achieves an average F1 of 95.8% in the recognition tasks of research objective, method, result and conclusion sentences, an improvement of 1.2%, 0.8%, 1.1%, and 0.9%, respectively. In addition, the results show that large language models (LLMs) exhibit robust performance in text classification tasks, with the fine-tuned GLM4-9B achieving superior performance by reaching an average F1 of 91.9%. This model can be applied to sentence recognition and classification tasks in various domains. By updating or replacing the feature word table, the model can be adapted to recognize and classify different types of sentences, providing a theoretical basis or model foundation for other downstream tasks. More details and model weights are public at https://huggingface.co/wmsr22/Classification/tree/main.

14 October 2025 in Sustainability Accounting, Management and Policy Journal
Verified
Journal Article
Closed access
XWXiaoqing Wong
Xiaoqing Wong
PSPing Sun
Ping Sun
AWAnkang Wang
Ankang Wang
JKJisu Kim
Jisu Kim
Purpose: This study aims to examine the dynamic and distributional effects of digital economy (DIE), green innovation (GIN), renewable energy (REE) on sustainable development (SUS) amid accelerating digital and green transformations. Design/methodology/approach: Using a quantile autoregressive distributed lag model, this study conducts a time- and quantile-varying analysis of the relationships among DIE, GIN, REE and SUS across different quantiles and time horizons, focusing on asymmetric dynamics and quantile dependency. Findings: Results reveal that both DIE and REE exhibit significant positive influences on SUS over the long term, while REE serves as a key driver of sustainability in the short term. Asymmetry analysis indicates that the effects of REE and GIN are most pronounced at median levels of SUS, while DIE’s influence intensifies at higher quantiles, reflecting its role in advanced sustainability ecosystems. Strategic prioritization identifies DIE as the dominant long-term enabler, REE as the rapid-response tool and GIN as a latent force of sustainability. Practical implications: The findings provide practical insights for policymakers to tailor sustainability strategies by leveraging digital transformation, accelerating renewable energy deployment and strengthening green innovation systems. Social implications: By shedding light on the differentiated roles of digitalization, green innovation and clean energy in promoting sustainability, this study contributes to the formulation of targeted policies that support sustainable development goals. Originality/value: This paper offers a novel theoretical perspective by integrating DIE, GIN, REE and SUS into a unified framework. It also uniquely integrates the quantile-based approach to uncover the asymmetric and dynamic influences of DIE, GIN and REE on sustainable development, enhancing understanding of the contextual effectiveness of different sustainability drivers.