Yuheun Kim

selected publications

1. 

   Belief Alignment vs Opinion Leadership: Understanding Cross-linguistic Digital Activism in K-pop and BLM Communities

   Yuheun Kim, and Joshua Introne

   Accepted for ICWSM 2026

   Abs HTML

   The internet has transformed activism, giving rise to more organic, diverse, and dynamic social movements that transcend geo-political boundaries. Despite extensive research on the role of social media and the internet in cross-cultural activism, the fundamental motivations driving these global movements remain poorly understood. This study examines two plausible explanations for cross-cultural activism: first, that it is driven by influential online opinion leaders, and second, that it results from individuals resonating with emergent sets of beliefs, values, and norms. We conduct a case study of the interaction between K-pop fans and the Black Lives Matter (BLM) movement on Twitter following the murder of George Floyd. Our findings provide strong evidence that belief alignment, where people resonate with common beliefs, is a primary driver of cross-cultural interactions in digital activism. We also demonstrate that while the actions of potential opinion leaders–in this case, K-pop entertainers–may amplify activism and lead to further expressions of love and admiration from fans, they do not appear to be a direct cause of activism. Finally, we report some initial evidence that the interaction between BLM and K-pop led to slight increases in their overall belief similarity.

2. 

   LLM-Supported Content Analysis of Motivated Reasoning on Climate Change

   Yuheun Kim, Qiaoyi Liu, and Jeff Hemsley

   Accepted for ASIS&T 2025

   Abs HTML

   Public discourse around climate change remains polarized despite scientific consensus on anthropogenic climate change (ACC). This study examines how “believers” and “skeptics” of ACC differ in their YouTube comment discourse. We analyzed 44,989 comments from 30 videos using a large language model (LLM) as a qualitative annotator, identifying ten distinct topics. These annotations were combined with social network analysis to examine engagement patterns. A linear mixed-effects model showed that comments about government policy and natural cycles generated significantly lower interaction compared to misinformation, suggesting these topics are ideologically settled points within communities. These patterns reflect motivated reasoning, where users selectively engage with content that aligns with their identity and beliefs. Our findings highlight the utility of LLMs for large-scale qualitative analysis and highlight how climate discourse is shaped not only by content, but by underlying cognitive and ideological motivations.

3. 

   Can ChatGPT Understand Causal Language in Science Claims?

   Yuheun Kim, Lu Guo, Bei Yu, and Yingya Li

   In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis Jul 2023

   Abs Bib HTML

   This study evaluated ChatGPT’s ability to understand causal language in science papers and news by testing its accuracy in a task of labeling the strength of a claim as causal, conditional causal, correlational, or no relationship. The results show that ChatGPT is still behind the existing fine-tuned BERT models by a large margin. ChatGPT also had difficulty understanding conditional causal claims mitigated by hedges. However, its weakness may be utilized to improve the clarity of human annotation guideline. Chain-of-Thoughts were faithful and helpful for improving prompt performance, but finding the optimal prompt is difficult with inconsistent results and the lack of effective method to establish cause-effect between prompts and outcomes, suggesting caution when generalizing prompt engineering results across tasks or models.

   @inproceedings{2023-kim-chatgpt,
     title = {Can {C}hat{GPT} Understand Causal Language in Science Claims?},
     author = {Kim, Yuheun and Guo, Lu and Yu, Bei and Li, Yingya},
     booktitle = {Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis},
     month = jul,
     year = {2023},
     address = {Toronto, Canada},
     publisher = {Association for Computational Linguistics},
     pages = {379--389}
   }

4. 

   BioPREP: Deep learning-based predicate classification with SemMedDB

   Gibong Hong*, Yuheun Kim*, YeonJung Choi*, and Min Song

   Journal of Biomedical Informatics Jul 2021

   Abs Bib HTML

   When it comes to inferring relations between entities in biomedical texts, Relation Extraction (RE) has become key to biomedical information extraction. Although previous studies focused on using rule-based and machine learning-based approaches, these methods lacked efficiency in terms of the demanding amount of feature processing while resulting in relatively low accuracy. Some existing biomedical relation extraction tools are based on neural networks. Nonetheless, they rarely analyze possible causes of the difference in accuracy among predicates. Also, there have not been enough biomedical datasets that were structured for predicate classification. With these regards, we set our research goals as follows: constructing a large-scale training dataset, namely Biomedical Predicate Relation-extraction with Entity-filtering by PKDE4J (BioPREP), based on SemMedDB then using PKDE4J as an entity-filtering tool, evaluating the performances of each neural network-based algorithms on the structured dataset. We then analyzed our model’s performance in-depth by grouping predicates into semantic clusters. Based on comprehensive experimental outcomes, the experiments showed that the BioBERT-based model outperformed other models for predicate classification. The suggested model achieved an f1-score of 0.846 when BioBERT was loaded as the pre-trained model and 0.840 when SciBERT weights were loaded. Moreover, the semantic cluster analysis showed that sentences containing key phrases were classified better, such as comparison verb + ‘than’.

   @article{hong-2021-bioprep,
     title = {BioPREP: Deep learning-based predicate classification with SemMedDB},
     author = {Hong*, Gibong and Kim*, Yuheun and Choi*, YeonJung and Song, Min},
     journal = {Journal of Biomedical Informatics},
     volume = {122},
     pages = {103888},
     year = {2021},
     publisher = {Elsevier}
   }