1 code implementation • 2 Apr 2024 • Zoher Kachwala, Jisun An, Haewoon Kwak, Filippo Menczer
Knowledge graphs play a pivotal role in various applications, such as question-answering and fact-checking.
Ranked #2 on Graph Matching on RARE
1 code implementation • 26 Mar 2024 • Fan Huang, Haewoon Kwak, Kunwoo Park, Jisun An
Our results show that ChatGPT aligns better with humans in more coarse-grained scales.
no code implementations • 1 Mar 2024 • Rachith Aiyappa, Shruthi Senthilmani, Jisun An, Haewoon Kwak, Yong-Yeol Ahn
We investigate the performance of LLM-based zero-shot stance detection on tweets.
no code implementations • 17 Feb 2024 • Fan Huang, Haewoon Kwak, Jisun An
The robustness of AI-content detection models against cultivated attacks (e. g., paraphrasing or word switching) remains a significant concern.
no code implementations • 22 Mar 2023 • Rachith Aiyappa, Jisun An, Haewoon Kwak, Yong-Yeol Ahn
ChatGPT, the first large language model (LLM) with mass adoption, has demonstrated remarkable performance in numerous natural language tasks.
1 code implementation • 21 Mar 2023 • Hong Zhang, Haewoon Kwak, Wei Gao, Jisun An
People who share similar opinions towards controversial topics could form an echo chamber and may share similar political views toward other topics as well.
no code implementations • 11 Feb 2023 • Fan Huang, Haewoon Kwak, Jisun An
Recent studies have alarmed that many online hate speeches are implicit.
no code implementations • 11 Sep 2022 • Fan Huang, Haewoon Kwak, Jisun An
Recent studies have exploited advanced generative language models to generate Natural Language Explanations (NLE) for why a certain text could be hateful.
no code implementations • 20 Apr 2022 • Haewoon Kwak, Jisun An, Kunwoo Park
A conversation corpus is essential to build interactive AI applications.
no code implementations • 19 Apr 2022 • Yun Yu Chong, Haewoon Kwak
While the contagious nature of online toxicity sparked increasing interest in its early detection and prevention, most of the literature focuses on the Western world.
no code implementations • 16 Mar 2021 • Preslav Nakov, Husrev Taha Sencar, Jisun An, Haewoon Kwak
The present level of proliferation of fake, biased, and propagandistic content online has made it impossible to fact-check every single suspicious claim or article, either manually or automatically.
1 code implementation • 17 Sep 2020 • Kunwoo Park, Haewoon Kwak, Jisun An, Sanjay Chawla
To reach a broader audience and optimize traffic toward news articles, media outlets commonly run social media accounts and share their content with a short text summary.
1 code implementation • ACL 2020 • Ramy Baly, Georgi Karadzhov, Jisun An, Haewoon Kwak, Yoan Dinkov, Ahmed Ali, James Glass, Preslav Nakov
Alternatively, we can profile entire news outlets and look for those that are likely to publish fake or biased content.
no code implementations • 4 May 2020 • Haewoon Kwak, Jisun An, Yong-Yeol Ahn
By examining the ebb and flow of media frames over almost two decades, we show that short-term frame abundance fluctuation closely corresponds to major events, while there also exist several long-term trends, such as the gradually increasing prevalence of the ``Cultural identity'' frame.
no code implementations • 31 Mar 2020 • Kunwoo Park, Haewoon Kwak, Hyunho Song, Meeyoung Cha
The results show that exposing academic degrees is likely to lead to higher audience votes as well as larger discussion size, compared to the users without the disclosed identities, in a community that covers peer-reviewed scientific articles.
Social and Information Networks
1 code implementation • 20 Feb 2020 • Haewoon Kwak, Jisun An, Elise Jing, Yong-Yeol Ahn
{Here, we propose FrameAxis, a method for characterizing documents by identifying the most relevant semantic axes ("microframes") that are overrepresented in the text using word embedding.
no code implementations • IJCNLP 2019 • Yifan Zhang, Giovanni Da San Martino, Alberto Barrón-Cedeño, Salvatore Romeo, Jisun An, Haewoon Kwak, Todor Staykovski, Israa Jaradat, Georgi Karadzhov, Ramy Baly, Kareem Darwish, James Glass, Preslav Nakov
We introduce Tanbih, a news aggregator with intelligent analysis tools to help readers understanding what's behind a news story.
no code implementations • 11 Apr 2019 • Jisun An, Haewoon Kwak, Oliver Posegga, Andreas Jungherr
While research on political talk in online environments abounds, we know surprisingly little about the potentially varying nature of discussions in politically homogeneous spaces as compared to cross-cutting communication spaces.
1 code implementation • ACL 2018 • Jisun An, Haewoon Kwak, Yong-Yeol Ahn
Because word semantics can substantially change across communities and contexts, capturing domain-specific word semantics is an important challenge.
no code implementations • 15 Mar 2016 • Haewoon Kwak, Jisun An
In this work, we analyze more than two million news photos published in January 2016.
no code implementations • 26 Mar 2015 • Julio Reis, Fabricio Benevenuto, Pedro O. S. Vaz de Melo, Raquel Prates, Haewoon Kwak, Jisun An
In order to discover strategies that could be used to attract clicks, we extracted features from the text of the news headlines related to the sentiment polarity of the headline.