@inproceedings{gwak-etal-2024-forecasting,
title = "Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling",
author = "Gwak, Daehoon and
Park, Junwoo and
Park, Minho and
Park, ChaeHun and
Lee, Hyunchan and
Choi, Edward and
Choo, Jaegul",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.526/",
doi = "10.18653/v1/2024.findings-emnlp.526",
pages = "9000--9023",
abstract = "Predicting future international events from textual information, such as news articles, has tremendous potential for applications in global policy, strategic decision-making, and geopolitics. However, existing datasets available for this task are often limited in quality, hindering the progress of related research. In this paper, we introduce a novel dataset designed to address these limitations by leveraging the advanced reasoning capabilities of large-language models (LLMs). Our dataset features high-quality scoring labels generated through advanced prompt modeling and rigorously validated by domain experts in political science. We showcase the quality and utility of our dataset for real-world event prediction tasks, demonstrating its effectiveness through extensive experiments and analysis. Furthermore, we publicly release our dataset along with the full automation source code for data collection, labeling, and benchmarking, aiming to support and advance research in text-based event prediction."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gwak-etal-2024-forecasting">
<titleInfo>
<title>Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daehoon</namePart>
<namePart type="family">Gwak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junwoo</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minho</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">ChaeHun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunchan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaegul</namePart>
<namePart type="family">Choo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Predicting future international events from textual information, such as news articles, has tremendous potential for applications in global policy, strategic decision-making, and geopolitics. However, existing datasets available for this task are often limited in quality, hindering the progress of related research. In this paper, we introduce a novel dataset designed to address these limitations by leveraging the advanced reasoning capabilities of large-language models (LLMs). Our dataset features high-quality scoring labels generated through advanced prompt modeling and rigorously validated by domain experts in political science. We showcase the quality and utility of our dataset for real-world event prediction tasks, demonstrating its effectiveness through extensive experiments and analysis. Furthermore, we publicly release our dataset along with the full automation source code for data collection, labeling, and benchmarking, aiming to support and advance research in text-based event prediction.</abstract>
<identifier type="citekey">gwak-etal-2024-forecasting</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.526</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.526/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>9000</start>
<end>9023</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling
%A Gwak, Daehoon
%A Park, Junwoo
%A Park, Minho
%A Park, ChaeHun
%A Lee, Hyunchan
%A Choi, Edward
%A Choo, Jaegul
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F gwak-etal-2024-forecasting
%X Predicting future international events from textual information, such as news articles, has tremendous potential for applications in global policy, strategic decision-making, and geopolitics. However, existing datasets available for this task are often limited in quality, hindering the progress of related research. In this paper, we introduce a novel dataset designed to address these limitations by leveraging the advanced reasoning capabilities of large-language models (LLMs). Our dataset features high-quality scoring labels generated through advanced prompt modeling and rigorously validated by domain experts in political science. We showcase the quality and utility of our dataset for real-world event prediction tasks, demonstrating its effectiveness through extensive experiments and analysis. Furthermore, we publicly release our dataset along with the full automation source code for data collection, labeling, and benchmarking, aiming to support and advance research in text-based event prediction.
%R 10.18653/v1/2024.findings-emnlp.526
%U https://aclanthology.org/2024.findings-emnlp.526/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.526
%P 9000-9023
Markdown (Informal)
[Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling](https://aclanthology.org/2024.findings-emnlp.526/) (Gwak et al., Findings 2024)
ACL
- Daehoon Gwak, Junwoo Park, Minho Park, ChaeHun Park, Hyunchan Lee, Edward Choi, and Jaegul Choo. 2024. Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 9000–9023, Miami, Florida, USA. Association for Computational Linguistics.