Link Prediction Between Structured Geopolitical Events: Models and Experiments
Often thought of as higher-order entities, events have recently become important subjects of research in the computational sciences, including within complex systems and natural language processing (NLP). One such application is event link prediction. Given an input event, event link prediction is t...
Guardado en:
Autor principal: | |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/842bbebe44194e148319c8ff2822d291 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:842bbebe44194e148319c8ff2822d291 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:842bbebe44194e148319c8ff2822d2912021-12-01T19:31:36ZLink Prediction Between Structured Geopolitical Events: Models and Experiments2624-909X10.3389/fdata.2021.779792https://doaj.org/article/842bbebe44194e148319c8ff2822d2912021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fdata.2021.779792/fullhttps://doaj.org/toc/2624-909XOften thought of as higher-order entities, events have recently become important subjects of research in the computational sciences, including within complex systems and natural language processing (NLP). One such application is event link prediction. Given an input event, event link prediction is the problem of retrieving a relevant set of events, similar to the problem of retrieving relevant documents on the Web in response to keyword queries. Since geopolitical events have complex semantics, it is an open question as to how to best model and represent events within the framework of event link prediction. In this paper, we formalize the problem and discuss how established representation learning algorithms from the machine learning community could potentially be applied to it. We then conduct a detailed empirical study on the Global Terrorism Database (GTD) using a set of metrics inspired by the information retrieval community. Our results show that, while there is considerable signal in both network-theoretic and text-centric models of the problem, classic text-only models such as bag-of-words prove surprisingly difficult to outperform. Our results establish both a baseline for event link prediction on GTD, and currently outstanding challenges for the research community to tackle in this space.Mayank KejriwalFrontiers Media S.A.articleevent representationsrepresentation learninggeopolitical event link predictionword embeddingsmulti-partite networksInformation technologyT58.5-58.64ENFrontiers in Big Data, Vol 4 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
event representations representation learning geopolitical event link prediction word embeddings multi-partite networks Information technology T58.5-58.64 |
spellingShingle |
event representations representation learning geopolitical event link prediction word embeddings multi-partite networks Information technology T58.5-58.64 Mayank Kejriwal Link Prediction Between Structured Geopolitical Events: Models and Experiments |
description |
Often thought of as higher-order entities, events have recently become important subjects of research in the computational sciences, including within complex systems and natural language processing (NLP). One such application is event link prediction. Given an input event, event link prediction is the problem of retrieving a relevant set of events, similar to the problem of retrieving relevant documents on the Web in response to keyword queries. Since geopolitical events have complex semantics, it is an open question as to how to best model and represent events within the framework of event link prediction. In this paper, we formalize the problem and discuss how established representation learning algorithms from the machine learning community could potentially be applied to it. We then conduct a detailed empirical study on the Global Terrorism Database (GTD) using a set of metrics inspired by the information retrieval community. Our results show that, while there is considerable signal in both network-theoretic and text-centric models of the problem, classic text-only models such as bag-of-words prove surprisingly difficult to outperform. Our results establish both a baseline for event link prediction on GTD, and currently outstanding challenges for the research community to tackle in this space. |
format |
article |
author |
Mayank Kejriwal |
author_facet |
Mayank Kejriwal |
author_sort |
Mayank Kejriwal |
title |
Link Prediction Between Structured Geopolitical Events: Models and Experiments |
title_short |
Link Prediction Between Structured Geopolitical Events: Models and Experiments |
title_full |
Link Prediction Between Structured Geopolitical Events: Models and Experiments |
title_fullStr |
Link Prediction Between Structured Geopolitical Events: Models and Experiments |
title_full_unstemmed |
Link Prediction Between Structured Geopolitical Events: Models and Experiments |
title_sort |
link prediction between structured geopolitical events: models and experiments |
publisher |
Frontiers Media S.A. |
publishDate |
2021 |
url |
https://doaj.org/article/842bbebe44194e148319c8ff2822d291 |
work_keys_str_mv |
AT mayankkejriwal linkpredictionbetweenstructuredgeopoliticaleventsmodelsandexperiments |
_version_ |
1718404641157283840 |