@inproceedings{47b0084ae88c40c2be569115d552a27c,
title = "Mining News Events from Comparable News Corpora: A Multi-Attribute Proximity Network Modeling Approach",
abstract = "We present ProxiModel, a novel event mining framework for extracting high-quality structured event knowledge from large, redundant, and noisy news data sources. The proposed model differentiates itself from other approaches by modeling both the event correlation within each individual document as well as across the corpus. To facilitate this, we introduce the concept of a proximity-network, a novel space-efficient data structure to facilitate scalable event mining. This proximity network captures the corpus-level co-occurence statistics for candidate event descriptors, event attributes, as well as their connections. We probabilistically model the proximity network as a generative process with sparsity-inducing regularization. This allows us to efficiently and effectively extract high-quality and interpretable news events. Experiments on three different news corpora demonstrate that the proposed method is effective and robust at generating high-quality event descriptors and attributes. We briefly detail many interesting applications from our proposed framework such as news summarization, event tracking and multi-dimensional analysis on news. Finally, we explore a case study on visualizing the events for a Japan Tsunami news corpus and demonstrate ProxiModel's ability to automatically summarize emerging news events.",
author = "Hyungsul Kim and Ahmed El-Kishky and Xiang Ren and Jiawei Han",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE International Conference on Big Data, Big Data 2019 ; Conference date: 09-12-2019 Through 12-12-2019",
year = "2019",
month = dec,
doi = "10.1109/BigData47090.2019.9006049",
language = "English (US)",
series = "Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "105--114",
editor = "Chaitanya Baru and Jun Huan and Latifur Khan and Hu, {Xiaohua Tony} and Ronay Ak and Yuanyuan Tian and Roger Barga and Carlo Zaniolo and Kisung Lee and Ye, {Yanfang Fanny}",
booktitle = "Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019",
address = "United States",
}