arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.16082cs.CLcs.AI
收藏

EnrichEvent:利用上下文信息丰富社会数据以提取新兴事件

EnrichEvent: Enriching Social Data with Contextual Information for Emerging Event Extraction

Department of Mathematics and Computer Science, Amirkabir University of Technology(数学与计算机科学系,阿米尔卡比尔技术大学)

Mohammadali Sefidi Esfahani, Mohammad Akbari

AI总结:

提出端到端 EnrichEvent 框架,融合词汇、结构与上下文知识识别流式社会数据中的未知新兴事件,提升检测效果并降低最高50%运行时间。

摘要:

社交平台已成为传播信息和讨论社会事件的关键平台,为研究人员设计和实现新型事件检测框架提供了绝佳机会。识别未明确说明的事件并在没有先验知识的情况下检测事件,使政府、援助机构和专家能够通过评估严重程度和优化援助交付,对自然灾害等正在发展的局势作出迅速而有效的反应。社会数据具有拼写错误、不完整、词义歧义和语言不规范等特点。在讨论正在发生的事件时,用户会根据其先前经验、背景和知识分享不同的意见和观点。先前的工作主要利用推文的词汇和结构模式来捕捉用户对事件的意见和看法。在本研究中,我们提出了一个名为 EnrichEvent 的新型端到端框架,用于从流式社会数据中识别未明确说明的事件。除词汇和结构模式外,我们还利用推文的上下文知识来丰富其表示,并更好地理解用户对事件的看法。与基线相比,EnrichEvent 框架在 Consolidation outcome 上取得最高值,平均为87%,而基线为67%;在 Discrimination outcome 上取得最低值,平均为10%,而基线为16%。此外,EnrichEvent 框架中的 Trending Data Extraction 模块通过识别并丢弃消息块内的无关推文,将 Runtime 最多降低50%,从而提高了效率,使该框架在处理流式数据时具有高度可扩展性。我们的源代码和数据集可在官方复制包中获取。

英文摘要:

Social platforms have emerged as crucial platforms for distributing information and discussing social events, offering researchers an excellent opportunity to design and implement novel event detection frameworks. Identifying unspecified events and detecting events without prior knowledge enables governments, aid agencies, and experts to respond swiftly and effectively to unfolding situations, such as natural disasters, by assessing severity and optimizing aid delivery. Social data is characterized by misspellings, incompleteness, word sense ambiguation, and irregular language. While discussing an ongoing event, users share different opinions and perspectives based on their prior experience, background, and knowledge. Prior works primarily leverage tweets' lexical and structural patterns to capture users' opinions and views about events. In this study, we propose an end-to-end novel framework, EnrichEvent, to identify unspecified events from streaming social data. In addition to lexical and structural patterns, we leverage contextual knowledge of the tweets to enrich their representation and gain a better perspective on users' opinions about events. Compared to our baselines, the EnrichEvent framework achieves the highest values for Consolidation outcome with an average of 87% vs. 67% and the lowest for Discrimination outcome with an average of 10% vs. 16%. Moreover, the Trending Data Extraction module in the EnrichEvent framework improves efficiency by reducing Runtime by up to 50% by identifying and discarding irrelevant tweets within message blocks, making the framework highly scalable for processing streaming data. Our source code and dataset are available in our official replication package.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑