分析俄乌战争推文，区分真实开源情报与虚假信息。
OSINT or BULLSHINT? Exploring Open-Source Intelligence tweets about the Russo-Ukrainian War
- 通过情感、立场和实体识别分析近200万条推文
- 发现负面情绪主导，亲乌亲俄立场交织且存在信息操纵
- 识别出不同立场与话题的传播社群，揭示虚假信息策略
本文研究了社交媒体平台Twitter上关于俄乌战争的开源情报（OSINT）现象，区分真实OSINT与伪装成情报的虚假信息（称作“BULLSHINT”）。基于2022年1月至2023年7月期间约1,040名用户的近200万条推文数据，采用情感分析、立场检测、虚假信息识别及命名实体识别（NER）技术，揭示了该社群的传播模式与信息扩散策略。研究发现，战事事件显著影响情绪基调，呈现复杂的亲乌与亲俄立场分布，并存在潜在的信息操控行为。进一步运用社区检测方法，识别出由立场、话题和虚假信息构成的不同传播集群，凸显社交媒体上信息传播的复杂动态。本研究为数字战与虚假信息机制提供了新理解，有助于认识全球地缘冲突中开源情报的实际运作。
原文摘要 · Abstract (English)
This paper examines the role of Open Source Intelligence (OSINT) on Twitter regarding the Russo-Ukrainian war, distinguishing between genuine OSINT and deceptive misinformation efforts, termed "BULLSHINT." Utilizing a dataset spanning from January 2022 to July 2023, we analyze nearly 2 million tweets from approximately 1,040 users involved in discussing real-time military engagements, strategic analyses, and misinformation related to the conflict. Using sentiment analysis, partisanship detection, misinformation identification, and Named Entity Recognition (NER), we uncover communicative patterns and dissemination strategies within the OSINT community. Significant findings reveal a predominant negative sentiment influenced by war events, a nuanced distribution of pro-Ukrainian and pro-Russian partisanship, and the potential strategic manipulation of information. Additionally, we apply community detection techniques, which are able to identify distinct clusters partisanship, topics, and misinformation, highlighting the complex dynamics of information spread on social media. This research contributes to the understanding of digital warfare and misinformation dynamics, offering insights into the operationalization of OSINT in geopolitical conflicts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。