[论文解读] Detecting Topic and Sentiment Dynamics Due to COVID-19 Pandemic Using Social Media

Hui Yin, Shuiqiao Yang+1 more|arXiv (Cornell University)|Jul 5, 2020

Misinformation and Its Impacts参考文献 25被引用 14

一句话总结

本研究提出了一种动态主题建模与情感分析框架，利用2020年4月期间的1300万条Twitter推文，追踪早期COVID-19大流行期间全球主题与情感的演变。通过结合动态主题模型（DTM）与VADER情感分析，研究发现尽管整体情感呈正面趋势，但与'居家隔离'相关的主题表现出强烈的正面情感，而'人员死亡'主题则持续呈现负面情感，凸显了主题层面的情感动态差异。

ABSTRACT

The outbreak of the novel Coronavirus Disease (COVID-19) has greatly influenced people's daily lives across the globe. Emergent measures and policies (e.g., lockdown, social distancing) have been taken by governments to combat this highly infectious disease. However, people's mental health is also at risk due to the long-time strict social isolation rules. Hence, monitoring people's mental health across various events and topics will be extremely necessary for policy makers to make the appropriate decisions. On the other hand, social media have been widely used as an outlet for people to publish and share their personal opinions and feelings. The large scale social media posts (e.g., tweets) provide an ideal data source to infer the mental health for people during this pandemic period. In this work, we propose a novel framework to analyze the topic and sentiment dynamics due to COVID-19 from the massive social media posts. Based on a collection of 13 million tweets related to COVID-19 over two weeks, we found that the positive sentiment shows higher ratio than the negative sentiment during the study period. When zooming into the topic-level analysis, we find that different aspects of COVID-19 have been constantly discussed and show comparable sentiment polarities. Some topics like ``stay safe home" are dominated with positive sentiment. The others such as ``people death" are consistently showing negative sentiment. Overall, the proposed framework shows insightful findings based on the analysis of the topic-level sentiment dynamics.

研究动机与目标

• 利用社交媒体数据实时监测与COVID-19大流行相关的主题与情感动态。
• 理解公众情感如何随不同疫情相关主题而演变。
• 通过识别公共卫生危机期间情绪化主题与情感转变，为政策制定者提供支持。
• 开发一种可扩展的框架，用于大规模社交媒体数据的动态主题与情感分析。

提出的方法

• 在2020年4月1日至4月14日期间，从Twitter收集了13,746,822条与COVID-19相关的推文。
• 应用动态主题模型（DTM）从推文语料中发现每日演变的主题。
• 使用VADER情感词典对推文及主题层面的情感极性进行分类。
• 按主题频率排序，并分析主要主题随时间的情感趋势。
• 利用时间序列图表与词云图可视化主题演变与情感动态。
• 评估不同主题聚类中的主题连贯性与情感分布。

实验结果

研究问题

• RQ1 在COVID-19大流行的早期阶段，公众情感如何动态演变？
• RQ2 哪些与COVID-19相关的主题在社交媒体上被最频繁讨论？
• RQ3 主题如何随疫情发展而随时间演变？
• RQ4 不同疫情相关主题的情感极性有何差异？

主要发现

• 在研究期间，1300万条推文的整体情感显示正面情感比例高于负面情感。
• 主题11（与'居家隔离'及自我隔离相关）始终表现出主导的正面情感，反映出公众对防护措施的支持。
• 主题49（与病例报告及官方数据相关）表现出主要负面情感，表明公众对病例数上升的焦虑情绪。
• 主题64（聚焦于COVID-19导致的死亡）持续保持高水平的负面情感，反映出公众对死亡率的沮丧或悲痛情绪。
• 排名前三的主题——11、49与64——在整个两周内始终位列每日讨论的前10名，表明公众关注持续存在。
• 尽管整体情感呈正面趋势，但情感在不同主题间存在显著差异，'人员死亡'与'病例报告'主题表现出强烈负面情感，而'居家隔离'则被广泛视为正面主题。