Nowadays, positioning technologies have become widely available providing then large datasets of individuals’ mobility data. Actually, annotating raw traces with contextual information brings semantics to them and then provides a better understanding of people behavior. To do so, literature work explored novel techniques to enrich raw mobility data with contextual information using either geographic context represented by landmarks/points of interest or widely used social media feeds. Accordingly, in this work, a novel approach integrating three data sources: raw mobility data, geographic information and social media feeds for a two-fold trajectory semantic annotation process is presented. In a first step, structured trajectories are constructed using geographic information. Later, the former are annotated by event-related words grasped from social media. Indeed, combining both data sources could result in a more complete annotation of trajectories. The proposed approach is experimented and evaluated on datasets of tourists in Kyoto. Results showed that the proposed approach quantitatively performed well compared to previous work in terms of precision of annotation words that maintained $\simeq 0.9$ when recall reached 50%, while improving its quality by consolidating both sources of semantics.

如今，定位技术已变得广泛可用，可提供个人移动性数据的大型数据集。实际上，用上下文信息注释原始痕迹会给它们带来语义，然后可以更好地理解人们的行为。为此，文献工作探索了新颖的技术，以使用由地标/兴趣点表示的地理环境或广泛使用的社交媒体供稿，通过上下文信息丰富原始流动性数据。因此，在这项工作中，提出了一种新颖的方法，该方法集成了两个数据源：原始移动性数据，地理信息和用于双向轨迹语义注释过程的社交媒体提要。第一步，使用地理信息构造结构化的轨迹。后来，前者由社交媒体掌握的与事件相关的词语注释。确实，将两个数据源组合在一起可以产生更完整的轨迹注释。在京都的游客数据集上对所提出的方法进行了实验和评估。结果表明，与以往的工作相比，所提出的方法在保持注释字词的准确性方面在数量上表现良好$\simeq 0。9$ 当召回率达到50％时，同时通过合并两个语义源来提高其质量。