In this paper, a probabilistic topic modeling algorithm called Latent Dirichlet Allocation (LDA) is implemented to infer trip purposes from activity attributes revealed from smart card transit data in an unsupervised manner. While most literature focused on finding patterns for home and work activities, we further investigated non-home and non-work-related activities to detect patterns associated with them. Temporal attributes of activities are extracted from trip information recorded by Tehran subway’s automatic fare collection system. In addition, land-use data is also incorporated to further enhance spatial attributes for non-home/work activities. Various activity attributes such as start time, duration, and frequency in addition to land-use data are used to infer the activity purposes and patterns. We identified 14 different patterns related to non-commuting activities on the basis of both their temporal and spatial attributes including educational, recreational, commercial, and health and other service-related activity types. We investigated passengers’ activity pattern and behavior changes before and during COVID-19 pandemic by comparing the discovered patterns. For recreational patterns it is revealed that not only has the number of recreational patterns dropped, but also the duration of recreational activities decreased. Morning patterns of educational activities have also been eliminated and number of commercial activities was decreased during COVID-19. The proposed model demonstrates the ability to capture travel behavior changes for different disruptions using smart card transit data without performing costly and time consuming manual surveys which can be useful for authorties and decision makers.

中文翻译：

---

揭示家庭/工作活动之外的出行模式：使用交通智能卡和土地利用数据的主题建模方法


在本文中，实现了一种称为潜在狄利克雷分配 （LDA） 的概率主题建模算法，以无监督的方式从智能卡传输数据中揭示的活动属性中推断出行目的。虽然大多数文献都集中在寻找家庭和工作活动的模式上，但我们进一步调查了非家庭和非工作相关活动，以检测与它们相关的模式。活动的时态属性是从德黑兰地铁自动收费系统记录的行程信息中提取的。此外，还纳入了土地利用数据，以进一步增强非家庭/工作活动的空间属性。除了土地利用数据外，还使用各种活动属性（例如开始时间、持续时间和频率）来推断活动目的和模式。我们根据非通勤活动的时间和空间属性确定了 14 种不同的模式，包括教育、娱乐、商业和健康以及其他与服务相关的活动类型。我们通过比较发现的模式，调查了乘客在 COVID-19 大流行之前和期间的活动模式和行为变化。对于娱乐模式，不仅娱乐模式的数量下降了，而且娱乐活动的持续时间也减少了。在 COVID-19 期间，早上的教育活动模式也被取消，商业活动的数量也减少了。所提出的模型展示了使用智能卡交通数据捕获不同中断的出行行为变化的能力，而无需执行昂贵且耗时的手动调查，这对作者和决策者非常有用。