A recent surge of users migrating from Twitter to alternative platforms, such as Mastodon, raised questions regarding what migration patterns are, how different platforms impact user behaviors, and how migrated users settle in the migration process. In this study, we elaborate on how we investigate these questions by collecting data over 10,000 users who migrated from Twitter to Mastodon within the first ten weeks following the ownership change of Twitter. Our research is structured in three primary steps. First, we develop algorithms to extract and analyze migration patterns. Second, by leveraging behavioral analysis, we examine the distinct architectures of Twitter and Mastodon to learn how user behaviors correspond with the characteristics of each platform. Last, we determine how particular behavioral factors influence users to stay on Mastodon. We share our findings of user migration, insights, and lessons learned from the user behavior study.

We propose a simple yet effective solution to tackle the often-competing goals of fairness and utility in classification tasks. While fairness ensures that the model's predictions are unbiased and do not discriminate against any particular group or individual, utility focuses on maximizing the model's predictive performance. This work introduces the idea of leveraging aleatoric uncertainty (e.g., data ambiguity) to improve the fairness-utility trade-off. Our central hypothesis is that aleatoric uncertainty is a key factor for algorithmic fairness and samples with low aleatoric uncertainty are modeled more accurately and fairly than those with high aleatoric uncertainty. We then propose a principled model to improve fairness when aleatoric uncertainty is high and improve utility elsewhere. Our approach first intervenes in the data distribution to better decouple aleatoric uncertainty and epistemic uncertainty. It then introduces a fairness-utility bi-objective loss defined based on the estimated aleatoric uncertainty. Our approach is theoretically guaranteed to improve the fairness-utility trade-off. Experimental results on both tabular and image datasets show that the proposed approach outperforms state-of-the-art methods w.r.t. the fairness-utility trade-off and w.r.t. both group and individual fairness metrics. This work presents a fresh perspective on the trade-off between utility and algorithmic fairness and opens a key avenue for the potential of using prediction uncertainty in fair machine learning.

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these algorithms ineffective. Prior solutions to the OOD challenge seek to identify invariant features across different training domains. The underlying assumption is that these invariant features should also work reasonably well in the unlabeled target domain. By contrast, this work is interested in the domain-specific features that include both invariant features and features unique to the target domain. We propose a simple yet effective approach that relies on correlations in general regardless of whether the features are invariant or not. Our approach uses the most confidently predicted samples identified by an OOD base model (teacher model) to train a new model (student model) that effectively adapts to the target domain. Empirical evaluations on benchmark datasets show that the performance is improved over the SOTA by ∼10-20%.

Visualizing data on maps is deemed a powerful tool for data scientists to make sense of geospatial data. The geospatial map visualization (abbr. MapViz) process first loads the designated geospatial data, processes the data and then applies the map visualization effect. Guaranteeing detailed and accurate geospatial MapViz (e.g., at multiple zoom levels) requires extremely high-resolution maps. Classic solutions suffer from limited computation resources while scalable MapViz system architectures are not able to co-optimize the data management and visualization phases in the same system. This paper demonstrates GeoSparkViz, a full-fledged system that allows the user to load, prepare, integrate and execute MapViz tasks in the same system. For demonstration purpose, we implemented a web interface using a node.js web server, Baidu echarts library, and MapBox on top of GeoSparkViz to visually explore patterns in the New York City Taxi Trips dataset. The demonstration scenarios show how the data preparation and map visualization phases are combined in GeoSparkViz.

When a data scientist analyzes mobility data (e.g., using a data visualization tool), she may find out some interesting facts in the dataset. An example of a fact can be: "The number of Taxi trips in NYC on January 23, 2016, dropped drastically as compared to other days of the same month". However, the data scientist may be left clueless if they cannot find a crisp explanation to such a fact. Furthermore, the tedious task of finding an explanation by manually scraping the data becomes even impossible with big data. Existing techniques are designed for non-spatial data which cannot be applied to spatial data because it does not consider the spatial proximity. In this paper, we propose an automatic framework which guides the data scientist to explain the fact discovered from mobility data. Our approach expands on the aggravation and intervention techniques while using spatial partitioning/clustering to improve explanations for spatial data. Experiments show that the proposed approach outperforms the state-of-the-art approaches in finding the explanation for facts extracted from NYC taxi real mobility dataset.