Data-driven approaches to urban management and planning have attracted significant attention within interdisciplinary research spanning civil engineering and spatial data mining. Urban computing methods, particularly those leveraging graph representation learning techniques developed over the past decade, provide great potential in advancing urban management planning. In this paper, we adopt the perspective that cities can be effectively represented as network-structured graphs, wherein locations such as buildings and amenities are interconnected through road networks. These urban networks are further partitioned into subgraphs, and we introduce a novel model designed to learn effective representations of these subgraphs as distinct urban areas by utilizing heterogeneous graph neural networks. Specifically, our contributions include: firstly, developing a graph representation learning model that captures the geospatial characteristics of urban locations within dynamically-sized graphs; secondly, implementing an innovative graph pooling-based Graph Convolution Network; and finally, establishing a new benchmark for urban location representation learning tailored to urban management and planning tasks. Experimental results on various graph types demonstrate that our proposed model significantly outperforms existing methods in graph representation learning, particularly in applications involving urban location analysis for public safety and dense, heterogeneous social media networks.

The widespread dissemination of online misinformation poses significant threats to the public interest, highlighting the urgent need for effective fake news detection. In the era of Large Language Models (LLMs), the rise of AI-generated fake news has intensified this issue, making misinformation more pervasive and harder to control. While fact-checking offers a promising solution by leveraging external knowledge, efficiently linking claims within news articles to relevant external facts remains a significant challenge. To address this, we propose a mis-information detection framework FCRV (Full-Context Retrieval and Verification) that constructs a "full-context" for news articles by integrating LLM-based claim extraction with Retrieval-Augmented Generation (RAG) for fact-checking. We implemented an LLM pipeline for human-like extraction of key claims from datasets, significantly improving extraction quality over traditional methods. Our retrieval workflow effectively detects fictitious entities prevalent in AI-generated news by identifying claims lacking a basis in reality. Experiments across multiple human-generated and AI-generated datasets demonstrate that verifying news using this "full-context" approach leads to more stable and robust fake news detection, enhancing scalability, accuracy, and the model’s ability to handle AI-generated content.

Sentiment summary generation task is very valuable in social media, which can extract different aspects from people’s evaluation of products or services, such as the quality of products, and generate summarized opinionated sentiment summaries. And nowadays, sentiment summarization still suffers from insufficient contextual information capture and incorrect and comprehensive aspect extraction. In this paper, we propose a new strategy to solve the above problems: firstly, MILNET is used to automatically identify aspects related to a product or service from a large number of user reviews, and then the results are inputted into GCN, which is used to enhance the importance of contextual words close to the aspect; meanwhile, E-MABA is utilized for further optimization of the model on aspect extraction. By conducting a large number of experiments on the OPOSUM dataset and comparing the existing state-of-the-art methods, it is found that our method achieves better performance than other methods, proving the feasibility and effectiveness of our proposed strategy.

Large-scale Text-to-Image (T2I) models can generate high-quality images by controlling the synthesis based on textual prompts. However, concepts related to specific subjects are often challenging to accurately describe through text, leading to the model's inability to generate diverse images containing these specific concepts. Current methods exhibit shortcomings, including stringent requirements for input images, poor model generalization, uncontrollable image generation quality, lack of editing flexibility and unbalanced semantic consistency. In this paper, we propose a personalized generation method for targeted subject image editing, referred to as SSIE-Diffusion. We address these challenges by training an image encoder to invert original images into text embeddings, ensuring the controllability and accuracy of concept generation. To mitigate overfitting issues during training, we devise a mask loss. Additionally, building upon the T2I model, we propose fine-tuning the U-Net architecture in the model using a regularized dataset. This involves improving the projection matrices mapping to key and value features in the cross-attention layers, enhancing the visual fidelity of personalized images of the subject, and simultaneously addressing language drift issues to balance semantic consistency. Experimental results demonstrate the effectiveness of our proposed method in editing specific subjects within individual images, surpassing current SOTA methods. Across various scenarios, the generated images exhibit superior visual fidelity and editing flexibility, while maintaining high computational efficiency.

Forecasting citations of scientific patents and publications is a crucial task for understanding the evolution and development of technological domains and for foresight into emerging technologies. By construing citations as a time series, the task can be cast into the domain of temporal point processes. Most existing work on forecasting with temporal point processes, both conventional and neural network-based, only performs single-step forecasting. In citation forecasting, however, the more salient goal is n -step forecasting: predicting the arrival of the next n citations. In this article, we propose Dynamic Multi-Context Attention Networks (DMA-Nets), a novel deep learning sequence-to-sequence (Seq2Seq) model with a novel hierarchical dynamic attention mechanism for long-term citation forecasting. Extensive experiments on two real-world datasets demonstrate that the proposed model learns better representations of conditional dependencies over historical sequences compared to state-of-the-art counterparts and thus achieves significant performance for citation predictions.

Diverse efforts to combat the COVID-19 pandemic have continued throughout the past two years. Governments have announced plans for unprecedentedly rapid vaccine development, quarantine measures, and economic revitalization. They contribute to a more effective pandemic response by determining the precise opinions of individuals regarding these mitigation measures. In this paper, we propose a deep learning-based topic monitoring and storyline extraction system for COVID-19 that is capable of analyzing public sentiment and pandemic trends. The proposed method is able to retrieve Twitter data related to COVID-19 and conduct spatiotemporal analysis. Furthermore, a deep learning component of the system provides monitoring and modeling capabilities for topics based on advanced natural language processing models. A variety of visualization methods are applied to the project to show the distribution of each topic. Our proposed system accurately reflects how public reactions change over time along with pandemic topics.

Data-driven related solutions are dominating various scientific fields with the assistance of machine learning and data analytics. Finding effective solutions has long been discussed in the area of machine learning. The recent decade has witnessed the promising performance of the Physics-Informed Neural Networks (PINN) in bridging the gap between real-world scientific problems and machine learning models. In this paper, we explore the behavior of PINN in a particular range of different diffusion coefficients under specific boundary conditions. In addition, different initial conditions of partial differential equations are solved by applying the proposed PINN. Our paper illustrates how the effectiveness of the PINN can change under various scenarios. As a result, we demonstrate a better insight into the behaviors of the PINN and how to make the proposed method more robust while encountering different scientific and engineering problems.

For both investors and policymakers, forecasting the stock market is essential as it serves as an indicator of economic well-being. To this end, we harness the power of social media data, a rich source of public sentiment, to enhance the accuracy of stock market predictions. Diverging from conventional methods, we pioneer an approach that integrates sentiment analysis, macroeconomic indicators, search engine data, and historical prices within a multi-attention deep learning model, masterfully decoding the complex patterns inherent in the data. We showcase the state-of-the-art performance of our proposed model using a dataset, specifically curated by us, for predicting stock market movements and volatility.

The prompt estimation of traffic incident impacts (TIIs) plays a crucial role in guiding commuters’ trip planning and enhancing the decision-making resilience of transportation agencies. Despite the strong capability of spatiotemporal modeling, the gap between the TII prediction and the dynamic data mining approaches has not been seamlessly filled. (1) The TII evaluation metrics have never been well-defined, although many criteria for TII exist in research works. (2) Previous attempts heavily rely on predefined road network structures and underscore vital features, leading to inaccurate TII predictions. (3) Predicting the spatiotemporal TII using dynamic road networks is more challenging as it requires extracting both abnormal sub-graph and long-range dependencies due to the large variation of incident clearance time. This research proposes RoadFormer, a novel Road-Anchored Adversarial Dynamic Graph Transformer, for predicting unlimited-range spatiotemporal TIIs. (1) We introduce novel criteria for assessing spatiotemporal TIIs and construct two new benchmark datasets to validate the performance of our methods. (2) RoadFormer leverages a road-anchored spatial transformer and an importance-score temporal transformer to form an encoder-decoder framework. The road-anchored spatial transformer prunes unnecessary edges between nodes with a road-anchored cascade attention mechanism, accurately pinpointing the affected sub-graphs. (3) The importance-score temporal transformer highlights abnormal changes in node features with a score-based adversarial training mechanism, enabling predictions to rely on informative feature changes after the accident occurrence. Extensive experiments on real-world datasets demonstrate that RoadFormer outperforms the state-of the-art methods, especially in capturing spatiotemporal dependency patterns and predicting unlimited-range spatiotemporal TIIs.

Predicting stock market is vital for investors and policymakers, acting as a barometer of the economic health. We leverage social media data, a potent source of public sentiment, in tandem with macroeconomic indicators as government-compiled statistics, to refine stock market predictions. However, prior research using tweet data for stock market prediction faces three challenges. First, the quality of tweets varies widely. While many are filled with noise and irrelevant details, only a few genuinely mirror the actual market scenario. Second, solely focusing on the historical data of a particular stock without considering its sector can lead to oversight. Stocks within the same industry often exhibit correlated price behaviors. Lastly, simply forecasting the direction of price movement without assessing its magnitude is of limited value, as the extent of the rise or fall truly determines profitability. In this paper, diverging from the conventional methods, we pioneer an ECON (A Framework Leveraging Tweets, Macroeconomic Indicators, and Historical Prices to Predict Stock Movement and Volatility). The framework has following advantages: First, ECON has an adept tweets filter that efficiently extracts and decodes the vast array of tweet data. Second, ECON discerns multi-level relationships among stocks, sectors, and macroeconomic factors through a self-aware mechanism in semantic space. Third, ECON offers enhanced accuracy in predicting substantial stock price fluctuations by capitalizing on stock price movement. We showcase the state-of-the-art performance of our proposed model using a dataset, specifically curated by us, for predicting stock market movements and volatility.

Predicting and quantifying the impact of traffic accidents is necessary and critical to Intelligent Transport Systems (ITS). As a state-of-the-art technique in graph learning, current graph neural networks heavily rely on graph Fourier transform, assuming homophily among the neighborhood. However, the homophily assumption makes it challenging to characterize abrupt signals such as traffic accidents. Our paper proposes an abrupt graph wavelet network (AGWN) to model traffic accidents and predict their time durations using only one single snapshot.

Chinese characters have semantic-rich compositional information in radical form. While almost all previous research has applied CNNs to extract this compositional information, our work utilizes deep graph learning on a compact, graph-based representation of Chinese characters. This allows us to exploit temporal information within the strict stroke order used in writing characters. Our results show that our stroke-based model has potential for helping large-scale language models on some Chinese natural language understanding tasks. In particular, we demonstrate that our graph model produces more interpretable embeddings shown through word subtraction analogies and character embedding visualizations.

Influence blocking maximization (IBM) is crucial in many critical real-world problems such as rumors prevention and epidemic containment. The existing work suffers from: (1) concentrating on uniform costs at the individual level, (2) mostly utilizing greedy approaches to approximate optimization, (3) lacking a proper graph representation for influence estimates. To address these issues, this research introduces a neural network model dubbed Neural Influence Blocking (\algo) for improved approximation and enhanced influence blocking effectiveness. The code is available at https://github.com/oates9895/NIB.

Predicting and measuring the impact of traffic collisions is crucial for Intelligent Transportation Systems (ITS). Numerous works in this field have successfully applied graph neural networks to ITS. Existing research on graph neural networks mainly relies on the graph Fourier transform, assuming neighborhood homophily. The homophily assumption, on the other hand, makes it difficult to define abrupt signals such as traffic accidents. Our research proposes an abrupt graph wavelet network (AGWN) for forecasting the durations of traffic incidents using a single shot. To begin, graph wavelet (GW) is theoretically examined in terms of linear separability in comparison to graph Fourier (GF), demonstrating its advantage in modeling abrupt graph signals. Sensitivity analysis and admissibility conditions are utilized to further study the behavior of GW in abrupt graph signals, justifying the use of zero sum function as wavelet kernel. The synthetic data results support our proposed wavelet kernel's effectiveness in modeling a variety of abrupt signals, while real-world trials demonstrate that our method significantly outperforms baseline models in forecasting the duration of an accident impact.

Predicting the impact of traffic i ncidents b ased on traffic s ensor d ata i s a n e ssential r esearch t opic i n t he fi eld of Intelligent Transportation Systems (ITS). Tackling the problem of estimating the durations of incidents from their early stages is a challenge due to the variable nature of such incidents and the complex structure of modern road networks. Existing studies on forecasting the incident duration from sensor data are mostly incapable of modeling 1) the spatiotemporal correlations of traffic s ensors a nd a rterial r oads a nd 2 ) t he hierarchical topology of the traffic sensor and road networks. In this paper, we propose the Hierarchical Attention-based Spatiotemporal Graph Convolutional Network model (HastGCN) to solve the incident duration forecasting problem by formulating the spatiotemporal correlation and traffic p atterns o n b oth t he s ensor l evel and the road level in their natural hierarchical manner. At the sensor level, we propose a spatiotemporal attention mechanism followed by graph convolutions to model the local correlations and patterns between traffic s ensors o n t he s ame a rterial road. At the road level, a connectivity-aware attention mechanism is designed to learn the global spatial relatedness between each arterial road. Traffic-condition a ware g raph c onvolutions are then applied to understand the target incident representation for the incident duration forecasting.

Open and accessible public utilities such as mass public transit systems are some of the vexing venues that are vulnerable to several criminal acts due to the large volumes of commuters. Existing forms of threat or event detection for the rail-based transit systems are either not working in real-time or do not provide complete coverage. In this paper, we present RISECURE1, an open-source system, that uses real-time social media mining to aid in the early detection of such possible events within a rail-based/metro system. The system leverages dynamic query expansion to keep track of any new emerging information about any particular incident. The Real Time Incident panel of the proposed system provides a comprehensible representation of the evolution of threatening transit events, which are further shown in the storyline modal for each respective station. The alert notification module of the system is capable of monitoring threats to the rail-based/metro systems in real-time. We demonstrate the system by including case studies involving incidents occurring within the Washington DC Metropolitan Area Transit Authority (WMATA) metro system to justify the effectiveness of our approach.

Amidst the COVID-19 pandemic, cyberbullying has become an even more serious threat. Our work aims to investigate the viability of an automatic multiclass cyberbullying detection model that is able to classify whether a cyberbully is targeting a victim's age, ethnicity, gender, religion, or other quality. Previous literature has not yet explored making fine-grained cyberbullying classifications o f s uch m agnitude, a nd existing cyberbullying datasets suffer from quite severe class imbalances. To combat these challenges, we establish a framework for the automatic generation of balanced data by using a semi-supervised online Dynamic Query Expansion (DQE) process to extract more natural data points of a specific class from Twitter. W e also propose a Graph Convolutional Network (GCN) classifier, using a graph constructed from the thresholded cosine similarities between tweet embeddings. With our DQE-augmented dataset, which we have made publicly available, we compare our GCN model using eight different tweet embedding methods and six other classification models over two sizes of datasets. Our results show that our proposed GCN model matches or exceeds the performance of the baseline models, as indicated by McNemar statistical tests.

Cybersecurity event detection is a crucial problem for mitigating effects on various aspects of society. Social media has become a notable source of indicators for detection of diverse events. Though previous social media based strategies for cyber-security event detection focus on mining certain event-related words, the dynamic and evolving nature of online discourse limits the performance of these approaches. Further, because these are typically unsupervised or weakly supervised learning strategies, they do not perform well in an environment of biased samples, noisy context, and informal language which is routine for online, user-generated content. This paper takes a supervised learning approach by proposing a novel multi-task learning based model. Our model can handle diverse structures in feature space by learning models for different types of potential high-profile targets simultaneously. For parameter optimization, we develop an efficient algorithm based on the alternating direction method of multipliers. Through extensive experiments on a real world Twitter dataset, we demonstrate that our approach consistently outperforms existing methods at encoding and identifying cyber-security incidents.

Critical incident stages identification and reasonable prediction of traffic incident duration are essential in traffic incident management. In this paper, we propose a traffic incident duration prediction model that simultaneously predicts the impact of the traffic incidents and identifies the critical groups of temporal features via a multi-task learning framework. First, we formulate a sparsity optimization problem that extracts low-level temporal features based on traffic speed readings and then generalizes higher level features as phases of traffic incidents. Second, we propose novel constraints on feature similarity exploiting prior knowledge about the spatial connectivity of the road network to predict the incident duration. The proposed problem is challenging to solve due to the orthogonality constraints, non-convexity objective, and non-smoothness penalties. We develop an algorithm based on the alternating direction method of multipliers (ADMM) framework to solve the proposed formulation. Extensive experiments and comparisons to other models on real-world traffic data and traffic incident records justify the efficacy of our model.

Modeling and forecasting forward citations to a patent is a central task for the discovery of emerging technologies and for measuring the pulse of inventive progress. Conventional methods for forecasting these forward citations cast the problem as analysis of temporal point processes which rely on the conditional intensity of previously received citations. Recent approaches model the conditional intensity as a chain of recurrent neural networks to capture memory dependency in hopes of reducing the restrictions of the parametric form of the intensity function. For the problem of patent citations, we observe that forecasting a patent's chain of citations benefits from not only the patent's history itself but also from the historical citations of assignees and inventors associated with that patent. In this paper, we propose a sequence-to-sequence model which employs an attention-of-attention mechanism to capture the dependencies of these multiple time sequences. Furthermore, the proposed model is able to forecast both the timestamp and the category of a patent's next citation. Extensive experiments on a large patent citation dataset collected from USPTO demonstrate that the proposed model outperforms state-of-the-art models at forward citation forecasting.

With the rapid growth in urban transit networks in recent years, detecting service disruptions in a timely manner is a problem of increased interest to service providers. Transit agencies are seeking to move beyond traditional customer questionnaires and manual service inspections to leveraging open source indicators like social media for deteting emerging transit events. In this paper, we leverage Twitter data for early detection of metro service disruptions. Inspired by the multi-task learning framework, we propose the Metro Disruption Detection Model, which captures the semantic similarity between transit lines in Twitter space. We propose novel constraints on feature semantic similarity exploiting prior knowledge about the spatial connectivity and shared tracks of the metro network. An algorithm based on the alternating direction method of multipliers (ADMM) framework is developed to solve the proposed model. We run extensive experiments and comparisons to other models with real world Twitter data and transit disruption records from the Washington Metropolitan Area Transit Authority (WMATA) to justify the efficacy of our model.

One can infer from the broken window theory that the perception of a city street's safety level relies significantly on the visual appearance of the street. Previous works have addressed the feasibility of using computer vision algorithms to classify urban scenes. Most of the existing urban perception predictions focus on binary outcomes such as safe or dangerous, wealthy or poor. However, binary predictions are not representative and cannot provide informative inferences such as the potential crime types in certain areas. In this paper, we explore the connection between urban perception and crime inferences. We propose a convolutional neural network (CNN) - StreetNet to learn crime rankings from street view images. The learning process is formulated on the basis of preference learning and label ranking settings. We design a street view images retrieval algorithm to improve the representation of urban perception. A data-driven, spatiotemporal algorithm is proposed to find unbiased label mappings between the street view images and the crime ranking records. Extensive evaluations conducted on images from different cities and comparisons with baselines demonstrate the effectiveness of our proposed method.

Traditional statistical analysis on speed, volume, and occupancy has dominated the field of Arterial Incident Management Study (AIMS). However, few previous works have focused on investigating into the causality of the incidents. In this paper, we present ButterFly, a social media based arterial incident detection and analysis system. The proposed system is dedicated to identify the traffic incident from a novel perspective and discover causalities between traffic incidents. The main functionalities of the proposed system include: 1) Traffic incident detection based on userinput social media contents, 2) Transportation incidents storyline generation, and 3) Traffic incidents causalities analysis and visualization. We demonstrate the system by considering the Washington DC area as our experimental environment. ButterFly is targeted to provide effective and convenient real-time and historical traffic incidents analysis interfaces for transportation management agencies and academies. Our proposed system, integrated with multiple social media resources, can greatly broaden the visions for traffic incidents analysis.

This paper presents TREADS, a novel travel route recommendation system that suggests safe travel itineraries in real time by incorporating social media data resources and points of interest review summarization techniques. The system consists of an efficient route recommendation service that considers safety and user interest factors, a transportation related tweets retriever with high accuracy, and a novel text summarization module that provides summaries of location based Twitter data and Yelp reviews to enhance our route recommendation service. We demonstrate the system by utilizing crime and points of interest data in the Washington DC area. TREADS is targeted to provide safe, effective, and convenient travel strategies for commuters and tourists. Our proposed system, integrated with multiple social media resources, can greatly improve the travel experience for tourists in unfamiliar cities.

As a form of social media, Twitter records real life events in our cities as they happen. Huge numbers of tweets under the heading of transportation or metro are published every day. This paper presents an application for Traffic Events Detection and Summary (TEDS) based on mining representative terms from the tweets posted when anomalies occur. The proposed ensemble application contains an efficient TEDS search engine with multiple indexing, ranking, and scoring schemes. Spatio-temporal analysis and a novel wavelet analysis model are applied for traffic event detection. This application could benefit both drivers and transportation authorities. Users can search transportation status and analyze traffic events in specific locations of interest. Utilizing the proposed signal processing technology, we demonstrate the system's effectiveness by examining traffic and metro travel in the Washington D.C. area. As the collaboration between a citizen's life and social media becomes ever greater, this could have a significant impact on the prediction of traffic flow, travel selection, and other city computing functions.