Search

Abstract: There is a family of well-known external clustering validity indexes to measure the degree of compatibility or similarity between two hard partitions of a given data set, including partitions with different numbers of categories. A unified, fully equivalent set-theoretic formulation for an important class of such indexes was derived and extended to the fuzzy domain in a previous work by the author [Campello, R.J.G.B., 2007. A fuzzy extension of the Rand index and other related indexes for clustering and classification assessment. Pattern Recognition Lett., 28, 833–841]. However, the proposed fuzzy set-theoretic formulation is not valid as a general approach for comparing two fuzzy partitions of data. Instead, it is an approach for comparing a fuzzy partition against a hard referential partition of the data into mutually disjoint categories. In this paper, generalized external indexes for comparing two data partitions with overlapping categories are introduced. These indexes can be used as general measures for comparing two partitions of the same data set into overlapping categories. An important issue that is seldom touched in the literature is also addressed in the paper, namely, how to compare two partitions of different subsamples of data. A number of pedagogical examples and three simulation experiments are presented and analyzed in details. A review of recent related work compiled from the literature is also provided. [Copyright &y& Elsevier]

This paper is concerned with both the problems of quantitative and qualitative modelling of complex systems by using fuzzy techniques. A unified approach for the identification and subsequent extraction of linguistic knowledge of systems using fuzzy relational models is addressed. This approach deals with the identification problem by means of optimal numerical solutions based on weighted least squares and quadratic programming formulations. The linguistic knowledge is extracted in the form of consistent fuzzy rules that describe linguistically the behaviour of the identified system. A new methodology for the simplification of the extracted rules is derived by using a pruning criterion based on the representability matrix concept introduced in previous work. Several numerical aspects concerning the proposed optimization schemes and a covering discussion about the linguistic interpretation of the resulting models are also included together with illustrative examples in the contexts of pattern classification and dynamic systems identification. The paper also provides an overview of fuzzy modelling techniques that intends to situate the relational models among other fuzzy model architectures typically adopted in the literature, highlighting their main advantages and drawbacks. [ABSTRACT FROM AUTHOR]

The impact of sporting events on local economies and their spatial distribution is a topic of active policy debate. This study adds to the discussion by examining granular cellphone location data to assess the spillover effects of Major League Baseball (MLB) games in a major US city. Focusing on the 2019 season, we explore granular geospatial patterns in mobility and consumer spending on game days versus non-game days in the Saint Louis region. Through density-based clustering and hotspot analysis, we uncover distinct spatiotemporal signatures and variations in visitor affluence across different teams. This study uses features like game day characteristics, location data (latitude and longitude), business types, and spending data. A significant finding is that specific spatial clusters of economic activity are formed around the stadium, particularly on game days, with multiple clusters identified. These clusters reveal a marked increase in spending at businesses such as restaurants, bars, and liquor stores, with revenue surges of up to 38% in certain areas. We identified a significant change in spending patterns in the local economy during games, with results varying greatly across teams. Notably, the XGBoost model performs best, achieving a test R2 of 0.80. The framework presented enhances the literature at the intersection of urban economics, sports analytics, and spatial modeling while providing data-driven actionable insights for businesses and policymakers. [ABSTRACT FROM AUTHOR]

One-shot devices are products that can only be used once. Typical one-shot devices include airbags, fire extinguishers, inflatable life vests, ammo, and handheld flares. Most of them are life-saving products and should be highly reliable in an emergency. Quality control of those productions and predicting their reliabilities over time is critically important. To assess the reliability of the products, manufacturers usually test them in controlled conditions rather than user conditions. We may rely on public datasets that reflect their reliability in actual use, but the datasets often come with missing observations. The experimenter may lose information on covariate readings due to human errors. Traditional missing-data-handling methods may not work well in handling one-shot device data as they only contain their survival statuses. In this research, we propose Multiple Imputation with Unsupervised Learning (MIUL) to impute the missing data using Hierarchical Clustering, k-prototype, and density-based spatial clustering of applications with noise (DBSCAN). Our simulation study shows that MIUL algorithms have superior performance. We also illustrate the method using datasets from the Crash Report Sampling System (CRSS) of the National Highway Traffic Safety Administration (NHTSA). [ABSTRACT FROM AUTHOR]

This study addresses the challenges of maritime traffic management in the western waters of Taiwan, a region characterized by substantial commercial shipping activity and ongoing environmental development. Using 2023 Automatic Identification System (AIS) data, this study develops a robust feature extraction framework involving data cleaning, anomaly trajectory point detection, trajectory compression, and advanced processing techniques. Dynamic Time Warping (DTW) and the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) algorithms are applied to cluster the trajectory data, revealing 16 distinct maritime traffic patterns, key navigation routes, and intersections. The findings provide fresh perspectives on analyzing maritime traffic, identifying high-risk areas, and informing safety and spatial planning. In practical applications, the results help navigators optimize route planning, improve resource allocation for maritime authorities, and inform the development of infrastructure and navigational aids. Furthermore, these outcomes are essential for detecting abnormal ship behavior, and they highlight the potential of route extraction in maritime surveillance. [ABSTRACT FROM AUTHOR]

Innovative Industrial Clusters (IIC), characterized by geographical aggregation and technological collaboration among technology enterprises and institutions, serve as pivotal drivers of regional economic competitiveness and technological advancements. Prior research on cluster identification, crucial for IIC analysis, has predominantly emphasized geographical dimensions while overlooking technological proximity. Addressing these limitations, this study introduces a comprehensive framework incorporating multiple indices and methods for accurately identifying IIC using patent data. To unearth latent technological insights within patent documents, Latent Dirichlet Allocation (LDA) is employed to generate topics from a collection of terms. Utilizing the applicants' names and addresses recorded in patents, an Application Programming Interface (API) map systems facilitates the extraction of geographic locations. Subsequently, a Multivariate Density-Based Spatial Clustering of Applications with Noise (MDBSCAN) algorithm, which accounts for both technological and spatial distances, is deployed to delineate IIC. Moreover, a bipartite network model based on patent geographic information collected from the patent is constructed to analyze the technological distribution on the geography and development mode of IIC. The utilization of the model and methodologies is demonstrated through a case study on the China flexible electronics industry (FEI). The findings reveal that the clusters identified via this novel approach are significantly correlated with both technological innovation and geographical factors. Moreover, the MDBSCAN algorithm demonstrates notable superiority over other algorithms in terms of computational precision and efficiency, as evidenced by the case analysis. [ABSTRACT FROM AUTHOR]

The task of finding natural groupings within a dataset exploiting proximity of samples is known as clustering, an unsupervised learning approach. Density-based clustering algorithms, which identify arbitrarily shaped clusters using spatial dimensions and neighbourhood aspects, are sensitive to the selection of parameters. For instance, DENsity CLUstEring (DENCLUE)—a density-based clustering algorithm—requires a trial-and-error approach to find suitable parameters for optimal clusters. Earlier attempts to automate the parameter estimation of DENCLUE have been highly dependent either on the choice of prior data distribution (which could vary across datasets) or by fixing one parameter (which might not be optimal) and learning other parameters. This article addresses this challenge by learning the parameters of DENCLUE through the differential evolution optimisation technique without prior data distribution assumptions. Experimental evaluation of the proposed approach demonstrated consistent performance across datasets (synthetic and real datasets) containing clusters of arbitrary shapes. The clustering performance was evaluated using clustering validation metrics (e.g., Silhouette Score, Davies–Bouldin Index and Adjusted Rand Index) as well as qualitative visual analysis when compared with other density-based clustering algorithms, such as DPC, which is based on weighted local density sequences and nearest neighbour assignments (DPCSA) and Variable KDE-based DENCLUE (VDENCLUE). [ABSTRACT FROM AUTHOR]

This study utilizes machine learning to quantify CO2 plume extents by analyzing microseismic data from the Illinois Basin Decatur Project (IBDP). Leveraging a unique dataset of well logs, microseismic records, and CO2 injection metrics, this work aims to predict the temporal evolution of subsurface CO2 saturation plumes. The findings illustrate that machine learning can predict plume dynamics, revealing vertical clustering of microseismic events over distinct time periods within certain proximities to the injection well, consistent with an invasion percolation model. The buoyant CO2 plume partially trapped within sandstone intervals periodically breaches localized barriers or baffles, which act as leaky seals and impede vertical migration until buoyancy overcomes gravity and capillary forces, leading to breakthroughs along vertical zones of weakness. Between different unsupervised clustering techniques, K-Means and DBSCAN were applied and analyzed in detail, where K-means outperformed DBSCAN in this specific study by indicating the combination of the highest Silhouette Score and the lowest Davies–Bouldin Index. The predictive capability of machine learning models in quantifying CO2 saturation plume extension is significant for real-time monitoring and management of CO2 sequestration sites. The models exhibit high accuracy, validated against physical models and injection data from the IBDP, reinforcing the viability of CO2 geological sequestration as a climate change mitigation strategy and enhancing advanced tools for safe management of these operations. [ABSTRACT FROM AUTHOR]

Co-resident attacks are serious security threats in multi-tenant public cloud platforms. They are often implemented by building side channels between virtual machines (VMs) hosted on the same cloud server. Traditional defense methods are troubled by the deployment cost. The existing tenant classification methods can hardly cope with the real dataset that is quite large and extremely unevenly distributed, and may have problems in the processing speed considering the computation complexity of the DBSCAN algorithm. In this paper, we propose a novel co-resident attack defense strategy which solve these problems through an improved and efficient multi-level clustering algorithm and semi-supervised classification method. We propose a novel multi-level clustering algorithm which can efficiently reduce the complexity, since only a few parameter adjustments are required. Built on the proposed clustering algorithm, a semi-supervised classification model is designed. The experimental results of the classification effect and training speed show that our model achieves F-scores of over 85% and is significantly faster than traditional SVM classification methods. Based on the classification of unlabeled tenants into different security groups, the cloud service provider may modify the VM placement policy to achieve physical isolation among different groups, reducing the co-residency probability between attackers and target tenants. Experiments are conducted on a large-scale dataset collected from Azure Cloud Platform. The results show that the proposed model achieves 97.86% accuracy and an average 96.06% F-score, proving the effectiveness and feasibility of the proposed defense strategy. [ABSTRACT FROM AUTHOR]

Accurate livestock counts are essential for effective pastureland management. High spatial resolution remote sensing, coupled with deep learning, has shown promising results in livestock detection. However, challenges persist, particularly when the targets are small and in a heterogeneous environment, such as those in African rangelands. This study evaluated nine state-of-the-art object detection models, four variants each from YOLOv5 and YOLOv8, and Faster R-CNN, for detecting cattle in 10 cm resolution aerial RGB imagery in Kenya. The experiment involved 1039 images with 9641 labels for training from sites with varying land cover characteristics. The trained models were evaluated on 277 images and 2642 labels in the test dataset, and their performance was compared using Precision, Recall, and Average Precision (AP0.5–0.95). The results indicated that reduced spatial resolution, dense shrub cover, and shadows diminish the model's ability to distinguish cattle from the background. The YOLOv8m architecture achieved the best AP0.5–0.95 accuracy of 39.6% with Precision and Recall of 91.0% and 83.4%, respectively. Despite its superior performance, YOLOv8m had the highest counting error of −8%. By contrast, YOLOv5m with AP0.5–0.95 of 39.3% attained the most accurate cattle count with RMSE of 1.3 and R2 of 0.98 for variable cattle herd densities. These results highlight that a model with high AP0.5–0.95 detection accuracy may struggle with counting cattle accurately. Nevertheless, these findings suggest the potential to upscale aerial-imagery-trained object detection models to satellite imagery for conducting cattle censuses over large areas. In addition, accurate cattle counts will support sustainable pastureland management by ensuring stock numbers do not exceed the forage available for grazing, thereby mitigating overgrazing. [ABSTRACT FROM AUTHOR]

This work proposes a methodology for noise removal, separation, and classification of partial discharges in electrical system assets. Partial discharge analysis is an essential method for fault detection and evaluation of the operational conditions of high-voltage equipment. However, it faces several limitations in field measurements due to interference from radio signals, television transmissions, WiFi, corona signals, and multiple sources of partial discharges. To address these challenges, we propose the development of a clustering model to identify partial discharge sources and a classification model to identify the types of discharges. New features extracted from pulses are introduced to model the clustering and classification of discharge sources. The methodology is tested in the laboratory with controlled partial discharge sources, and field tests are conducted in substations to assess its practical applicability. The results of laboratory tests achieved an accuracy of 85% in classifying discharge sources. Field tests were performed in a substation of the Eletrobras group, allowing the identification of at least three potentially defective current transformers. [ABSTRACT FROM AUTHOR]

Featured Application: Here, we propose the integration of network analyses and 3D clustering techniques to comprehensively detect statistical patterns in the artefact spatial distribution of an archaeological site. In recent years, the most advanced pioneering techniques in the computing field have found application in assorted areas. Deep learning approaches, including artificial neural networks (ANNs), have become popular thanks to their ability to draw inferences from intricate and seemingly unconnected datasets. Additionally, 3D clustering techniques manage to associate groups of elements by identifying the specific inherent structures exhibited by such objects based on similarity measures. Generally, the characteristics of archaeological information gathered after extraction operations align with the previously mentioned challenges. Hence, an excavation could be an opportunity to use these prior innovative computing approaches. Our objective is to integrate software techniques to organise recovered artefacts and derive logical conclusions from their spatial location and the correlation between tangible attributes. These results can statistically improve our approach to investigations and provide a mathematical interpretation of archaeological excavations. [ABSTRACT FROM AUTHOR]

In RNA-seq data analysis, condensing the gene count matrix size is pivotal for downstream investigations, particularly pathway analysis. For this purpose, harnessing machine learning attracts increasing interest, while conventional methodologies depend on p-value comparisons. In this study, 20 tissue samples from real-world cervical cancers were subjected to sequencing, followed by the application of the Mclust algorithm to delineate an optimal cluster. By stratifying tumor budding into high and low groups and quantifying the epithelial-to-mesenchymal transition (EMT) score to scrutinize tumor budding, we discerned 24 EMT-related genes, with 5 showing strong associations with cervical cancer prognosis. Our observations elucidate a biological flow wherein EMT, Matrix Metallopep-tidase 2 (MMP2), and extracellular matrix (ECM) degradation are interconnected, ultimately leading to collagen type VI and exacerbating the prognosis of cervical cancer. The present study underscores an alternative method for selecting useful EMT-related genes by employing an appropriate clustering algorithm, thereby avoiding classical methods while unveiling novel insights into cervical cancer etiology and prognosis. Moreover, when comparing high and low tumor budding, collagen type VI emerges as a potential gene marker for the prognosis of cervical cancer. [ABSTRACT FROM AUTHOR]

To quickly obtain rice plant phenotypic traits, this study put forward the computational process of six rice phenotype features (e.g., crown diameter, perimeter of stem, plant height, surface area, volume, and projected leaf area) using terrestrial laser scanning (TLS) data, and proposed the extraction method for the tiller number of rice plants. Specifically, for the first time, we designed and developed an automated phenotype extraction tool for rice plants with a three-layer architecture based on the PyQt5 framework and Open3D library. The results show that the linear coefficients of determination (R2) between the measured values and the extracted values marked a better reliability among the selected four verification features. The root mean square error (RMSE) of crown diameter, perimeter of stem, and plant height is stable at the centimeter level, and that of the tiller number is as low as 1.63. The relative root mean squared error (RRMSE) of crown diameter, plant height, and tiller number stays within 10%, and that of perimeter of stem is 18.29%. In addition, the user-friendly automatic extraction tool can efficiently extract the phenotypic features of rice plant, and provide a convenient tool for quickly gaining phenotypic trait features of rice plant point clouds. However, the comparison and verification of phenotype feature extraction results supported by more rice plant sample data, as well as the improvement of accuracy algorithms, remain as the focus of our future research. The study can offer a reference for crop phenotype extraction using 3D point clouds. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for electricity consumption profiling in households through the fusion of usage data for individual smart devices. The novelty of the approach consists of leveraging the data representing the usage of individual appliances rather than using direct measurements of energy consumption. Our methodology focuses on merging signals representing the interaction of the user with the device to compute patterns in the total energy consumption per household. Subsequently, we apply data mining techniques—specifically, unsupervised clustering—to analyze the resulting time-series data representing daily energy consumption. Through this approach, we aim to identify and characterize patterns in energy usage within households, enabling insights for energy optimization strategies and resource allocation. This information can be further used in practical tasks, such as flattening energy consumption. The proposed approach offers an alternative to the direct measurement of energy usage, considering the potential for sensor failure or malfunction. This underscores the importance of implementing a complementary method for verifying and validating energy consumption data. [ABSTRACT FROM AUTHOR]

Continuous discovery and update of applications or their boundaries running in cloud environments in an automatic way is a highly required function of modern data center operation solutions. Prior attempts to address this problem within various products or projects were/are applying rule-driven approaches or machine learning techniques on specific types of data–network traffic as well as property/configuration data of infrastructure objects, which all have their drawbacks in effectively identifying roles of those resources. The current proposal (ADLog) leverages log data of sources, which contain incomparably richer contextual information, and demonstrates a reliable way of discriminating application objects. Specifically, using native constructs of VMware Aria Operations for Logs in terms of event types and their distributions, we group those entities, which then can be potentially enriched with indicative tags automatically and recommended for further management tasks and policies. Our methods differentiate not only diverse kinds of applications, but also their specific deployments, thus providing hierarchical representation of the applications in time and topology. For several applications under Aria Ops management in our experimental test bed, we discover those in terms of similarity behavior of their components with a high accuracy. The validation of the proposal paves the path for an AI-driven solution in cloud management scenarios. [ABSTRACT FROM AUTHOR]

Despite the significant impacts of biomass burning (BB) on global climate change and regional air pollution, there is a relative lack of research on the temporal trends and geographic patterns of BB in Northeast China (NEC). This study investigates the spatial–temporal distribution of BB and its impact on the atmospheric environment in the NEC region during 2004 to 2023 based on remote sensing satellite data and reanalyzed data, using the Siegel's Repeated Median Estimator and Mann–Kendall test for trend analysis, HDBSCAN to identify significant BB change regions, and Moran's Index to examine the spatial autocorrelation of BB. The obtained results indicate a fluctuating yet overall increasing BB trend, characterized by annual increases of 759 for fire point counts (FPC) and 12,000 MW for fire radiated power (FRP). BB predominantly occurs in the Songnen Plain (SNP), Sanjiang Plain (SJP), Liaohe Plain (LHP), and the transitional area between SNP and the adjacent Greater Khingan Mountains (GKM) and Lesser Khingan Mountains (LKM). Cropland and urban areas exhibit the highest growth in BB trends, each surpassing 60% (p < 0.05), with the most significant growth cluster spanning 68,634.9 km2. Seasonal analysis shows that BB peaks in spring and autumn, with spring experiencing the highest severity. The most critical periods for BB are March–April and October–November, during which FPC and FRP contribute to over 80% of the annual total. This trend correlates with spring planting and autumn harvesting, where cropland FPC constitutes 71% of all land-cover types involved in BB. Comparative analysis of the aerosol extinction coefficient (AEC) between areas with increasing and decreasing BB indicates higher AEC in BB increasing regions, especially in spring, with the vertical transport of BB reaching up to 1.5 km. County-level spatial autocorrelation analysis indicates high–high clustering in the SNP and SJP, with a notable resurgence of autocorrelation in the SNP, suggesting the need for coordinated provincial prevention and control efforts. Finally, our analysis of the impact of BB on atmospheric pollutants shows that there is a correlation between FRP and pollutants, with correlations for PM2.5, PM10, and CO of 0.4, 0.4, and 0.5, respectively. In addition, the impacts of BB vary by region and season, with the most significant impacts occurring in the spring, especially in the SNP, which requires more attention. In summary, considering the escalating BB trend in NEC and its significant effect on air quality, this study highlights the urgent necessity for improved monitoring and strategic interventions. [ABSTRACT FROM AUTHOR]

Induction motors make up approximately 80% of the electric motors in the railway sector due to their robustness, high efficiency, and low maintenance cost. Nevertheless, these motors are subject to failures which can lead to costly downtime and service interruptions. In recent years, there has been a growing interest in developing fault diagnosis systems for railway traction motors using advanced non-invasive detection and data analysis techniques. Implementing these methods in railway applications can prove challenging due to variable speed and low-load operating conditions, as well as the use of inverter-fed motor drives. This comprehensive review paper summarizes general methods of fault diagnosis for induction machines. It details the faults seen in induction motors, the most relevant signals measured for fault detection, the signal processing techniques for fault extraction as well as some classification algorithms for diagnosis purposes. By giving the advantages and drawbacks of each technique, it helps select the appropriate method that could address the challenges of railway applications. [ABSTRACT FROM AUTHOR]

The benefits of ideation for both industry and academia alike have been outlined by countless studies, leading to research into various approaches attempting to add new ideation methods or examine how the quality of the ideas and solutions created can be measured. Although AI-based approaches are being researched, there is no attempt to provide the ideation participants with information that inspire new ideas and solutions in real time. Our proposal presents a novel and intuitive approach that supports users in real time by providing them with relevant information as they conduct ideation. By analyzing their ideas within the respective ideation sessions, our approach recommends items of interest with high contextual similarity to the proposed ideas, allowing users to skim through, for example, publications and inspire new ideas quickly. The recommendations also evolve in real time. As more ideas are written during the ideation session, the recommendations become more precise. This real-time approach is instantiated with various ideation methods as a proof of concept, and various models are evaluated and compared to identify the best model for working with ideas. [ABSTRACT FROM AUTHOR]

Background: This paper examines scientific papers in the field of digital twins to explore the different areas of application in supply chains. Methods: Using a machine learning-based topic modeling approach, this study aims to provide insights into the key areas of supply chain management that benefit from digital twin capabilities. Results: The research findings highlight key priorities in the areas of infrastructure, construction, business, technology, manufacturing, blockchain, and agriculture, providing a comprehensive perspective. Conclusions: Our research findings confirm several recommendations. First, the machine learning-based model identifies new areas that are not addressed in the human review results. Second, while the human review results put more emphasis on practicality, such as management activities, processes, and methods, the machine learning results pay more attention to macro perspectives, such as infrastructure, technology, and business. Third, the machine learning-based model is able to extract more granular information; for example, it identifies core technologies beyond digital twins, including AI/reinforcement learning, picking robots, cybersecurity, 5G networks, the physical internet, additive manufacturing, and cloud manufacturing. [ABSTRACT FROM AUTHOR]

In decentralized systems, the quest for heightened security and integrity within blockchain networks becomes an issue. This survey investigates anomaly detection techniques in blockchain ecosystems through the lens of unsupervised learning, delving into the intricacies and going through the complex tapestry of abnormal behaviors by examining avant-garde algorithms to discern deviations from normal patterns. By seamlessly blending technological acumen with a discerning gaze, this survey offers a perspective on the symbiotic relationship between unsupervised learning and anomaly detection by reviewing this problem with a categorization of algorithms that are applied to a variety of problems in this field. We propose that the use of unsupervised algorithms in blockchain anomaly detection should be viewed not only as an implementation procedure but also as an integration procedure, where the merits of these algorithms can effectively be combined in ways determined by the problem at hand. In that sense, the main contribution of this paper is a thorough study of the interplay between various unsupervised learning algorithms and how this can be used in facing malicious activities and behaviors within public and private blockchain networks. The result is the definition of three categories, the characteristics of which are recognized in terms of the way the respective integration takes place. When implementing unsupervised learning, the structure of the data plays a pivotal role. Therefore, this paper also provides an in-depth presentation of the data structures commonly used in unsupervised learning-based blockchain anomaly detection. The above analysis is encircled by a presentation of the typical anomalies that have occurred so far along with a description of the general machine learning frameworks developed to deal with them. Finally, the paper spotlights challenges and directions that can serve as a comprehensive compendium for future research efforts. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for hierarchical image segmentation based on the nonsymetry and anti‐packing pattern representation model (NAM) and the hierarchical density‐based spatial clustering of application with noise (HDBSCAN). The proposed framework consists of two phases. In the first phase, a super‐pixel generation algorithm base on NAM is proposed. In the second phase, instead of defining an affinity matrix to merge similar regions using spatial clustering, the distance matrix defined by different region features is directly fitted into an HDBSCAN clustering module in order to merge similar regions efficiently. Similar adjacent regions can be merged into larger ones progressively and form a segmentation dendrogram for image segmentation with the clustering module. The experiments show that the proposed algorithm has a comparable or even better performance compared to the state‐of‐the‐art hierarchical image segmentation algorithms while having much less time and memory consumption. [ABSTRACT FROM AUTHOR]

With the vast amount of social media posts available online, topic modeling and sentiment analysis have become central methods to better understand and analyze online behavior and opinion. However, semantic and sentiment analysis have rarely been combined for joint topic-sentiment modeling which yields semantic topics associated with sentiments. Recent breakthroughs in natural language processing have also not been leveraged for joint topic-sentiment modeling so far. Inspired by these advancements, this paper presents a novel framework for joint topic-sentiment modeling of short texts based on pre-trained language models and a clustering approach. The method leverages techniques from dimensionality reduction and clustering for which multiple algorithms were considered. All configurations were experimentally compared against existing joint topic-sentiment models and an independent sequential baseline. Our framework produced clusters with semantic topic quality scores of up to 0.23 while the best score among the previous approaches was 0.12 . The sentiment classification accuracy increased from 0.35 to 0.72 and the uniformity of sentiments within the clusters reached up to 0.9 in contrast to the baseline of 0.56 . The presented approach can benefit various research areas such as disaster management where sentiments associated with topics can provide practical useful information. [ABSTRACT FROM AUTHOR]