arXiv subjects

Kenneth E. Barner

Publications and source records attributed to Kenneth E. Barner.

17 recordsLinked to original sources

arXiv2026

Echoes in the Sky: Computational Thematic Analysis of Online Public Discourse on Bluesky Across Trump's Reelection

As political disruption intensifies online discourse, Bluesky has become an important platform for political discussion and public reaction. In this study, we examine large-scale discourse on Bluesky related to U.S. policy developments associated with the Trump administration. Using the historical retrieval API, we collected all available posts matching Trump and related keywords from 2019 to 2026, yielding 38.5 million posts. We leverage a large language model (LLM)-assisted clustering pipeline, combined with human validation, to identify 14 interpretable thematic domains in English-language posts and 19 thematic categories across 258 executive orders (EOs) signed between January 20, 2025, and May 1, 2026. Our findings identify several dominant themes in Bluesky discourse, including executive governance, political identity, and national security, as well as recurring themes in EOs, including executive task forces, border enforcement, and foreign policy. We also find substantial variation in the persistence and volatility of issue attention, accompanied by an increasing proportion of negative sentiment over time. The dataset and resources are publicly available at https://github.com/Sensify-Lab/Echoes-in-the-Sky

cs.HC↗

arXiv2026

"The explanation makes sense": An Empirical Study on LLM Performance in News Classification and its Influence on Judgment in Human-AI Collaborative Annotation

The spread of media bias is a significant concern as political discourse shapes beliefs and opinions. Addressing this challenge computationally requires improved methods for interpreting news. While large language models (LLMs) can scale classification tasks, concerns remain about their trustworthiness. To advance human-AI collaboration, we investigate the feasibility of using LLMs to classify U.S. news by political ideology and examine their effect on user decision-making. We first compared GPT models with prompt engineering to state-of-the-art supervised machine learning on a 34k public dataset. We then collected 17k news articles and tested GPT-4 predictions with brief and detailed explanations. In a between-subjects study (N=124), we evaluated how LLM-generated explanations influence human annotation, judgment, and confidence. Results show that AI assistance significantly increases confidence ($p<.001$), with detailed explanations more persuasive and more likely to alter decisions. We highlight recommendations for AI explanations through thematic analysis and provide our dataset for further research.

cs.HC↗

arXiv2026

Wisdom of the LLM Crowd: A Large Scale Benchmark of Multi-Label U.S. Election-Related Harmful Social Media Content

The spread of election misinformation and harmful political content conveys misleading narratives and poses a serious threat to democratic integrity. Detecting harmful content at early stages is essential for understanding and potentially mitigating its downstream spread. In this study, we introduce USE24-XD, a large-scale dataset of nearly 100k posts collected from X (formerly Twitter) during the 2024 U.S. presidential election cycle, enriched with spatio-temporal metadata. To substantially reduce the cost of manual annotation while enabling scalable categorization, we employ six large language models (LLMs) to systematically annotate posts across five nuanced categories: Conspiracy, Sensationalism, Hate Speech, Speculation, and Satire. We validate LLM annotations with crowdsourcing (n = 34) and benchmark them against human annotators. Inter-rater reliability analyses show comparable agreement patterns between LLMs and humans, with LLMs exhibiting higher internal consistency and achieving up to 0.90 recall on Speculation. We apply a wisdom-of-the-crowd approach across LLMs to aggregate annotations and curate a robust multi-label dataset. 60% of posts receive at least one label. We further analyze how human annotator demographics, including political ideology and affiliation, shape labeling behavior, highlighting systematic sources of subjectivity in judgments of harmful content. The USE24-XD dataset is publicly released to support future research.

cs.HC↗

arXiv2025

MalVis: A Large-Scale Image-Based Framework and Dataset for Advancing Android Malware Classification

As technology advances, Android malware continues to pose significant threats to devices and sensitive data. The open-source nature of the Android OS and the availability of its SDK contribute to this rapid growth. Traditional malware detection techniques, such as signature-based, static, and dynamic analysis, struggle to detect obfuscated threats that use encryption, packing, or compression. While deep learning (DL)-based visualization methods have been proposed, they often fail to highlight the critical malicious features effectively. This research introduces MalVis, a unified visualization framework that integrates entropy and N-gram analysis to emphasize structural and anomalous patterns in malware bytecode. MalVis addresses key limitations of prior methods, including insufficient feature representation, poor interpretability, and limited data accessibility. The framework leverages a newly introduced large-scale dataset, the MalVis dataset, containing over 1.3 million visual samples across nine malware classes and one benign class. We evaluate MalVis against state-of-the-art visualization techniques using leading CNN models: MobileNet-V2, DenseNet201, ResNet50, and Inception-V3. To enhance performance and reduce overfitting, we implement eight ensemble learning strategies. Additionally, an undersampling technique mitigates class imbalance in the multiclass setting. MalVis achieves strong results: 95.19% accuracy, 90.81% F1-score, 92.58% precision, 89.10% recall, 87.58% MCC, and 98.06% ROC-AUC. These findings demonstrate the effectiveness of MalVis in enabling accurate, interpretable malware detection and providing a valuable resource for security research and applications.

cs.CR↗

arXiv2023

MMASD: A Multimodal Dataset for Autism Intervention Analysis

Autism spectrum disorder (ASD) is a developmental disorder characterized by significant social communication impairments and difficulties perceiving and presenting communication cues. Machine learning techniques have been broadly adopted to facilitate autism studies and assessments. However, computational models are primarily concentrated on specific analysis and validated on private datasets in the autism community, which limits comparisons across models due to privacy-preserving data sharing complications. This work presents a novel privacy-preserving open-source dataset, MMASD as a MultiModal ASD benchmark dataset, collected from play therapy interventions of children with Autism. MMASD includes data from 32 children with ASD, and 1,315 data samples segmented from over 100 hours of intervention recordings. To promote public access, each data sample consists of four privacy-preserving modalities of data; some of which are derived from original videos: (1) optical flow, (2) 2D skeleton, (3) 3D skeleton, and (4) clinician ASD evaluation scores of children, e.g., ADOS scores. MMASD aims to assist researchers and therapists in understanding children's cognitive status, monitoring their progress during therapy, and customizing the treatment plan accordingly. It also has inspiration for downstream tasks such as action quality assessment and interpersonal synchrony estimation. MMASD dataset can be easily accessed at https://github.com/Li-Jicheng/MMASD-A-Multimodal-Dataset-for-Autism-Intervention-Analysis.

cs.CV↗

arXiv2023

Social Visual Behavior Analytics for Autism Therapy of Children Based on Automated Mutual Gaze Detection

Social visual behavior, as a type of non-verbal communication, plays a central role in studying social cognitive processes in interactive and complex settings of autism therapy interventions. However, for social visual behavior analytics in children with autism, it is challenging to collect gaze data manually and evaluate them because it costs a lot of time and effort for human coders. In this paper, we introduce a social visual behavior analytics approach by quantifying the mutual gaze performance of children receiving play-based autism interventions using an automated mutual gaze detection framework. Our analysis is based on a video dataset that captures and records social interactions between children with autism and their therapy trainers (N=28 observations, 84 video clips, 21 Hrs duration). The effectiveness of our framework was evaluated by comparing the mutual gaze ratio derived from the mutual gaze detection framework with the human-coded ratio values. We analyzed the mutual gaze frequency and duration across different therapy settings, activities, and sessions. We created mutual gaze-related measures for social visual behavior score prediction using multiple machine learning-based regression models. The results show that our method provides mutual gaze measures that reliably represent (or even replace) the human coders' hand-coded social gaze measures and effectively evaluates and predicts ASD children's social visual performance during the intervention. Our findings have implications for social interaction analysis in small-group behavior assessments in numerous co-located settings in (special) education and in the workplace.

cs.HC↗

arXiv2020

A Probabilistic Representation of Deep Learning for Improving The Information Theoretic Interpretability

In this paper, we propose a probabilistic representation of MultiLayer Perceptrons (MLPs) to improve the information-theoretic interpretability. Above all, we demonstrate that the activations being i.i.d. is not valid for all the hidden layers of MLPs, thus the existing mutual information estimators based on non-parametric inference methods, e.g., empirical distributions and Kernel Density Estimate (KDE), are invalid for measuring the information flow in MLPs. Moreover, we introduce explicit probabilistic explanations for MLPs: (i) we define the probability space (Omega_F, t, P_F) for a fully connected layer f and demonstrate the great effect of an activation function on the probability measure P_F ; (ii) we prove the entire architecture of MLPs as a Gibbs distribution P; and (iii) the back-propagation aims to optimize the sample space Omega_F of all the fully connected layers of MLPs for learning an optimal Gibbs distribution P* to express the statistical connection between the input and the label. Based on the probabilistic explanations for MLPs, we improve the information-theoretic interpretability of MLPs in three aspects: (i) the random variable of f is discrete and the corresponding entropy is finite; (ii) the information bottleneck theory cannot correctly explain the information flow in MLPs if we take into account the back-propagation; and (iii) we propose novel information-theoretic explanations for the generalization of MLPs. Finally, we demonstrate the proposed probabilistic representation and information-theoretic explanations for MLPs in a synthetic dataset and benchmark datasets.

cs.LG↗

arXiv2020

PAC-Bayesian Generalization Bounds for MultiLayer Perceptrons

We study PAC-Bayesian generalization bounds for Multilayer Perceptrons (MLPs) with the cross entropy loss. Above all, we introduce probabilistic explanations for MLPs in two aspects: (i) MLPs formulate a family of Gibbs distributions, and (ii) minimizing the cross-entropy loss for MLPs is equivalent to Bayesian variational inference, which establish a solid probabilistic foundation for studying PAC-Bayesian bounds on MLPs. Furthermore, based on the Evidence Lower Bound (ELBO), we prove that MLPs with the cross entropy loss inherently guarantee PAC- Bayesian generalization bounds, and minimizing PAC-Bayesian generalization bounds for MLPs is equivalent to maximizing the ELBO. Finally, we validate the proposed PAC-Bayesian generalization bound on benchmark datasets.

cs.LG↗

arXiv2020

Graph Neural Networks for Image Understanding Based on Multiple Cues: Group Emotion Recognition and Event Recognition as Use Cases

A graph neural network (GNN) for image understanding based on multiple cues is proposed in this paper. Compared to traditional feature and decision fusion approaches that neglect the fact that features can interact and exchange information, the proposed GNN is able to pass information among features extracted from different models. Two image understanding tasks, namely group-level emotion recognition (GER) and event recognition, which are highly semantic and require the interaction of several deep models to synthesize multiple cues, were selected to validate the performance of the proposed method. It is shown through experiments that the proposed method achieves state-of-the-art performance on the selected image understanding tasks. In addition, a new group-level emotion recognition database is introduced and shared in this paper.

cs.CV↗

arXiv2020

Audio-video Emotion Recognition in the Wild using Deep Hybrid Networks

This paper presents an audiovisual-based emotion recognition hybrid network. While most of the previous work focuses either on using deep models or hand-engineered features extracted from images, we explore multiple deep models built on both images and audio signals. Specifically, in addition to convolutional neural networks (CNN) and recurrent neutral networks (RNN) trained on facial images, the hybrid network also contains one SVM classifier trained on holistic acoustic feature vectors, one long short-term memory network (LSTM) trained on short-term feature sequences extracted from segmented audio clips, and one Inception(v2)-LSTM network trained on image-like maps, which are built based on short-term acoustic feature sequences. Experimental results show that the proposed hybrid network outperforms the baseline method by a large margin.

cs.CV↗

arXiv2019

Explicitly Bayesian Regularizations in Deep Learning

Generalization is essential for deep learning. In contrast to previous works claiming that Deep Neural Networks (DNNs) have an implicit regularization implemented by the stochastic gradient descent, we demonstrate explicitly Bayesian regularizations in a specific category of DNNs, i.e., Convolutional Neural Networks (CNNs). First, we introduce a novel probabilistic representation for the hidden layers of CNNs and demonstrate that CNNs correspond to Bayesian networks with the serial connection. Furthermore, we show that the hidden layers close to the input formulate prior distributions, thus CNNs have explicitly Bayesian regularizations based on the Bayesian regularization theory. In addition, we clarify two recently observed empirical phenomena that are inconsistent with traditional theories of generalization. Finally, we validate the proposed theory on a synthetic dataset

cs.LG↗

arXiv2019

A Probabilistic Representation of Deep Learning

In this work, we introduce a novel probabilistic representation of deep learning, which provides an explicit explanation for the Deep Neural Networks (DNNs) in three aspects: (i) neurons define the energy of a Gibbs distribution; (ii) the hidden layers of DNNs formulate Gibbs distributions; and (iii) the whole architecture of DNNs can be interpreted as a Bayesian neural network. Based on the proposed probabilistic representation, we investigate two fundamental properties of deep learning: hierarchy and generalization. First, we explicitly formulate the hierarchy property from the Bayesian perspective, namely that some hidden layers formulate a prior distribution and the remaining layers formulate a likelihood distribution. Second, we demonstrate that DNNs have an explicit regularization by learning a prior distribution and the learning algorithm is one reason for decreasing the generalization ability of DNNs. Moreover, we clarify two empirical phenomena of DNNs that cannot be explained by traditional theories of generalization. Simulation results validate the proposed probabilistic representation and the insights into these properties of deep learning based on a synthetic dataset.

cs.LG↗

arXiv2019

Bayesian Convolutional Neural Networks for Compressed Sensing Restoration

Deep Neural Networks (DNNs) have aroused great attention in Compressed Sensing (CS) restoration. However, the working mechanism of DNNs is not explainable, thereby it is unclear that how to design an optimal DNNs for CS restoration. In this paper, we propose a novel statistical framework to explain DNNs, which proves that the hidden layers of DNNs are equivalent to Gibbs distributions and interprets DNNs as a Bayesian hierarchical model. The framework provides a Bayesian perspective to explain the working mechanism of DNNs, namely some hidden layers learn a prior distribution and other layers learn a likelihood distribution. Moreover, the framework provides insights into DNNs and reveals two inherent limitations of DNNs for CS restoration. In contrast to most previous works designing an end-to-end DNNs for CS restoration, we propose a novel DNNs to model a prior distribution only, which can circumvent the limitations of DNNs. Given the prior distribution generated from the DNNs, we design a Bayesian inference algorithm to realize CS restoration in the framework of Bayesian Compressed Sensing. Finally, extensive simulations validate the proposed theory of DNNs and demonstrate that the proposed algorithm outperforms the state-of-the-art CS restoration methods.

eess.SP↗

arXiv2018

Smile detection in the wild based on transfer learning

Smile detection from unconstrained facial images is a specialized and challenging problem. As one of the most informative expressions, smiles convey basic underlying emotions, such as happiness and satisfaction, which lead to multiple applications, e.g., human behavior analysis and interactive controlling. Compared to the size of databases for face recognition, far less labeled data is available for training smile detection systems. To leverage the large amount of labeled data from face recognition datasets and to alleviate overfitting on smile detection, an efficient transfer learning-based smile detection approach is proposed in this paper. Unlike previous works which use either hand-engineered features or train deep convolutional networks from scratch, a well-trained deep face recognition model is explored and fine-tuned for smile detection in the wild. Three different models are built as a result of fine-tuning the face recognition model with different inputs, including aligned, unaligned and grayscale images generated from the GENKI-4K dataset. Experiments show that the proposed approach achieves improved state-of-the-art performance. Robustness of the model to noise and blur artifacts is also evaluated in this paper.

cs.CV↗

arXiv2017

Exploiting Restricted Boltzmann Machines and Deep Belief Networks in Compressed Sensing

This paper proposes a CS scheme that exploits the representational power of restricted Boltzmann machines and deep learning architectures to model the prior distribution of the sparsity pattern of signals belonging to the same class. The determined probability distribution is then used in a maximum a posteriori (MAP) approach for the reconstruction. The parameters of the prior distribution are learned from training data. The motivation behind this approach is to model the higher-order statistical dependencies between the coefficients of the sparse representation, with the final goal of improving the reconstruction. The performance of the proposed method is validated on the Berkeley Segmentation Dataset and the MNIST Database of handwritten digits.

cs.LG↗

arXiv2014

Exploiting Prior Knowledge in Compressed Sensing Wireless ECG Systems

Recent results in telecardiology show that compressed sensing (CS) is a promising tool to lower energy consumption in wireless body area networks for electrocardiogram (ECG) monitoring. However, the performance of current CS-based algorithms, in terms of compression rate and reconstruction quality of the ECG, still falls short of the performance attained by state-of-the-art wavelet based algorithms. In this paper, we propose to exploit the structure of the wavelet representation of the ECG signal to boost the performance of CS-based methods for compression and reconstruction of ECG signals. More precisely, we incorporate prior information about the wavelet dependencies across scales into the reconstruction algorithms and exploit the high fraction of common support of the wavelet coefficients of consecutive ECG segments. Experimental results utilizing the MIT-BIH Arrhythmia Database show that significant performance gains, in terms of compression rate and reconstruction quality, can be obtained by the proposed algorithms compared to current CS-based methods.

cs.CE↗

arXiv2013

Lorentzian Iterative Hard Thresholding: Robust Compressed Sensing with Prior Information

Commonly employed reconstruction algorithms in compressed sensing (CS) use the $L_2$ norm as the metric for the residual error. However, it is well-known that least squares (LS) based estimators are highly sensitive to outliers present in the measurement vector leading to a poor performance when the noise no longer follows the Gaussian assumption but, instead, is better characterized by heavier-than-Gaussian tailed distributions. In this paper, we propose a robust iterative hard Thresholding (IHT) algorithm for reconstructing sparse signals in the presence of impulsive noise. To address this problem, we use a Lorentzian cost function instead of the $L_2$ cost function employed by the traditional IHT algorithm. We also modify the algorithm to incorporate prior signal information in the recovery process. Specifically, we study the case of CS with partially known support. The proposed algorithm is a fast method with computational load comparable to the LS based IHT, whilst having the advantage of robustness against heavy-tailed impulsive noise. Sufficient conditions for stability are studied and a reconstruction error bound is derived. We also derive sufficient conditions for stable sparse signal recovery with partially known support. Theoretical analysis shows that including prior support information relaxes the conditions for successful reconstruction. Simulation results demonstrate that the Lorentzian-based IHT algorithm significantly outperform commonly employed sparse reconstruction techniques in impulsive environments, while providing comparable performance in less demanding, light-tailed environments. Numerical results also demonstrate that the partially known support inclusion improves the performance of the proposed algorithm, thereby requiring fewer samples to yield an approximate reconstruction.

cs.IT↗