Discrete Features Research Articles

Multivariate time series anomaly detection via separation, decomposition, and dual transformer-based autoencoder

Multivariate time series usually have entangled temporal patterns and various anomaly types. Meanwhile, they often contain both continuous and discrete features. Many existing methods directly model correlations in complex multivariate time series to conduct anomaly detection. Decomposing time series into different components, such as the overall trend and fluctuations, can contribute to better extracting semantic information and detecting anomalies. Existing decomposition-based anomaly detection methods still have several limitations. First, they directly decompose all features without considering that discrete features are unsuitable for decomposition because they do not have trends or fluctuations. Second, they adopt the same networks for different components with different characteristics, limiting their ability to extract semantic information. Moreover, due to the nature of Transformers, existing reconstruction-based methods using Transformers rarely form information bottlenecks, reducing the differentiation between the reconstruction errors of normal data and anomalies. This paper proposes a multivariate time series anomaly detection method with separation, decomposition, and dual Transformer-based autoencoder (SDDformer). Different from existing methods, SDDformer separates continuous and discrete features and only decomposes continuous features into trend and residual components. Considering the different characteristics of different components, SDDformer adopts Crossformer and the vanilla Transformer as the backbone of two different autoencoders to reconstruct the trend and residual components. Information bottlenecks are better formed using an extra token as the latent variable between the encoder and the decoder. SDDformer regards reconstructing a discrete feature as a classification task and calculates Cross-Entropy as its reconstruction error. Three different metrics are adopted in this paper to compare SDDformer with a variety of typical anomaly detection methods on public data sets, and the experimental results prove that SDDformer can achieve state-of-the-art performance.

Groundwater flow modelling in Neoproterozoic carbonate karst based on dye tracer pathways

The current study consisted of the development of a hydrogeological numerical model in the Lagoa Santa Karst Environmental Protection region, in order to represent the conduit-flow karst springs in the most well-studied karst system in Brazil. Once carbonate aquifers are characterized by a complex 3D pattern with a combination of a double porosity of matrix and conduits, two different modelling approaches were used: Equivalent Porous Medium (EPM), based on Darcy’s law, to represent laminar flow in the fractured massif and Conduit Network (CN), using Manning-Stricker Law and the discrete feature tool, to represent the karst conduits with turbulent flow. Modeling was calibrated in a steady-state and simulations of groundwater flow and an evaluation of water exchanges between the karstic aquifer and the other hydrogeological units, were conducted. The model was developed based on data available for many studies carried out in the area, including tracer-derived route data. The calibration results for spring discharges, water levels and mass balance were satisfactory and aligned with modeling good practices. In turn, the hydraulic conductivities and recharge rates obtained by back-analysis were in agreement with literature references. The regional groundwater flow was well represented and indicated how external water entrances can be relevant to explain the higher discharge rates observed in some karstic springs. In addition, the representation of conduits allowed for the simulation of tracer pathways, enabling the inference of potential flow rates to the karstic springs from the particle simulations.

Attributed Graph Force Learning.

In numerous network analysis tasks, feature representation plays an imperative role. Due to the intrinsic nature of networks being discrete, enormous challenges are imposed on their effective usage. There has been a significant amount of attention on network feature learning in recent times that has the potential of mapping discrete features into a continuous feature space. The methods, however, lack preserving the structural information owing to the utilization of random negative sampling during the training phase. The ability to effectively join attribute information to embedding feature space is also compromised. To address the shortcomings identified, a novel attribute force-based graph (AGForce) learning model is proposed that keeps the structural information intact along with adaptively joining attribute information to the node's features. To demonstrate the effectiveness of the proposed framework, comprehensive experiments on benchmark datasets are performed. AGForce based on the spring-electrical model extends opportunities to simulate node interaction for graph learning.

Evaluating different approaches to integrate genome-wide genetic diversity in spatial conservation prioritization

Locations for new protected areas should be identified with consideration of intraspecific genetic diversity because genetic variation enhances the adaptability of species to novel environmental conditions. The process of siting new protected areas is called spatial conservation prioritization and is often formulated as a mathematical problem to be solved with the aid of computer software. Integrating multidimensional continuous metrics of genome-wide genetic diversity in spatial conservation prioritization involves significant challenges in terms of computation speed and memory requirements. In this study, we tested and compared several approaches to approximate the multidimensional continuous metrics of genetic diversity using multidimensional discrete genetic clusters or unidimensional discrete conservation features. To this end, we applied two tools for spatial conservation prioritization, raptr and prioritizr, to genomic datasets of two fish species (the white seabream Diplodus sargus and the red mullet Mullus surmuletus) sampled throughout most of their distribution range in the Mediterranean Sea. We found that most of the approximations tested either did not achieve all genetic conservation targets or resulted in excessively high conservation costs. Nonetheless, approaches based on multidimensional genetic clusters allowed generating prioritizations with relatively small gaps in genetic objectives at very high computation speed. This might be an interesting option for exploratory or interactive analyses such as those performed in workshop with stakeholders.

A Learnable Discrete-Prior Fusion Autoencoder with Contrastive Learning for Tabular Data Synthesis

The actual collection of tabular data for sharing involves confidentiality and privacy constraints, leaving the potential risks of machine learning for interventional data analysis unsafely averted. Synthetic data has emerged recently as a privacy-protecting solution to address this challenge. However, existing approaches regard discrete and continuous modal features as separate entities, thus falling short in properly capturing their inherent correlations. In this paper, we propose a novel contrastive learning guided Gaussian Transformer autoencoder, termed GTCoder, to synthesize photo-realistic multimodal tabular data for scientific research. Our approach introduces a transformer-based fusion module that seamlessly integrates multimodal features, permitting for mining more informative latent representations. The attention within the fusion module directs the integrated output features to focus on critical components that facilitate the task of generating latent embeddings. Moreover, we formulate a contrastive learning strategy to implicitly constrain the embeddings from discrete features in the latent feature space by encouraging the similar discrete feature distributions closer while pushing the dissimilar further away, in order to better enhance the representation of the latent embedding. Experimental results indicate that GTCoder is effective to generate photo-realistic synthetic data, with interactive interpretation of latent embedding, and performs favorably against some baselines on most real-world and simulated datasets.

Visual Hallucination Elevates Speech Recognition

Due to the detrimental impact of noise on the conventional audio speech recognition (ASR) task, audio-visual speech recognition~(AVSR) has been proposed by incorporating both audio and visual video signals. Although existing methods have demonstrated that the aligned visual input of lip movements can enhance the robustness of AVSR systems against noise, the paired videos are not always available during inference, leading to the problem of the missing visual modality, which restricts their practicality in real-world scenarios. To tackle this problem, we propose a Discrete Feature based Visual Generative Model (DFVGM) which exploits semantic correspondences between the audio and visual modalities during training, generating visual hallucinations in lieu of real videos during inference. To achieve that, the primary challenge is to generate the visual hallucination given the noisy audio while preserving semantic correspondences with the clean speech. To tackle this challenge, we start with training the audio encoder in the Audio-Only (AO) setting, which generates continuous semantic features closely associated with the linguistic information. Simultaneously, the visual encoder is trained in the Visual-Only (VO) setting, producing visual features that are phonetically related. Next, we employ K-means to discretize the continuous audio and visual feature spaces. The discretization step allows DFVGM to capture high-level semantic structures that are more resilient to noise and generate visual hallucinations with high quality. To evaluate the effectiveness and robustness of our approach, we conduct extensive experiments on two publicly available datasets. The results demonstrate that our method achieves a remarkable 53% relative reduction (30.5%->12.9%) in Word Error Rate (WER) on average compared to the current state-of-the-art Audio-Only (AO) baselines while maintaining comparable results (< 5% difference) under the Audio-Visual (AV) setting even without video as input.

Fusion of GBDT and neural network for click-through rate estimation

Aiming at the issue that the current click-through rate prediction methods ignore the varying impacts of different input features on prediction accuracy and exhibit low accuracy when dealing with large-scale data, a click-through rate prediction method (GBIFM) which combines Gradient Boosting Decision Tree (GBDT) and Input-aware Factorization Machine (IFM) is proposed in this paper. The proposed GBIFM method employs GBDT for data processing, which can flexibly handle various types of data without the need for one-hot encoding of discrete features. An Input-aware strategy is introduced to refine the weight vector and embedding vector of each feature for different instances, adaptively learning the impact of each input vector on feature representation. Furthermore, a fully connected network is incorporated to capture high-order features in a non-linear manner, enhancing the method’s ability to express and generalize complex structured data. A comprehensive experiment is conducted on the Criteo and Avazu datasets, the results show that compared to typical methods such as DeepFM, AFM, and IFM, the proposed method GBIFM can increase the AUC value by 10% –12% and decrease the Logloss value by 6% –20%, effectively improving the accuracy of click-through rate prediction.

Local Extrema Min-Max Pattern: A novel descriptor for extracting compact and discrete features for hand gesture recognition

In this paper, a handcrafted feature descriptor namely Local Extrema Min–Max Pattern (LEMMP) is introduced for static hand gesture recognition (HGR). LEMMP thoroughly characterizes the discriminative information between a specific coefficient and its nearby neighbors within a local window. The proposed approach extracts 2nd-order local information by encoding the most informative directions contained within multiple discrete spatial associations from each neighborhood pixel using a two-structure encoding method, which helps in detecting the gray level variations that may occur in different directions. LEMMP encodes the structure of hand gestures utilizing texture information in an easy-to-understand and compact coding scheme, resulting in improved accuracy with less memory and time as compared to existing approaches. Furthermore, the features extracted by the proposed LEMMP are classified using SVM classifier. The proposed LEMMP is tested on nine benchmark HGR datasets. The experimental results and the visual analysis demonstrate that the proposed LEMMP outperforms the existing state-of-the-art approaches with an accuracy of 52%(ASL Static), 92% (MUGD Set1), 98% (MUGD Set2), 75%(MUGD Set3), 64%(MUGD Set4), 71%(MUGD Set5), 98%(ASL Digit), 85% (NUS-I Dataset), 80% (NUS-II Dataset), 99% (ASLFS A), 99% (ASLFS B), 99%(ASLFS C), 96%(ASLFS D), 99%(ASLFS E), 39% Bengali Sign Language, 70% (HG-14 Dataset) and 42% (OU Hands) respectively.

TAG-Net: Target Attitude Angle-Guided Network for Ship Detection and Classification in SAR Images

Synthetic aperture radar (SAR) ship detection and classification has gained unprecedented attention due to its important role in maritime transportation. Many deep learning-based detectors and classifiers have been successfully applied and achieved great progress. However, ships in SAR images present discrete and multi-centric features, and their scattering characteristics and edge information are sensitive to variations in target attitude angles (TAAs). These factors pose challenges for existing methods to obtain satisfactory results. To address these challenges, a novel target attitude angle-guided network (TAG-Net) is proposed in this article. The core idea of TAG-Net is to leverage TAA information as guidance and use an adaptive feature-level fusion strategy to dynamically learn more representative features that can handle the target imaging diversity caused by TAA. This is achieved through a TAA-aware feature modulation (TAFM) module. It uses the TAA information and foreground information as prior knowledge and establishes the relationship between the ship scattering characteristics and TAA information. This enables a reduction in the intra-class variability and highlights ship targets. Additionally, considering the different requirements of the detection and classification tasks for the scattering information, we propose a layer-wise attention-based task decoupling detection head (LATD). Unlike general deep learning methods that use shared features for both detection and classification tasks, LATD extracts multi-level features and uses layer attention to achieve feature decoupling and select the most suitable features for each task. Finally, we introduce a novel salient-enhanced feature balance module (SFB) to provide richer semantic information and capture the global context to highlight ships in complex scenes, effectively reducing the impact of background noise. A large-scale ship detection dataset (LSSDD+) is used to verify the effectiveness of TAG-Net, and our method achieves state-of-the-art performance.

A study on the application of discrete curvature feature extraction and optimization algorithms to battery health estimation

A study on the application of discrete curvature feature extraction and optimization algorithms to battery health estimation

Intelligent Analysis of Import and Export in Green Trade Barrier Based on Big Data Analysis

Abstract With the rapid development of economic globalisation, global economic and trade activities are escalating. However, environmental problems and the emergence of green economy, a response to these problems, has led to the widespread introduction of green trade barriers. These barriers implicitly limit the development of trade activities. This paper focuses on the export difficulties caused by green trade barriers and proposes a method to quantify discrete product characteristics, explore the internal characteristics of commodities and decide optimally on intended export regions. Firstly, the discrete feature of products is quantified by quantitative transformation method. Secondly, the quantitative data are used to derive the best decision for export regions through support vector regression (SVR) method. Particle swarm optimisation is used in optimising SVR parameters to achieve high-precision decision making. Comparison with historical data from the industry park shows the identification accuracy of the optimised SVR model to be better than that of the traditional regression model. This finding presents a novel perspective for developing import and export under the background of green trade barriers.

Attacking Click-through Rate Predictors via Generating Realistic Fake Samples

How to construct imperceptible (realistic) fake samples is critical in adversarial attacks. Due to the sample feature diversity of a recommender system (containing both discrete and continuous features), traditional gradient-based adversarial attack methods may fail to construct realistic fake samples. Meanwhile, most recommendation models adopt click-through rate (CTR) predictors, which usually utilize black-box deep models with discrete features as input. Thus, how to efficiently construct realistic fake samples for black-box recommender systems is still full of challenges. In this article, we propose a hierarchical adversarial attack method against black-box CTR models via generating realistic fake samples, named CTRAttack. To better train the generation network, the weights of its embedding layer are shared with those of the substitute model, with both the similarity loss and classification loss used to update the generation network. To ensure that the discrete features of the generated fake samples are all real, we first adopt the similarity loss to ensure that the distribution of the generated perturbed samples is sufficiently close to the distribution of the real features, and then the nearest neighbor algorithm is used to retrieve the most appropriate features for non-existent discrete features from the candidate instance set. Extensive experiments demonstrate that CTRAttack can not only effectively attack the black-box recommender systems but also improve the robustness of these models while maintaining prediction accuracy.

A Dual Robust Strategy for Removing Outliers in Multi-Beam Sounding to Improve Seabed Terrain Quality Estimation.

During the process of seabed terrain exploration using a multi-beam echo system, it is inevitable to obtain a sounding set containing anomalous points. Conventional methods for eliminating outliers are unable to reduce the disruption caused by outliers over the whole dataset. Furthermore, incomplete consideration is given to the terrain complexity, error magnitude, and outlier distribution. In order to achieve both a high-precision terrain quality estimate and quick detection of depth anomalies, this study suggests a dual robust technique. Firstly, a robust polyhedral function is utilized to solve anomaly detection for large errors. Secondly, the robust kriging algorithm is used for refined outlier removal. Ultimately, the process of dual detection and anomaly removal is achieved. The experimental results demonstrate that DRS technology has the most favorable mean square error and error fluctuation range in the test set, with values of 0.8321 and [-2.0582, 1.9209], respectively, when compared to RPF, WT, GF, and WLS-SVM schemes. Furthermore, DRS is able to adjust to various terrain complexities, discrete distribution features, and cluster outlier detection, as shown by objective indicators and visual outcome maps, guaranteeing a high-quality seabed terrain estimate.

Osteology of the two-fingered oviraptorid Oksoko avarsan (Theropoda: Oviraptorosauria)

Abstract Oviraptorosaurs are among the most diverse and best-known extinct theropod groups. Their bizarre anatomy and their social and reproductive behaviour are now well understood. Among the oviraptorid subclade, the two-fingered Oksoko avarsan is particularly well-represented. It is known from several exquisite skeletons, preserving not only the entire skeleton, but multiple stages through ontogeny, providing an exemplar for understanding the anatomy of oviraptorids and the changes that their skeletons experienced over their lifetimes. Here I comprehensively describe the osteology of Oksoko avarsan and comment on its ontogenetic variation. Excellent preservation of the specimens provides unparalleled detail into the anatomy of an oviraptorid, providing valuable context for interpreting other oviraptorosaurs. Several changes are observed to occur through ontogeny relating to robustness of the bones and proportions of the skeleton, but there is little evidence suggesting that discrete features like the cranial crest arose late in ontogeny. Instead, early development of the cranial crest in oviraptorids, and its internal connection with the nasal passages and other pneumatic spaces, argue in favour of a role in vocalization, perhaps alongside sexual display. Detailed anatomical and ontogenetic data, like those provided by known specimens of Oksoko avarsan, are necessary to help to underpin ongoing research into the palaeobiology and macroevolution of Oviraptorosauria.

Hybrid Prompt Recommendation Explanation Generation combined with Graph Encoder

Recommendation systems have been effectively utilized in various fields, but their internal decision-making methods are still largely unknown. This opaque decision-making method can greatly affect users’ trust in the recommendation system. Therefore, finding a way to explain the reasons for model decisions has become an urgent task. Previous studies often used LSTM and other models to generate recommendation explanations and explain the reasons for recommendations in text form. However, traditional methods cannot effectively use the ID information of users and items, and the text generated is highly repetitive. To solve this problem, this paper uses the method of prompt learning combined with a graph encoder to design a recommendation explanation generation model. In order to narrow the semantic gap between the ID information of users and items and natural language and capture high-level interaction information, this paper designs a graph encoder based on user similarity to learn the interactive semantic information of user and item IDs, and to construct a continuous prompt. Then, the discrete prompt composed of discrete features of users and items is combined with the continuous prompt to construct a hybrid prompt to input into the pre-trained model to generate the recommended explanation. This paper experiments on three publicly available datasets and compares them with several state-of-the-art methods to demonstrate the personalization and text quality of the generated explanations.

Multidimensional Spatial Vitality Automated Monitoring Method for Public Open Spaces Based on Computer Vision Technology: Case Study of Nanjing’s Daxing Palace Square

Assessing the vitality of public open spaces is critical in urban planning and provides insights for optimizing residents’ lives. However, prior research has fragmented study scopes and lacks fine-grained behavioral data segmentation capabilities and diverse vitality dimension assessments. We utilized computer vision technology to collect fine-grained behavioral data and proposed an automated spatial vitality monitoring framework based on discrete trajectory feature points. The framework supported the transformation of trajectory data into four multidimensional vitality indicators: crowd heat, resident behavior ratio, movement speed, and spatial participation. Subsequently, we designed manual validation mechanisms to demonstrate the monitoring framework’s efficacy and utilized the results to explore the changes in vitality, and the influencing factors, in a small public space. Discrete trajectory feature points effectively addressed the literature’s fragmented study scope and limited sample size issues. Spatial boundaries had a significantly positive impact on spatial vitality, confirming the “boundary effect” theory. The peak spatial vitality periods were from 08:30 to 09:30 and from 17:30 to 18:30. A higher enclosure degree and better rest facilities positively impacted spatial vitality, while a lower enclosure degree did not consistently suppress spatial vitality in all situations. Overall, spatial features and spatial vitality have a complex nonlinear relationship.

Recurrent Convolution Neural Network for Space Debris and Asteroids Detection and Classification on the Monitored Satellite Information Using Deep Space Network

Satellites are used for many monitoring, prediction and forecasting application operation in space , hence it has to be continuously monitored and controlled against the catastrophic damage due to collision of space debris and asteroids debris in the space. Timely and efficient Controlling of satellite will eliminate the heavy irreparable damages as number of space debris and asteroids debris is continuously increasing in the space. Hence monitoring of the satellites increases the sustainability and its safety navigation in the space operations. In order to achieve this objective, deep space network (Satellite ground station ) has to be designed as space situational awareness mechanism on basis of the detection and classification of the space objects towards providing optimal path for satellite trajectory with high processing speed and reduction of memory in data processing. In this work, a new deep learning architecture entitled as optimized recurrent convolution neural network is designed to satellite ground station towards detection and classification of space debris and asteroids debris. Initially architecture is interfaced with feature extraction technique named as principle component analysis to extract the space features and those extracted feature were detected and classified using deep learning model. In this work, convolution neural network composed of convolution layer is used to filter the discrete features, max pooling layer for downsizing the features and represent the feature map and finally fully connected layer to detect and classify the space debris and predict the optimal path for satellite trajectory on basis of the velocity of the debris in the particular orbit. Experimental results of the proposed model has been evaluated using accuracy and precision metric. Further design is implemented and verified using Xilinx Software. The performance analysis of the proposed model yields better accuracy on the classifying the monitored information on comparing with conventional approaches such as support vector machine and K- Nearest Neighbour Technique. Keywords: Satellite Collision Analysis, Deep learning, Space Debris , Asteroid Debris, Convolution Neural Network, Principle Component analysis , Deep Space Network

Absorption function loss due to the history of previous ankle sprain explored by unsupervised machine learning

BackgroundAnkle sprains are common and cause persistent ankle function reduction. To biomechanically evaluate the ankle function after ankle sprains, the ground reaction force (GRF) measurement during the single-legged landing had been used. However, previous studies focused on discrete features of vertical GRF (vGRF), which largely ignored vGRF waveform features that could better identify the ankle function. PurposeTo identify how the history of ankle sprain affect the vGRF waveform during the single-legged landing with unsupervised machine learning considering the time-series information of vGRF. MethodsEighty-seven currently healthy basketball athletes (12 athletes without ankle sprain, 49 athletes with bilateral, and 26 athletes with unilateral ankle sprain more than 6 months before the test day) performed single-legged landings from a 20 centimeters (cm) high box onto the force platform. Totally 518 trials vGRF data were collected from 87 athletes of 174 ankles, including 259 ankle sprain trials (from previous sprain ankles) and 259 non-ankle sprain trials (from without sprain ankles). The first 100 milliseconds (ms) vGRF waveforms after landing were extracted. Principal component analysis (PCA) was applied to the vGRF data, selecting 8 principal components (PCs) representing 96% of the information. Based on these 8 PCs, k-means method (k = 3) clustered the 518 trials into three clusters. Chi-square test assessed significant differences (p < 0.01) in the distribution of ankle sprain and non-ankle sprain trials among clusters. FindingsThe ankle sprain trials accounted for a significantly larger percentage (63.9%) in Cluster 3, which exhibited rapidly increased impulse vGRF waveforms with larger peaks in a short time. SignificancePCA and k-means method for vGRF waveforms during single-legged landing identified that the history of previous ankle sprains caused a loss of ankle absorption ability lasting at least 6 months from an ankle sprain.

Abstract IA020: Micronuclei are a nexus of DNA damage signaling and genomic instability

Abstract Micronuclei have classically been considered inert biomarkers of genomic instability arising from failed DNA damage repair and chromosome segregation errors in mitosis. Work from several groups including our own have now demonstrated that micronuclei are active contributors to the cellular response to DNA damage by driving chromothripsis and through induction of anti-viral gene expression programs mediated by the cGAS-STING pathway. We now show that the specific DNA damage type leading to micronuclei formation influences the capacity for cGAS localization and activation. This arises in part due to discrete chromatin features, present prior to DNA damage induction, that are retained in micronuclei several days after their formation. Together these data demonstrate that micronuclei connect the pre-damage chromatin status and the chromatin context of micronuclei-inciting lesions to the long-term signaling outcomes important for anti-tumor immunity. This finding implies that micronuclei represent archives for the nature of DNA repair failure and downstream signaling consequences. Based on this premise we will present our efforts in micronuclear proteomics where we uncover common features of micronuclei including splicing deficiencies. Such deficiencies presage exacerbated MN-associated DNA damage that is upstream of chromothripsis. These studies have direct implications for how cells sense the aftermath of DNA damage and how micronuclei contribute to ongoing genomic instability. Citation Format: Shane M. Harding. Micronuclei are a nexus of DNA damage signaling and genomic instability [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: DNA Damage Repair: From Basic Science to Future Clinical Application; 2024 Jan 9-11; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2024;84(1 Suppl):Abstract nr IA020.

Discrete Emotion Synchronicity and Video Engagement on Social Media: A Moment-to-Moment Analysis

ABSTRACT Although previous studies have identified several discrete emotion features that drive video diffusion on social media, little research has viewed the video consumption experience as a continuous communication process and combined viewer-side moment-to-moment (MTM) emotional reactions with supply-side MTM emotional dynamics. In this article, we examine how discrete emotion synchronicity, which refers to the synchronicity between MTM discrete emotions in the video content and MTM viewer emotional reactions, is associated with user engagement on video-based social media. Using a set of state-of-the-art deep learning algorithms and a regression model, we first extract discrete emotion synchronicity from videos with multimodal data streams. Then, we conduct an empirical analysis to determine the impact of discrete emotion synchronicity on user engagement. Our results indicate that discrete emotion synchronicity does not always lead to higher user engagement on video-based social media. First, discrete emotion synchronicity that increases the number of video tips (i.e., joy) cannot increase the number of saves and shares. Second, discrete emotion synchronicity (i.e., calm, solemnity, and sadness) has a negative effect on 3 types of engagement behaviors in some cases. Third, the negative effect of discrete emotion synchronicity outweighs its positive effect. Our work offers new insight into how discrete emotions facilitate or hinder user engagement in the context of video-based social media and has practical implications for firms’ marketing strategies on video-oriented social media.