Article
Computer Science, Information Systems
Saurabh Sharma, Vishal Gupta
Summary: This research explores the influence of numerical features extracted from user profiles on the process of information sharing on Twitter. The study finds that user profile features have a better predictive accuracy for retweets and user behavior compared to tweet content features, and their combined use performs even better.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Construction & Building Technology
Tongping Hao, Haoliang Chang, Sisi Liang, Phil Jones, P. W. Chan, Lishuai Li, Jianxiang Huang
Summary: Urban heat disrupts park usage, and the extent of this disruption is still debated. Previous studies have used small data methods, which often contradict each other due to limitations in sample size, study duration, and study sites. This study utilized Twitter data and field studies to examine park attendance under hot weather conditions. The findings suggest that a 1°C increase in temperature corresponds to a 4% decrease in park attendance and a 1% decrease in park-related tweets. The differences between the two data sources could be attributed to indoor tweets mistakenly associated with parks. The Universal Thermal Climate Index was found to be a better predictor of thermal sensations compared to other biometeorological indicators.
BUILDING AND ENVIRONMENT
(2023)
Article
Computer Science, Artificial Intelligence
Yuh-Jen Chen, Yuh-Min Chen
Summary: Corporate credit ratings are comprehensive indicators that reflect a company's management performance, earnings quality, and future prospects. With the popularity of social media, financial institutions can use social media data to determine corporate credit ratings. This study develops a method to forecast corporate credit ratings by analyzing public opinion on social media.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Green & Sustainable Science & Technology
Mohammed Abdul-Rahman, Mayowa I. Adegoriola, Wilson Kodwo McWilson, Oluwole Soyinka, Yusuf A. Adenle
Summary: University towns in the 21st century face challenges related to urbanization, growing student population, and inadequate on-campus housing. To ensure resilience and sustainability, these challenges must be identified and addressed. This study utilized artificial intelligence and social media big data (user-generated content on Twitter) to conduct remote community resilience assessments in six university towns across different continents. By analyzing historical big data and validating the findings through an online expert survey, cultural, social, physical, economic, and institutional challenges were identified. The study demonstrates that artificial intelligence offers a convenient, cost-effective, and accurate approach to evaluating community resilience in urban areas and contributes to the understanding of research in the new normal by proving the feasibility of remote longitudinal studies.
Article
Computer Science, Interdisciplinary Applications
Afzal Badshah, Celestine Iwendi, Ateeqa Jalal, Syed Shabih Ul Hasan, Ghawar Said, Shahab S. Band, Arthur Chang
Summary: The widespread use of smart devices has led to an increase in social media engagement and workload, placing a heavy burden on mainstream networks and social media cloud servers. To address this challenge, this paper introduces the concept of Regional Computing (RC) for Social Media Platforms (SMP), which involves processing and storing data at regional computing servers before migrating to cloud servers during off-peak hours. Preliminary results show that RC effectively filters content regionally, reducing the burden on mainstream networks and minimizing delays and costs for instant communication.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Review
Environmental Studies
Hongxu Guo, Zhuoqiao Luo, Mengtian Li, Shumin Kong, Haiyan Jiang
Summary: Urban parks play a crucial role in promoting human well-being and health. Big data offers new and powerful ways to study visitors' experiences in urban parks, yet its application in this field is still limited and lacks accuracy.
Article
Environmental Sciences
Wanggi Jaung
Summary: This study used machine learning and big data analyses of global news articles to analyze changes in human-nature relations during pandemic outbreaks, emphasizing the importance of social-ecological systems in understanding indirect impacts. The study found that major pandemic impacts were linked to reduced use of cultural ecosystem services at a global scale, highlighting a challenge in adapting nature-based solutions to mitigate future pandemic risks.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Operations Research & Management Science
Taiga Saito, Shivam Gupta
Summary: This study investigates the applications of big data and social media factors in financial management, proposing three models for revenue management, interest rate modeling, and high-frequency trading equity market modeling. The research highlights the importance of including social media factors in stochastic optimization models for financial management, as social media plays a significant role in product promotion and sentiment sharing among market participants.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Geography
Hongbin He, Ranhao Sun, Jiayan Li, Wenning Li
Summary: This study quantifies the sentiment fluctuations in the Beijing metropolitan area based on Weibo social media data and investigates their spatiotemporal variations and potential drivers. The results show that sentiment is higher during holidays, while extreme precipitation, air pollution, and COVID-19 lockdown measures reduce sentiment. Spring has the highest sentiment, and moderate greenness and comfortable daily temperature also contribute to higher sentiment. Daily air pollutants such as PM2.5, NO2, and CO are negatively associated with sentiment.
Article
Business
Cecile Zachlod, Olga Samuel, Andrea Ochsner, Sarah Werthmueller
Summary: This study provides an in-depth overview of research analyzing social media data since 2017 through an extensive literature review of 94 papers. The findings reveal that there is a lack of clear definitions and common applications for social media data. The main research domains include marketing, hospitality and tourism, disaster management, and disruptive technology. Twitter is the primary source of analyzed social media data, with sentiment and content analysis being the prevailing methods. Additionally, half of the studies include practical implications, and future areas for high-quality research are suggested.
JOURNAL OF BUSINESS RESEARCH
(2022)
Article
Automation & Control Systems
Quande Qin, Zhihao Zhou, Jieying Zhou, Zhaorong Huang, Xihuan Zeng, Bi Fan
Summary: This study investigates attention and sentiment towards electric vehicles using data from social media interactions. Findings indicate that official users show higher attention towards electric vehicles, while individual users' attention is influenced by policy changes. There are variations in attention and sentiment towards electric vehicles across regions and genders.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2024)
Article
Computer Science, Software Engineering
Salih Erdem Erol, Cagla Aksoy, Seref Sagiroglu
Summary: The impact of social media platforms has drastically changed individual lifestyles, transforming individuals into assets of social media. However, challenges such as legal compliance, data confidentiality and privacy hinder the collection and processing of social big data. Despite these challenges, researchers tend to prefer using data from social media platforms and employ machine learning methods for analysis.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2023)
Article
Green & Sustainable Science & Technology
Andreu Casero-Ripolles
Summary: Interactivity is a defining characteristic of social media, and connections among users have a direct impact on political conversations. Digital discussions in the hybrid media system can influence mainstream media agendas and offline political life. The study aims to identify influencers with the highest digital authority on Twitter, revealing the expanding role of political and media elites in the digital environment and the beginning of opening up to new social actors.
Article
Computer Science, Artificial Intelligence
Arun Kumar Sangaiah, Samira Rezaei, Amir Javadpour, Weizhe Zhang
Summary: This paper presents an explainable medical recommender system that utilizes graph concepts for interpretable medical data analysis. The approach is based on community detection algorithms, which form a graph based on similarity scores between users and group individuals with common interests. Additionally, two community detection algorithms are applied to address the cold start problem and improve recommendation accuracy.
APPLIED SOFT COMPUTING
(2023)
Editorial Material
Hospitality, Leisure, Sport & Tourism
Nicholas M. Watanabe, Stephen Shapiro, Joris Drayer
Summary: Big data and analytics are now crucial in organizational operations, including in the sports management field. There are concerns about the use of enhanced analytic techniques and their impact on knowledge and theory. This special issue aims to advance our understanding of big data in sport management research and its potential for furthering scholarship in the industry.
JOURNAL OF SPORT MANAGEMENT
(2021)
Article
Computer Science, Information Systems
Huakui Zhang, Yi Cai, Haopeng Ren, Qing Li
Summary: Millions of people express their feelings and views on social media through images and texts, especially on short text platforms like Twitter or Weibo. However, existing multimodal topic models often fail to capture the characteristics of short text multimodal social media, leading to low-quality topics. To address this, we propose an unsupervised multimodal topic model (SMMTM) that can effectively model the relationships between text and images in social media posts. Experimental results on three social media datasets demonstrate the superiority of our model over existing ones.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Education & Educational Research
Xieling Chen, Di Zou, Gary Cheng, Haoran Xie, Morris Jong
Summary: Researchers and practitioners have shown increasing interest in the potential of blockchain technology to address trust, privacy, and transparency issues in smart education. The field of educational blockchain research is gaining momentum, with studies primarily published in computer science conferences. Asian countries and institutions, particularly China and India, are actively involved in this field, with close collaborations within the same regions. Blockchain is being used for online testing and learning, education data mining and analytics, resource sharing, educational record verification, and more. The study highlights the importance of integrating artificial intelligence to enhance scalability and security, as well as leveraging accumulated big data for personalized blockchain solutions that can detect abnormal behaviors.
EDUCATION AND INFORMATION TECHNOLOGIES
(2023)
Article
Education & Educational Research
Di Zou, Haoran Xie, Fu Lee Wang
Summary: This study investigated the effects of technology-enhanced peer, teacher, and self-feedback in project-based collaborative learning on students' writing, critical thinking tendency, and engagement in learning. The results showed that technology-enhanced peer and teacher feedback were more effective in collaborative writing, while peer and self-feedback were more effective in promoting critical thinking tendency and engagement in learning. Teacher feedback was more effective in enhancing cognitive engagement in learning.
JOURNAL OF COMPUTING IN HIGHER EDUCATION
(2023)
Article
Engineering, Civil
Yanhong Li, Wang Zhang, Yunjun Gao, Qing Li, Lihchyun Shu, Changyin Luo
Summary: This paper proposes a direction-aware augmented spatial keyword top-k query (DATkQ) that considers various factors to return the top-k objects. The paper focuses on answering the why-not question in DATkQs and introduces methods to refine the query direction and prune irrelevant search space. The efficiency of the proposed approach is demonstrated through experiments on real datasets.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Xieling Chen, Haoran Xie, Zongxi Li, Gary Cheng, Mingming Leng, Fu Lee Wang
Summary: With the rapid development of information technologies and artificial intelligence, smart healthcare and the integration of various healthcare data have gained significant momentum. This study provides a comprehensive analysis of information fusion for healthcare with AI, including major research topics, trends, and correlations, as well as the primary concerns of top countries/regions, institutions, and authors. The findings offer valuable insights for the future development of smart health with AI and guidance for international collaborations.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Computer Science, Artificial Intelligence
Zeyu Dai, Shengcai Liu, Qing Li, Ke Tang
Summary: In this article, a method of restricting perturbations to a small salient region to generate adversarial examples that can hardly be perceived is proposed. This approach is compatible with many existing black-box attacks and significantly improves their imperceptibility. Furthermore, a new black-box attack called Saliency Attack is introduced, which aims to refine the perturbations in the salient region for better imperceptibility. Extensive experiments demonstrate that our approach achieves much better imperceptibility scores and is also robust to different detection-based defenses.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Zongxi Li, Xianming Li, Haoran Xie, Fu Lee Wang, Mingming Leng, Qing Li, Xiaohui Tao
Summary: Researchers have found that emotion is not limited to one category in emotion-relevant classification tasks, and multiple emotions can exist together in a sentence. Recent studies have focused on using distribution or grayscale labels to enhance the classification model, providing additional information on the intensity of emotions and their correlations. This approach has been effective in overcoming overfitting and improving model robustness. However, it can also reduce the model's discriminative ability within similar emotion categories.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Computer Science, Artificial Intelligence
Lingling Xu, Haoran Xie, Zongxi Li, Fu Lee Wang, Weiming Wang, Qing Li
Summary: Sentence representation learning is an important task in natural language processing, and the quality of learned representations directly impacts downstream tasks. Pretrained Transformer-based language models like BERT have shown moderate performance on various tasks. However, the anisotropy of BERT sentence embeddings hinders good results in semantic textual similarity tasks. Contrastive learning has been shown to alleviate this problem and improve representation performance. This article provides a summary and categorization of contrastive learning-based models for sentence representations, evaluation tasks, and future research directions, along with exhaustive experiments illustrating the quantitative improvement of various strategies on sentence representations.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Xiaodong Li, Chenxin Zou, Pangjing Wu, Qing Li
Summary: The exposure to massive information in daily lives has made it necessary for people to efficiently obtain major points. This article proposes a topic sentiment summarization framework based on reaching definition (TSSRD) to generate high-quality summaries by incorporating sentiment changes and flow. Experimental results demonstrate the effectiveness of the framework.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Xinhong Chen, Qing Li, Zongxi Li, Haoran Xie, Fu Lee Wang, Jianping Wang
Summary: Recently, there have been efforts to promote the Emotion-Cause Pair Extraction (ECPE) task, as jointly extracting emotions and their causes is considered more helpful than only identifying the emotions. End-to-end approaches have become popular, but pipeline models have been underestimated despite their advantages. To address these limitations, we propose a novel two-stage model and incorporate reinforcement learning to handle cascading errors. Our model first detects emotion clauses and then recognizes cause clauses sequentially. Extensive experiments demonstrate the effectiveness of our model and the promising effect of reducing cascading errors by incorporating reinforcement learning.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Information Systems
Yuqi Bu, Liuwu Li, Jiayuan Xie, Qiong Liu, Yi Cai, Qingbao Huang, Qing Li
Summary: This article introduces a new task called scene-text oriented referring expression comprehension and proposes a scene text awareness network to address alignment and error issues. Experimental results show that the proposed method effectively comprehends scene-text oriented referring expressions and achieves excellent performance.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Huan Deng, Zhenguo Yang, Tianyong Hao, Qing Li, Wenyin Liu
Summary: This paper proposes a dense fusion transformer (DFT) framework for integrating textual, acoustic, and visual information for multimodal affective computing. DFT utilizes a modality-shared transformer (MT) module to extract modality-shared features and fuses sequential features of multiple modalities through dense fusion blocks, achieving affective predictions with a transformer.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Artificial Intelligence
Da Ren, Qing Li
Summary: This research tackles the exposure bias problem in text generative models and proposes two techniques to improve their performance. It introduces a new evaluation metric to assess the quality of generated samples and demonstrates that the proposed model outperforms traditional MLE methods without using any pretraining techniques.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jiajin Wu, Bo Yang, Runze Mao, Qing Li
Summary: Sequential recommendation systems have gained significant attention, but current models still suffer from popularity bias. To alleviate this bias, this study proposes a debiasing model that considers the dynamic user desire and conducts intervention analysis and counterfactual reasoning. The proposed model, PAUDRec, outperforms existing models while alleviating popularity bias in sequential recommendation.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.