检索结果-内蒙古大学图书馆

Applied intelligence with deep learning assisted automated sarcasm recognition in twitter data

Alexandria Engineering Journal 2025年 128卷 79-91页

作者： Alzaidi, Muhammad Swaileh A. Alsudais, Taghreed Ali Eltahir, Majdy M. Ebad, Shouki A. Alshuhail, Asma Alshahrani, Mohammed Alanazi, Sultan Department of English Language College of Language Sciences King Saud University P. O. Box 145111 Riyadh Saudi Arabia Department of Teaching and Learning College of Education and Human Development Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Information Systems Applied College at Mahayil King Khalid University Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Computer Department Applied College Najran University Najran66462 Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj16273 Saudi Arabia

Sarcasm is essential in human interaction, particularly on social networking, where individuals share their feelings through criticism, humour, and satire. Sarcasm detection is vital in understanding the context of communication and the sentiment on platforms such as Twitter. This presents sarcasm detection as a complex problem in natural language processing (NLP). The challenges and importance upsurge, particularly in languages such as Arabic and Urdu, where resources for NLP are inadequate. The classical rule-based techniques need to improve performance owing to sarcasm's context-based and subtle nature. On the other hand, the current developments in deep learning (DL) and NLP offer efficient solutions. Therefore, this study presents an Applied Intelligence with Deep Learning Assisted Automated Sarcasm Recognition Approach (AIDL-ASRA) on Twitter Data. The presented AIDL-ASRA technique concentrates on identifying sarcastic and non-sarcastic contexts in tweets. In the AIDL-ASRA technique, the initial pre-processing stage is executed with different subprocesses. Next, Global Vectors for Word Representation (GloVe)-based word embedding process occurs. The AIDL-ASRA technique utilizes the Discriminative Deep Belief Networks (DDBN) method for sarcasm recognition. The DBN model's effectiveness is improved using the cat swarm optimization (CSO) model. A set of experiments were involved in evaluating the performance of the AIDL-ASRA method under the Arabic sarcastic dataset comprising 10,000 tweets. The experimental validation of the AIDL-ASRA method attained a superior accuracy value of 91.25 % over existing techniques under distinct measures. © 2025 The Authors

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Designing semantic substrates for visual network exploration

引用

Information Visualization 2007年第4期6卷 281-300页

作者： Aris, Aleks Shneiderman, Ben Computer Science Department Human-Computer Interaction Lab. University of Maryland College Park MD United States Computer Science Department Human-Computer Interaction Lab. University of Maryland College Park MD 20742 United States

A semantic substrate is a spatial template for a network, where nodes are grouped into regions and laid out within each region according to one or more node attributes. This paper shows how users can be given control in designing their own substrates and how this ability leads to a different approach to network data exploration. Users can create a semantic substrate, enter their data, get feedback from domain experts, edit the semantic substrate, and iteratively continue this procedure until the domain experts are satisfied with the insights they have gained. We illustrate this process in two case studies with domain experts working with legal precedents and food webs. Guidelines for designing substrates are provided, including how to locate, size, and align regions in a substrate, which attributes to choose for grouping nodes into regions, how to select placement methods and which attributes to set as parameters of the selected placement method. Throughout the paper, examples are illustrated with NVSS 2.0, the network visualization tool developed to explore the semantic substrate idea. © 2007 Palgrave Macmillan Ltd. All rights reserved.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Challenging Futures: Using Chatbots to Reflect on Aging and Dementia 25

Challenging Futures: Using Chatbots to Reflect on Aging and ...

引用

Proceedings of the 2025 CHI Conference on human Factors in Computing Systems

作者： Rucha Khot Teis Arets Joel Wester Franziska Burger Niels van Berkel Rens Brankaert Wijnand IJsselsteijn Minha Lee Industrial Design Eindhoven University of Technology Eindhoven Netherlands Human-Technology Interaction Eindhoven University of Technology Eindhoven Netherlands Department of Computer Science Aalborg University Aalborg Denmark Industrial Design Engineering University of Ghent Ghent Belgium Industrial Design Eindhoven University of Technology Eindhoven Netherlands Tranzo Tilburg University Tilburg Netherlands and Fontys School of Applied Sciences Eindhoven Netherlands Human Technology Interaction Eindhoven University of Technology Eindhoven Netherlands Industrial Design Eindhoven University of Technology Eindhoven Netherlands and Centrum Wiskunde & Informatica Amsterdam Netherlands

来源：评论

学校读者我要写书评

暂无评论

Discovering Chunks in Neural Embeddings for Interpretability

arXiv

引用

arXiv 2025年

作者： Wu, Shuchen Alaniz, Stephan Schulz, Eric Akata, Zeynep Explainable Machine Learning Lab Helmholtz Munich Germany Max Planck Institute for Biological Cybernetics Germany Munich Center for Machine Learning Germany Department of Computer Science Technical University of Munich Germany Institute for Human-Centered AI Helmholtz Munich Germany

Understanding neural networks is challenging due to their high-dimensional, interacting components. Inspired by human cognition, which processes complex sensory data by chunking it into recurring entities, we propose leveraging this principle to interpret artificial neural population activities. Biological and artificial intelligence share the challenge of learning from structured, naturalistic data, and we hypothesize that the cognitive mechanism of chunking can provide insights into artificial systems. We first demonstrate this concept in recurrent neural networks (RNNs) trained on artificial sequences with imposed regularities, observing that their hidden states reflect these patterns, which can be extracted as a dictionary of chunks that influence network responses. Extending this to large language models (LLMs) like LLaMA, we identify similar recurring embedding states corresponding to concepts in the input, with perturbations to these states activating or inhibiting the associated concepts. By exploring methods to extract dictionaries of identifiable chunks across neural embeddings of varying complexity, our findings introduce a new framework for interpreting neural networks, framing their population activity as structured reflections of the data they process. © 2025, CC BY.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

We Are Sending You Back... to the Optimum! Fuzzy Time Travel Particle Swarm Optimization 28th

We Are Sending You Back... to the Optimum! Fuzzy Time Trav...

引用

28th European Conference on Applications of Evolutionary Computation, EvoApplications 2025, held as part of EvoStar 2025

作者： Papetti, Daniele M. Tangherloni, Andrea Coelho, Vasco Besozzi, Daniela Cazzaniga, Paolo Nobile, Marco S. Department of Informatics Systems and Communication University of Milano-Bicocca Milan Italy Department of Computer Science Bocconi University Milan Italy Department of Human and Social Sciences University of Bergamo Bergamo Italy Department of Environmental Sciences Informatics and Statistics Ca’ Foscari University of Venice Venice Italy Research Center Milan Italy

ISBN: (纸本)9783031900648

Particle Swarm Optimization (PSO) is a swarm intelligence meta-heuristics whose performance highly depends on the selection of its hyper-parameters, which control the particles’ exploration and exploitation capabilities during the search process. Since the tuning of the hyper-parameters is problem-dependent, settings-free methods are preferable. Fuzzy Self-Tuning PSO (FST-PSO) is a settings-free variant of PSO that exploits a Fuzzy Rule-Based System to determine the best hyper-parameter values for each particle dynamically. Despite this advantage, the optimization process might get stuck in local optima. Here, we propose a what-if strategy to generate and explore alternate swarm histories: what happens if we could go back in time and change something in the past so that one particle "was" different at the beginning of the optimization? Specifically, whenever the global best particle does not improve for a number of iterations, it is terminated and re-initialized, meanwhile sending the rest of the swarm back to the initial configuration. This approach, called "time travel" FST-PSO (FTT-PSO), works under the assumption that the convergence of any particle towards an optimum is strongly related to the influence of the global best particle. We compare the performance of FTT-PSO against FST-PSO on the benchmark suites used in IEEE CEC and GECCO competitions. Our results show that time traveling allows for outperforming both the standard and the multistart versions of FST-PSO. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Claiming success, charting the future: Micro-HCI and macro-HCI

引用

interactions 2011年第5期18卷 10-11页

作者： Shneiderman, Ben Department of Computer Science Human-Computer Interaction Laboratory University of Maryland College Park United States

HCI professionals have developed design principles, guidelines, and standards dealing with consistency, informative feedback, error prevention, shortcuts for experts, and user control. Micro-HCI researchers can take comfort in dealing with wellstated requirements, clear benchmark tasks, established measures of human performance, and effective predictive models, such as Fitts' Law. Macro-HCI researchers and developers design and build interfaces in expanding areas, such as affective experience, aesthetics, motivation, social participation, trust, empathy, responsibility, and privacy. Although micro-HCI and macro-HCI have healthy overlaps, they attract different types of researchers, practitioners, and activists, thereby further broadening the scope and impact of HCI in general. Since commercial, social, legal, and ethical considerations play an increasing role in all areas of HCI, educational curricula and professional practices need to be updated regularly;midcareer continuing education for HCI professionals will help keep them current.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Towards Understanding Interactive Sonic Gastronomy with Chefs and Diners 25

Towards Understanding Interactive Sonic Gastronomy with Chef...

引用

Proceedings of the 2025 CHI Conference on human Factors in Computing Systems

作者： Hongyue Wang Jialin Deng Linjia He Nathalie Overdevest Ryan Wee Yan Wang Phoebe O. Toups Dugas Don Samitha Elvitigala Florian Floyd Mueller Exertion Games Lab Department of Human-Centred Computing Monash University Melbourne Australia Exertion Games Lab Department of Human-Centred Computing Monash University Melbourne Australia and Diverse-ability Interaction Lab School of Computer Science Bristol United Kingdom Exertion Games Lab Department of Human-Centred Computing Monash University Melbourne Australia and Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia Exertion Games Lab Department of Human-Centred Computing Monash University Melbourne Australia and Mineral Resources Commonwealth Scientific and Industrial Research Organisation Melbourne Australia

来源：评论

学校读者我要写书评

暂无评论

BackTrace: A human-AI Collaborative Approach to Discovering Studio Backdrops in Historical Photographs 11th

BackTrace: A Human-AI Collaborative Approach to Discovering ...

引用

11th AAAI Conference on human Computation and Crowdsourcing, HCOMP 2023

作者： Lim, Jude Mohanty, Vikram Dodson, Terryl Luther, Kurt Center for Human-Computer Interaction and Department of Computer Science Virginia Tech United States

ISBN: (纸本)9781577358848

In historical photo research, the presence of painted backdrops have the potential to help identify subjects, photographers, locations, and events surrounding certain photographs. However, there are few dedicated tools or resources available to aid researchers in this largely manual task. In this paper, we propose BackTrace, a human-AI collaboration system that employs a three-step workfow to retrieve and organize historical photos with similar backdrops. BackTrace is a content-based image retrieval (CBIR) system powered by deep learning that allows for the iterative refnement of search results via user feedback. We evaluated BackTrace with mixed-methods evaluation and found that it successfully aided users in fnding photos with similar backdrops and grouping them into collections. Finally, we discuss how our fndings can be applied to other domains, as well as implications of deploying BackTrace as a crowdsourcing system. © 2023, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Photography

来源：评论

学校读者我要写书评

暂无评论

Design and evaluation of a visual acclimation aid for a semi-natural locomotion device 10

Design and evaluation of a visual acclimation aid for a semi...

引用

2015 10th IEEE Symposium on 3D User Interfaces, 3DUI 2015

作者： Nabiyouni, Mahdi Scerbo, Siroberto Devito, Vincent Smolen, Stefan Starrin, Patrick Bowman, Doug A. Center for Human-Computer Interaction Department of Computer Science Virginia Tech United States

ISBN: (纸本)9781467368865

One of the limitations of most virtual reality (VR) systems is that users cannot physically walk through large virtual environments. Many solutions have been proposed to this problem, including locomotion devices such as the Virtusphere. Such devices allow the user to employ moderately natural walking motions without physically moving through space, but may actually be difficult to use at first due to a lack of interaction fidelity. We designed and evaluated a visual aid that shows a virtual representation of the sphere to the user during an acclimation phase, reasoning that this would help users understand the forces they were feeling, plan their movements, and better control their movements. In a user study, we evaluated participants' walking performance both during and after an acclimation phase. Half of the participants used the visual aid during acclimation, while the other half had no visual aid. After acclimation, all participants performed more complex walking assessment tasks without any visual aid. The results demonstrate that use of the visual aid during acclimation was effective for improving task performance and decreasing perceived difficulty in the assessment tasks. © 2015 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Interval Player: Designing a virtual musical instrument using in-air gestures 10

Interval Player: Designing a virtual musical instrument usin...

引用

2015 10th IEEE Symposium on 3D User Interfaces, 3DUI 2015

作者： Lages, Wallace Nabiyouni, Mahdi Tibau, Javier Bowman, Doug A. Center for Human Computer Interaction Department of Computer Science Virginia Tech United States

ISBN: (纸本)9781467368865

We present a novel virtual musical instrument interface based on in-air 3D gestures called the Interval Player. Instead of specifying absolute notes, the user specifies the melodic interval between the most recent note and the next one. The non-dominant hand is used to specify chords for harmony. We discuss the principles and rationale used in the design. © 2015 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：